Incremental algorithms on lists
Jeuring, J.T.
1991-01-01
Incremental computations can improve the performance of interactive programs such as spreadsheet programs, program development environments, text editors, etc. Incremental algorithms describe how to compute a required value depending on the input, after the input has been edited. By considering the
A New Incremental Support Vector Machine Algorithm
Directory of Open Access Journals (Sweden)
Wenjuan Zhao
2012-10-01
Full Text Available Support vector machine is a popular method in machine learning. Incremental support vector machine algorithm is ideal selection in the face of large learning data set. In this paper a new incremental support vector machine learning algorithm is proposed to improve efficiency of large scale data processing. The model of this incremental learning algorithm is similar to the standard support vector machine. The goal concept is updated by incremental learning. Each training procedure only includes new training data. The time complexity is independent of whole training set. Compared with the other incremental version, the training speed of this approach is improved and the change of hyperplane is reduced.
Incremental Supervised Subspace Learning for Face Recognition
Institute of Scientific and Technical Information of China (English)
无
2007-01-01
Subspace learning algorithms have been well studied in face recognition. Among them, linear discriminant analysis (LDA) is one of the most widely used supervised subspace learning method. Due to the difficulty of designing an incremental solution of the eigen decomposition on the product of matrices, there is little work for computing LDA incrementally. To avoid this limitation, an incremental supervised subspace learning (ISSL) algorithm was proposed, which incrementally learns an adaptive subspace by optimizing the maximum margin criterion (MMC). With the dynamically added face images, ISSL can effectively constrain the computational cost. Feasibility of the new algorithm has been successfully tested on different face data sets.
Evolving Classifiers: Methods for Incremental Learning
Hulley, Greg
2007-01-01
The ability of a classifier to take on new information and classes by evolving the classifier without it having to be fully retrained is known as incremental learning. Incremental learning has been successfully applied to many classification problems, where the data is changing and is not all available at once. In this paper there is a comparison between Learn++, which is one of the most recent incremental learning algorithms, and the new proposed method of Incremental Learning Using Genetic Algorithm (ILUGA). Learn++ has shown good incremental learning capabilities on benchmark datasets on which the new ILUGA method has been tested. ILUGA has also shown good incremental learning ability using only a few classifiers and does not suffer from catastrophic forgetting. The results obtained for ILUGA on the Optical Character Recognition (OCR) and Wine datasets are good, with an overall accuracy of 93% and 94% respectively showing a 4% improvement over Learn++.MT for the difficult multi-class OCR dataset.
Institute of Scientific and Technical Information of China (English)
LIU Ben-yong
2004-01-01
In recently proposed partial oblique projection (POP) learning, a function space is decomposed into two complementary subspaces, so that functions belonging to one of which can be optimally estimated. This paper shows that when the decomposition is specially performed so that the above subspace becomes the largest, a special learning called SPOP learning is obtained and correspondingly an incremental learning is implemented, result of which equals exactly to that of batch learning including novel data. The effectiveness of the method is illustrated by experimental results.
Incremental Alignment Manifold Learning
Institute of Scientific and Technical Information of China (English)
Zhi Han; De-Yu Meng; Zong-Sen Xu; Nan-Nan Gu
2011-01-01
A new manifold learning method, called incremental alignment method (IAM), is proposed for nonlinear dimensionality reduction of high dimensional data with intrinsic low dimensionality. The main idea is to incrementally align low-dimensional coordinates of input data patch-by-patch to iteratively generate the representation of the entire dataset. The method consists of two major steps, the incremental step and the alignment step. The incremental step incrementally searches neighborhood patch to be aligned in the next step, and the alignment step iteratively aligns the low-dimensional coordinates of the neighborhood patch searched to generate the embeddings of the entire dataset. Compared with the existing manifold learning methods, the proposed method dominates in several aspects: high efficiency, easy out-of-sample extension, well metric-preserving, and averting of the local minima issue. All these properties are supported by a series of experiments performed on the synthetic and real-life datasets. In addition, the computational complexity of the proposed method is analyzed, and its efficiency is theoretically argued and experimentally demonstrated.
Incremental multiple objective genetic algorithms.
Chen, Qian; Guan, Sheng-Uei
2004-06-01
This paper presents a new genetic algorithm approach to multiobjective optimization problems--incremental multiple objective genetic algorithms (IMOGA). Different from conventional MOGA methods, it takes each objective into consideration incrementally. The whole evolution is divided into as many phases as the number of objectives, and one more objective is considered in each phase. Each phase is composed of two stages. First, an independent population is evolved to optimize one specific objective. Second, the better-performing individuals from the single-objecive population evolved in the above stage and the multiobjective population evolved in the last phase are joined together by the operation of integration. The resulting population then becomes an initial multiobjective population, to which a multiobjective evolution based on the incremented objective set is applied. The experiment results show that, in most problems, the performance of IMOGA is better than that of three other MOGAs, NSGA-II, SPEA, and PAES. IMOGA can find more solutions during the same time span, and the quality of solutions is better.
An incremental clustering algorithm based on Mahalanobis distance
Aik, Lim Eng; Choon, Tan Wee
2014-12-01
Classical fuzzy c-means clustering algorithm is insufficient to cluster non-spherical or elliptical distributed datasets. The paper replaces classical fuzzy c-means clustering euclidean distance with Mahalanobis distance. It applies Mahalanobis distance to incremental learning for its merits. A Mahalanobis distance based fuzzy incremental clustering learning algorithm is proposed. Experimental results show the algorithm is an effective remedy for the defect in fuzzy c-means algorithm but also increase training accuracy.
Teraflop-scale Incremental Machine Learning
Özkural, Eray
2011-01-01
We propose a long-term memory design for artificial general intelligence based on Solomonoff's incremental machine learning methods. We use R5RS Scheme and its standard library with a few omissions as the reference machine. We introduce a Levin Search variant based on Stochastic Context Free Grammar together with four synergistic update algorithms that use the same grammar as a guiding probability distribution of programs. The update algorithms include adjusting production probabilities, re-using previous solutions, learning programming idioms and discovery of frequent subprograms. Experiments with two training sequences demonstrate that our approach to incremental learning is effective.
Embedded Incremental Feature Selection for Reinforcement Learning
2012-05-01
Classical reinforcement learning techniques become impractical in domains with large complex state spaces. The size of a domain’s state space is...require all the provided features. In this paper we present a feature selection algorithm for reinforcement learning called Incremental Feature
Incremental Support Vector Learning for Ordinal Regression.
Gu, Bin; Sheng, Victor S; Tay, Keng Yeow; Romano, Walter; Li, Shuo
2015-07-01
Support vector ordinal regression (SVOR) is a popular method to tackle ordinal regression problems. However, until now there were no effective algorithms proposed to address incremental SVOR learning due to the complicated formulations of SVOR. Recently, an interesting accurate on-line algorithm was proposed for training ν -support vector classification (ν-SVC), which can handle a quadratic formulation with a pair of equality constraints. In this paper, we first present a modified SVOR formulation based on a sum-of-margins strategy. The formulation has multiple constraints, and each constraint includes a mixture of an equality and an inequality. Then, we extend the accurate on-line ν-SVC algorithm to the modified formulation, and propose an effective incremental SVOR algorithm. The algorithm can handle a quadratic formulation with multiple constraints, where each constraint is constituted of an equality and an inequality. More importantly, it tackles the conflicts between the equality and inequality constraints. We also provide the finite convergence analysis for the algorithm. Numerical experiments on the several benchmark and real-world data sets show that the incremental algorithm can converge to the optimal solution in a finite number of steps, and is faster than the existing batch and incremental SVOR algorithms. Meanwhile, the modified formulation has better accuracy than the existing incremental SVOR algorithm, and is as accurate as the sum-of-margins based formulation of Shashua and Levin.
iBOA: The Incremental Bayesian Optimization Algorithm
Pelikan, Martin; Goldberg, David E
2008-01-01
This paper proposes the incremental Bayesian optimization algorithm (iBOA), which modifies standard BOA by removing the population of solutions and using incremental updates of the Bayesian network. iBOA is shown to be able to learn and exploit unrestricted Bayesian networks using incremental techniques for updating both the structure as well as the parameters of the probabilistic model. This represents an important step toward the design of competent incremental estimation of distribution algorithms that can solve difficult nearly decomposable problems scalably and reliably.
An Incremental Rule Acquisition Algorithm Based on Rough Set
Institute of Scientific and Technical Information of China (English)
YU Hong; YANG Da-chun
2005-01-01
Rough Set is a valid mathematical theory developed in recent years,which has the ability to deal with imprecise,uncertain,and vague information.This paper presents a new incremental rule acquisition algorithm based on rough set theory.First,the relation of the new instances with the original rule set is discussed.Then the change law of attribute reduction and value reduction are studied when a new instance is added.Follow,a new incremental learning algorithm for decision tables is presented within the framework of rough set.Finally,the new algorithm and the classical algorithm are analyzed and compared by theory and experiments.
Research of Incremental Learning Algorithm Based on Drive Error Criterion%基于驱动错误准则的SVM增量学习研究
Institute of Scientific and Technical Information of China (English)
文波; 单甘霖; 段修生
2012-01-01
Incremental learning is widely used in artificial intelligence, pattern recognition and other fields. It is an effective method to solve the problem that the efficiency of the system declines in the process of studying training samples which is of a small number in the beginning. For the disadvantage of the classical support vector machine getting slower when the number of training samples gets larger, this thesis proposes an incremental learning algorithm based on Drive error criterion. The experimental results show that this algorithm not only guarantees the precision and good generalization ability of the learning machine, but also faster than the classic SVM algorithm. Therefore, it can be used in incremental learning.%增量学习广泛运用于人工智能、模式识别等诸多领域,是解决系统在训练初期样本量少而随时间推移性能降低的有效方法.本文针对经典支持向量机当训练样本数量多而运算速度较慢的缺点,在分析支持向量机的基础上,提出基于驱动错误准则的增量学习方法,实验结果表明,该算法不仅能保证学习机器的精度和良好的推广能力,而且算法的学习速度比经典的SVM算法快,可以进行增量学习.
Assessing the Incremental Algorithm: A Response to Krahmer et al.
van Deemter, Kees; Gatt, Albert; van der Sluis, Ielka; Power, Richard
2012-01-01
This response discusses the experiment reported in Krahmer et al.'s Letter to the Editor of "Cognitive Science". We observe that their results do not tell us whether the Incremental Algorithm is better or worse than its competitors, and we speculate about implications for reference in complex domains, and for learning from "normal" (i.e.,…
REAL-TIME FACE TRACKING ALGORITHM BASED ON ONLINE INCREMENTAL LEARNING%基于在线增量学习的实时人脸跟踪算法
Institute of Scientific and Technical Information of China (English)
包芳; 张炎凯; 王士同
2016-01-01
提出基于在线增量式极端随机森林分类器的实时人脸跟踪算法。算法用在线极端随机森林分类器实现基于检测的跟踪，并结合动态目标框架和 P-N 学习矫正检测的错误。实验结果表明，该算法能够在不确定背景下对任意人脸实现较长时间段内的稳定快速的实时跟踪，并能有效排除背景等的干扰，效果较好。%The paper proposes a real-time face tracking algorithm,which is based on online incremental extremely random forests classifier.The algorithm achieves detection-based real-time tracking using online incremental extremely random forests classifier,and combines dynamic target framework and P-N learning to correct detection errors.Experimental results show,the proposed algorithm can realise fast and stable real-time tracking for any face in a longer period under uncertain background,and can effectively overcome interferences such as background with preferable effect.
一种新的兼类样本类增量学习算法%New Multi-label Sample Class Incremental Learning Algorithm
Institute of Scientific and Technical Information of China (English)
秦玉平; 伦淑娴; 王秀坤
2012-01-01
提出了一种基于超椭球的兼类样本类增量学习算法.对兼有同一类别的样本,在特征空间构建一个能包围该类尽可能多样本的最小超椭球,使各类样本之间通过超椭球球面分开.增量学习过程中,对新增样本中的每一新类别构建超椭球,对新增样本中的各历史类别重新构建超椭球,使得算法在很小的空间代价下实现了兼类样本类增量学习,同时保留了与新增样本类别无关的历史类训练结果.分类过程中,根据待分类样本是否在超椭球内或隶属度来确定其所属类别.实验结果表明,该算法较超球方法具有较快的分类速度和较高的分类精度.%To multi-label sample, a class incremental learning algorithm based on hyper ellipsoidals was proposed For every class, the smallest hyper ellipsoidal that contains most samples of the class was structured, which can divide the class samples from others. In the process of class incremental learning, the hyper ellipsoidals of new class were structured, and the historical hyper ellipsoidal that its class exists in the incremental samples was structured agaia The multi-label class incremental learning is realized in a small memory space,and the history results that has nothing to do with the new sample classes are saved at the same time. For the sample to be classified, its class is confirmed by the hyper ellipsoidal that it belongs to or its membership. The experimental results show that the algorithm has a higher performance on classification speed and classification precision compared with hyper sphere algorithm.
Incremental Centrality Algorithms for Dynamic Network Analysis
2013-08-01
the incremental betweenness centrality algorithm. The total upper bound for the space these data structures consume is 111 ((3*|AffectedSinks...when p = 0.4. In [153], the author examines the ethnocentrism phenomenon which refers to the tendency to behave differently towards strangers based...amount of memory consumed , but, among these two factors, what makes the real difference in how much memory is needed is the number of nodes in a
Incremental learning for automated knowledge capture.
Energy Technology Data Exchange (ETDEWEB)
Benz, Zachary O.; Basilico, Justin Derrick; Davis, Warren Leon,; Dixon, Kevin R.; Jones, Brian S.; Martin, Nathaniel; Wendt, Jeremy Daniel
2013-12-01
People responding to high-consequence national-security situations need tools to help them make the right decision quickly. The dynamic, time-critical, and ever-changing nature of these situations, especially those involving an adversary, require models of decision support that can dynamically react as a situation unfolds and changes. Automated knowledge capture is a key part of creating individualized models of decision making in many situations because it has been demonstrated as a very robust way to populate computational models of cognition. However, existing automated knowledge capture techniques only populate a knowledge model with data prior to its use, after which the knowledge model is static and unchanging. In contrast, humans, including our national-security adversaries, continually learn, adapt, and create new knowledge as they make decisions and witness their effect. This artificial dichotomy between creation and use exists because the majority of automated knowledge capture techniques are based on traditional batch machine-learning and statistical algorithms. These algorithms are primarily designed to optimize the accuracy of their predictions and only secondarily, if at all, concerned with issues such as speed, memory use, or ability to be incrementally updated. Thus, when new data arrives, batch algorithms used for automated knowledge capture currently require significant recomputation, frequently from scratch, which makes them ill suited for use in dynamic, timecritical, high-consequence decision making environments. In this work we seek to explore and expand upon the capabilities of dynamic, incremental models that can adapt to an ever-changing feature space.
基于局部平滑性的通用增量流形学习算法%Generalized incremental manifold learning algorithm based on local smoothness
Institute of Scientific and Technical Information of China (English)
周雪燕; 韩建敏; 詹宇斌
2012-01-01
Most of the existing manifold learning algorithms are not capable of dealing with new arrival samples. Although some incremental algorithms are developed via extending a specified manifold learning algorithm, most of them have some disadvantages more or less. In this paper, a new and more Generalized Incremental Manifold Learning ( G1ML) algorithm based on local smoothness was proposed. CIML algorithm firstly extracted the local smooth structure of data set via local Principal Component Analysis (PCA). Then the optimal linear transformation, which transformed the local smooth structure of new arrival sample' s neighborhood to its correspondent low-dimensional embedding coordinates, was computed. Finally the low-dimensional embedding coordinates of new arrival samples were obtained by the optimal transformation. Extensive and systematic experiments were conducted on both artificial and real image data sets. The experimental results demonstrate that the GIML algorithm is an effective incremental manifold learning algorithm and outperforms other existing algorithms.%目前大多数流形学习算法无法获取高维输入空间到低维嵌入空间的映射,无法处理新增数据,因此无增量学习能力.而已有的增量流形学习算法大多是通过扩展某一特定的流形学习算法使其具备增量学习能力,不具有通用性.针对这一问题,提出了一种通用的增量流形学习(GIML)算法.该方法充分考虑流形的局部平滑性这一本质特征,利用局部主成分分析法来提取数据集的局部平滑结构,并寻找包含新增样本点的局部平滑结构到对应训练数据的低维嵌入坐标的最佳变换.最后GIML算法利用该变换计算新增样本点的低维嵌入坐标.在人工数据集和实际图像数据集上进行了系统而广泛的比较实验,实验结果表明GIML算法是一种高效通用的增量流形学习方法,且相比当前主要的增量算法,能更精确地获取增量数据的低维嵌入坐标.
An Incremental Manifold Learning Algorithm Based on Iterative Decomposition%一种基于迭代分解的增量流形学习算法
Institute of Scientific and Technical Information of China (English)
谈超; 吉根林
2016-01-01
流形学习可以用于发现大型高维数据集的内在结构,并给出理解该数据集的潜在方式,已被视为一种有效的非线性降维方法.近年来,新数据点不断地从数据流中产生,将改变已有数据点及其邻域点的坐标,传统流形学习算法不能有效地用于寻找高维数据流的内在信息.为了解决该问题,本文提出了一种基于迭代分解的增量流形学习算法IMLID(Incremental Manifold Learning Algorithm Based on Iterative Decomposition),可以检测到数据流形中的逐步变化,校准逐渐变化中的流形,可提高在取样于真实世界的特征集上分类效果的精确率,利用真实数据集进行实验验证,结果表明本文提出的算法是有效的,与其他相关算法相比,其性能具有优势,在模式识别、生物信息等领域具有应用价值.%Manifold learning is used to discover intrinsic low-dimensional manifolds of data points embedded in high-dimensional spaces,which is useful in nonlinear dimension reduction. In recent years,new data points come continually, which will change the existing data points' neighborhoods and their local distributions. Tranditional methods cannot discover intrinsic information of high dimensional data streams effectively. To solve this problem,we propose an Incre?mental Manifold Learning Algorithm Based on Iterative Decomposition(IMLID),which can detect the change of mani?fold and improve the classification accuracy of the feature set sampling in the real world. Experiments on real-life datasets validate the effectiveness of the proposed method which has important significance and extensive application value in pattern recognition and so on.
Class Incremental Learning Algorithm for P2P Streaming Media Identification%用于P2P流媒体识别的类增量学习算法
Institute of Scientific and Technical Information of China (English)
李进; 张鑫; 王晖
2011-01-01
针对P2P流媒体流量识别中的类增量学习问题,提出一种基于“一对一”支持向量机多分类器的类增量学习算法CIOOL.充分利用原有多分类器知识,在不打破原有分类器体系的前提下加入新增类样本知识,以构造出新的多分类器.实验结果表明,CIOOL算法能在保证识别精度的同时减少训练时间和内存消耗,是一种解决P2P流媒体流量识别中类增量问题的有效方法.%This paper studies class incremental learning of P2P streaming traffic identification by using one-against-one Support VectorMachine(SVM) multi-classification. A new SVM class incremental learning algorithm--Class Incremental One-against-One Learning(CIOOL) ispresented. CIOOL can adequately use former knowledge to construct a new multi-classifier without training over again. Experimental results indicate that CIOOL can decrease the time of training and memory consuming, and it is an effective algorithm to solve the problem of class incremental learning in P2P streaming traffic identification.
Incremental learning of concept drift in nonstationary environments.
Elwell, Ryan; Polikar, Robi
2011-10-01
We introduce an ensemble of classifiers-based approach for incremental learning of concept drift, characterized by nonstationary environments (NSEs), where the underlying data distributions change over time. The proposed algorithm, named Learn(++). NSE, learns from consecutive batches of data without making any assumptions on the nature or rate of drift; it can learn from such environments that experience constant or variable rate of drift, addition or deletion of concept classes, as well as cyclical drift. The algorithm learns incrementally, as other members of the Learn(++) family of algorithms, that is, without requiring access to previously seen data. Learn(++). NSE trains one new classifier for each batch of data it receives, and combines these classifiers using a dynamically weighted majority voting. The novelty of the approach is in determining the voting weights, based on each classifier's time-adjusted accuracy on current and past environments. This approach allows the algorithm to recognize, and act accordingly, to the changes in underlying data distributions, as well as to a possible reoccurrence of an earlier distribution. We evaluate the algorithm on several synthetic datasets designed to simulate a variety of nonstationary environments, as well as a real-world weather prediction dataset. Comparisons with several other approaches are also included. Results indicate that Learn(++). NSE can track the changing environments very closely, regardless of the type of concept drift. To allow future use, comparison and benchmarking by interested researchers, we also release our data used in this paper.
Incremental learning for ν-Support Vector Regression.
Gu, Bin; Sheng, Victor S; Wang, Zhijie; Ho, Derek; Osman, Said; Li, Shuo
2015-07-01
The ν-Support Vector Regression (ν-SVR) is an effective regression learning algorithm, which has the advantage of using a parameter ν on controlling the number of support vectors and adjusting the width of the tube automatically. However, compared to ν-Support Vector Classification (ν-SVC) (Schölkopf et al., 2000), ν-SVR introduces an additional linear term into its objective function. Thus, directly applying the accurate on-line ν-SVC algorithm (AONSVM) to ν-SVR will not generate an effective initial solution. It is the main challenge to design an incremental ν-SVR learning algorithm. To overcome this challenge, we propose a special procedure called initial adjustments in this paper. This procedure adjusts the weights of ν-SVC based on the Karush-Kuhn-Tucker (KKT) conditions to prepare an initial solution for the incremental learning. Combining the initial adjustments with the two steps of AONSVM produces an exact and effective incremental ν-SVR learning algorithm (INSVR). Theoretical analysis has proven the existence of the three key inverse matrices, which are the cornerstones of the three steps of INSVR (including the initial adjustments), respectively. The experiments on benchmark datasets demonstrate that INSVR can avoid the infeasible updating paths as far as possible, and successfully converges to the optimal solution. The results also show that INSVR is faster than batch ν-SVR algorithms with both cold and warm starts. Copyright © 2015 Elsevier Ltd. All rights reserved.
Energy Technology Data Exchange (ETDEWEB)
Lima, Alan M.M. de; Schirru, Roberto [Universidade Federal, Rio de Janeiro, RJ (Brazil). Coordenacao dos Programas de Pos-graduacao de Engenharia. Programa de Engenharia Nuclear. E-mail: alan@lmp.ufrj.br; schirru@lmp.ufrj.br
2000-07-01
Genetic algorithms are biologically motivated adaptive systems which have been used, with good results, for function optimization. The purpose of this work is to introduce a new parallelization method to be applied to the Population-Based Incremental Learning (PBIL) algorithm. PBIL combines standard genetic algorithm mechanisms with simple competitive learning and has ben successfully used in combinatorial optimization problems. The development of this algorithm aims its application to the reload optimization of PWR nuclear reactors. Tests have been performed with combinatorial optimization problems similar to the reload problem. Results are compared to the serial PBIL ones, showing the new method's superiority and its viability as a tool for the nuclear core reload problem solution. (author)
An Incremental Approach to Automatic Algorithm Design
Institute of Scientific and Technical Information of China (English)
LUAN Shangmin; LI Wei
1999-01-01
This paper presents an incrementalapproach to automatic algorithm design, which can be described byalgebraic specifications precisely and conveniently. The definitions ofselection operator and extension operator which can be defined bystrategy relations and transformations are given in order to model theprocess of finding the solution of a problem. Also discussed is itsobject-oriented implementation. The functional specification and thedesign specification for an algorithm are given in one framework so thatthe correctness of the algorithm can be easily proved.
An Incremental Algorithm of Text Clustering Based on Semantic Sequences
Institute of Scientific and Technical Information of China (English)
FENG Zhonghui; SHEN Junyi; BAO Junpeng
2006-01-01
This paper proposed an incremental textclustering algorithm based on semantic sequence.Using similarity relation of semantic sequences and calculating the cover of similarity semantic sequences set, the candidate cluster with minimum entropy overlap value was selected as a result cluster every time in this algorithm.The comparison of experimental results shows that the precision of the algorithm is higher than other algorithms under same conditions and this is obvious especially on long documents set.
Incremental Learning with SVM for Multimodal Classification of Prostatic Adenocarcinoma
José Fernando García Molina; Lei Zheng; Metin Sertdemir; Dietmar J Dinter; Stefan Schönberg; Matthias Rädle
2014-01-01
Robust detection of prostatic cancer is a challenge due to the multitude of variants and their representation in MR images. We propose a pattern recognition system with an incremental learning ensemble algorithm using support vector machines (SVM) tackling this problem employing multimodal MR images and a texture-based information strategy. The proposed system integrates anatomic, texture, and functional features. The data set was preprocessed using B-Spline interpolation, bias field correcti...
Chen, C L Philip; Liu, Zhulin
2017-07-21
Broad Learning System (BLS) that aims to offer an alternative way of learning in deep structure is proposed in this paper. Deep structure and learning suffer from a time-consuming training process because of a large number of connecting parameters in filters and layers. Moreover, it encounters a complete retraining process if the structure is not sufficient to model the system. The BLS is established in the form of a flat network, where the original inputs are transferred and placed as "mapped features" in feature nodes and the structure is expanded in wide sense in the "enhancement nodes." The incremental learning algorithms are developed for fast remodeling in broad expansion without a retraining process if the network deems to be expanded. Two incremental learning algorithms are given for both the increment of the feature nodes (or filters in deep structure) and the increment of the enhancement nodes. The designed model and algorithms are very versatile for selecting a model rapidly. In addition, another incremental learning is developed for a system that has been modeled encounters a new incoming input. Specifically, the system can be remodeled in an incremental way without the entire retraining from the beginning. Satisfactory result for model reduction using singular value decomposition is conducted to simplify the final structure. Compared with existing deep neural networks, experimental results on the Modified National Institute of Standards and Technology database and NYU NORB object recognition dataset benchmark data demonstrate the effectiveness of the proposed BLS.
Generation of Referring Expressions: Assessing the Incremental Algorithm
van Deemter, Kees; Gatt, Albert; van der Sluis, Ielka; Power, Richard
2012-01-01
A substantial amount of recent work in natural language generation has focused on the generation of "one-shot" referring expressions whose only aim is to identify a target referent. Dale and Reiter's Incremental Algorithm (IA) is often thought to be the best algorithm for maximizing the similarity to referring expressions produced by people. We…
AN INCREMENTAL UPDATING ALGORITHM FOR MINING ASSOCIATION RULES
Institute of Scientific and Technical Information of China (English)
Xu Baowen; Yi Tong; Wu Fangjun; Chen Zhenqiang
2002-01-01
In this letter, on the basis of Frequent Pattern(FP) tree, the support function to update FP-tree is introduced, then an Incremental FP (IFP) algorithm for mining association rules is proposed. IFP algorithm considers not only adding new data into the database but also reducing old data from the database. Furthermore, it can predigest five cases to three cases.The algorithm proposed in this letter can avoid generating lots of candidate items, and it is high efficient.
A new incremental updating algorithm for association rules
Institute of Scientific and Technical Information of China (English)
WANG Zuo-cheng; XUE Li-xia
2007-01-01
Incremental data mining is an attractive goal for many kinds of mining in large databases or data warehouses. A new incremental updating algorithm rule growing algorithm (RGA) is presented for efficient maintenance discovered association rules when new transaction data is added to a transaction database. The algorithm RGA makes use of previous association rules as seed rules. By RGA, the seed rules whether are strong or not can be confirmed without scanning all the transaction DB in most cases. If the distributing of item of transaction DB is not uniform, the inflexion of robustness curve comes very quickly, and RGA gets great efficiency, saving lots of time for I/O. Experiments validate the algorithm and the test results showed that this algorithm is efficient.
Institute of Scientific and Technical Information of China (English)
宋涛; 汤宝平; 邓蕾
2014-01-01
针对现有的批量式流形学习算法无法利用已学习的流形结构实现新增样本的快速约简的缺点，提出增殖正交邻域保持嵌入（Incremental Orthogonal Neighborhood Preserving Embedding，IONPE）流形学习算法。该算法在正交邻域保持嵌入算法基础上利用分块处理思想实现新增样本子集的动态约简。从原始样本中选取部分重叠点合并至新增样本，对重叠点和新增样本子集不依赖原始样本使用正交邻域保持嵌入（ONPE）进行独立约简获取低维嵌入坐标子集，并基于重叠点坐标差值最小化原则，将新增样本低维嵌入坐标通过旋转平移缩放整合到原样本子集中。齿轮箱故障诊断案例证实了IONPE算法具有良好的增量学习能力，在继承ONPE优良聚类特性的同时有效提高了新增样本约简效率。%The current batch manifold learning algorithms can't achieve rapid dimension reduction of additional samples with learned manifold structures.Here,the incremental orthogonal neighborhood preserving embedding (IONPE) manifold learning algorithm was proposed.With it,dynamic incremental learning for additional samples was realized with a block processing idea based on orthogonal neighborhood preserving embedding.Firstly,some overlapping points were selected from the original samples and added to the additional samples. Secondly, the subset of low-dimensional embedding coordinates of additional samples was obtained with ONPE independing on the original samples.Finally,based on the principle of minimizing the differences of the overlapping point coordinates,the low-dimensional embedding coordinates of the additional samples were integrated into the original samples with rotating, shifting and scaling transformations.The fault diagnosis case of a gearbox confirmed that the IONPE algorithm has a good incremental learning ability,it improves the processing efficiency of the additional samples while inheriting the
Evolution of cooperation driven by incremental learning
Li, Pei; Duan, Haibin
2015-02-01
It has been shown that the details of microscopic rules in structured populations can have a crucial impact on the ultimate outcome in evolutionary games. So alternative formulations of strategies and their revision processes exploring how strategies are actually adopted and spread within the interaction network need to be studied. In the present work, we formulate the strategy update rule as an incremental learning process, wherein knowledge is refreshed according to one's own experience learned from the past (self-learning) and that gained from social interaction (social-learning). More precisely, we propose a continuous version of strategy update rules, by introducing the willingness to cooperate W, to better capture the flexibility of decision making behavior. Importantly, the newly gained knowledge including self-learning and social learning is weighted by the parameter ω, establishing a strategy update rule involving innovative element. Moreover, we quantify the macroscopic features of the emerging patterns to inspect the underlying mechanisms of the evolutionary process using six cluster characteristics. In order to further support our results, we examine the time evolution course for these characteristics. Our results might provide insights for understanding cooperative behaviors and have several important implications for understanding how individuals adjust their strategies under real-life conditions.
AN INCREMENTAL UPDATING ALGORITHM FOR MINING ASSOCIATION RULES
Institute of Scientific and Technical Information of China (English)
XuBaowen; YiTong; 等
2002-01-01
In this letter,on the basis of Frequent Pattern(FP) tree,the support function to update FP-tree is introduced,then an incremental FP(IFP) algorithm for mining association rules is proposed.IFP algorithm considers not only adding new data into the database but also reducing old data from the database.Furthermore,it can predigest five cases to three case .The algorithm proposed in this letter can avoid generating lots of candidate items,and it is high efficient.
Helou, E. S.; Zibetti, M. V. W.; Miqueles, E. X.
2017-04-01
We propose the superiorization of incremental algorithms for tomographic image reconstruction. The resulting methods follow a better path in its way to finding the optimal solution for the maximum likelihood problem in the sense that they are closer to the Pareto optimal curve than the non-superiorized techniques. A new scaled gradient iteration is proposed and three superiorization schemes are evaluated. Theoretical analysis of the methods as well as computational experiments with both synthetic and real data are provided.
A Novel Classification Algorithm Based on Incremental Semi-Supervised Support Vector Machine
Gao, Fei; Mei, Jingyuan; Sun, Jinping; Wang, Jun; Yang, Erfu; Hussain, Amir
2015-01-01
For current computational intelligence techniques, a major challenge is how to learn new concepts in changing environment. Traditional learning schemes could not adequately address this problem due to a lack of dynamic data selection mechanism. In this paper, inspired by human learning process, a novel classification algorithm based on incremental semi-supervised support vector machine (SVM) is proposed. Through the analysis of prediction confidence of samples and data distribution in a changing environment, a “soft-start” approach, a data selection mechanism and a data cleaning mechanism are designed, which complete the construction of our incremental semi-supervised learning system. Noticeably, with the ingenious design procedure of our proposed algorithm, the computation complexity is reduced effectively. In addition, for the possible appearance of some new labeled samples in the learning process, a detailed analysis is also carried out. The results show that our algorithm does not rely on the model of sample distribution, has an extremely low rate of introducing wrong semi-labeled samples and can effectively make use of the unlabeled samples to enrich the knowledge system of classifier and improve the accuracy rate. Moreover, our method also has outstanding generalization performance and the ability to overcome the concept drift in a changing environment. PMID:26275294
A Novel Classification Algorithm Based on Incremental Semi-Supervised Support Vector Machine.
Directory of Open Access Journals (Sweden)
Fei Gao
Full Text Available For current computational intelligence techniques, a major challenge is how to learn new concepts in changing environment. Traditional learning schemes could not adequately address this problem due to a lack of dynamic data selection mechanism. In this paper, inspired by human learning process, a novel classification algorithm based on incremental semi-supervised support vector machine (SVM is proposed. Through the analysis of prediction confidence of samples and data distribution in a changing environment, a "soft-start" approach, a data selection mechanism and a data cleaning mechanism are designed, which complete the construction of our incremental semi-supervised learning system. Noticeably, with the ingenious design procedure of our proposed algorithm, the computation complexity is reduced effectively. In addition, for the possible appearance of some new labeled samples in the learning process, a detailed analysis is also carried out. The results show that our algorithm does not rely on the model of sample distribution, has an extremely low rate of introducing wrong semi-labeled samples and can effectively make use of the unlabeled samples to enrich the knowledge system of classifier and improve the accuracy rate. Moreover, our method also has outstanding generalization performance and the ability to overcome the concept drift in a changing environment.
An Incremental High-Utility Mining Algorithm with Transaction Insertion
Directory of Open Access Journals (Sweden)
Jerry Chun-Wei Lin
2015-01-01
Full Text Available Association-rule mining is commonly used to discover useful and meaningful patterns from a very large database. It only considers the occurrence frequencies of items to reveal the relationships among itemsets. Traditional association-rule mining is, however, not suitable in real-world applications since the purchased items from a customer may have various factors, such as profit or quantity. High-utility mining was designed to solve the limitations of association-rule mining by considering both the quantity and profit measures. Most algorithms of high-utility mining are designed to handle the static database. Fewer researches handle the dynamic high-utility mining with transaction insertion, thus requiring the computations of database rescan and combination explosion of pattern-growth mechanism. In this paper, an efficient incremental algorithm with transaction insertion is designed to reduce computations without candidate generation based on the utility-list structures. The enumeration tree and the relationships between 2-itemsets are also adopted in the proposed algorithm to speed up the computations. Several experiments are conducted to show the performance of the proposed algorithm in terms of runtime, memory consumption, and number of generated patterns.
A fast flexible docking method using an incremental construction algorithm.
Rarey, M; Kramer, B; Lengauer, T; Klebe, G
1996-08-23
We present an automatic method for docking organic ligands into protein binding sites. The method can be used in the design process of specific protein ligands. It combines an appropriate model of the physico-chemical properties of the docked molecules with efficient methods for sampling the conformational space of the ligand. If the ligand is flexible, it can adopt a large variety of different conformations. Each such minimum in conformational space presents a potential candidate for the conformation of the ligand in the complexed state. Our docking method samples the conformation space of the ligand on the basis of a discrete model and uses a tree-search technique for placing the ligand incrementally into the active site. For placing the first fragment of the ligand into the protein, we use hashing techniques adapted from computer vision. The incremental construction algorithm is based on a greedy strategy combined with efficient methods for overlap detection and for the search of new interactions. We present results on 19 complexes of which the binding geometry has been crystallographically determined. All considered ligands are docked in at most three minutes on a current workstation. The experimentally observed binding mode of the ligand is reproduced with 0.5 to 1.2 A rms deviation. It is almost always found among the highest-ranking conformations computed.
Incremental refinement of a multi-user-detection algorithm (II
Directory of Open Access Journals (Sweden)
M. Vollmer
2003-01-01
Full Text Available Multi-user detection is a technique proposed for mobile radio systems based on the CDMA principle, such as the upcoming UMTS. While offering an elegant solution to problems such as intra-cell interference, it demands very significant computational resources. In this paper, we present a high-level approach for reducing the required resources for performing multi-user detection in a 3GPP TDD multi-user system. This approach is based on a displacement representation of the parameters that describe the transmission system, and a generalized Schur algorithm that works on this representation. The Schur algorithm naturally leads to a highly parallel hardware implementation using CORDIC cells. It is shown that this hardware architecture can also be used to compute the initial displacement representation. It is very beneficial to introduce incremental refinement structures into the solution process, both at the algorithmic level and in the individual cells of the hardware architecture. We detail these approximations and present simulation results that confirm their effectiveness.
Incremental learning with SVM for multimodal classification of prostatic adenocarcinoma.
García Molina, José Fernando; Zheng, Lei; Sertdemir, Metin; Dinter, Dietmar J; Schönberg, Stefan; Rädle, Matthias
2014-01-01
Robust detection of prostatic cancer is a challenge due to the multitude of variants and their representation in MR images. We propose a pattern recognition system with an incremental learning ensemble algorithm using support vector machines (SVM) tackling this problem employing multimodal MR images and a texture-based information strategy. The proposed system integrates anatomic, texture, and functional features. The data set was preprocessed using B-Spline interpolation, bias field correction and intensity standardization. First- and second-order angular independent statistical approaches and rotation invariant local phase quantization (RI-LPQ) were utilized to quantify texture information. An incremental learning ensemble SVM was implemented to suit working conditions in medical applications and to improve effectiveness and robustness of the system. The probability estimation of cancer structures was calculated using SVM and the corresponding optimization was carried out with a heuristic method together with a 3-fold cross-validation methodology. We achieved an average sensitivity of 0.844 ± 0.068 and a specificity of 0.780 ± 0.038, which yielded superior or similar performance to current state of the art using a total database of only 41 slices from twelve patients with histological confirmed information, including cancerous, unhealthy non-cancerous and healthy prostate tissue. Our results show the feasibility of an ensemble SVM being able to learn additional information from new data while preserving previously acquired knowledge and preventing unlearning. The use of texture descriptors provides more salient discriminative patterns than the functional information used. Furthermore, the system improves selection of information, efficiency and robustness of the classification. The generated probability map enables radiologists to have a lower variability in diagnosis, decrease false negative rates and reduce the time to recognize and delineate structures in
Incremental learning with SVM for multimodal classification of prostatic adenocarcinoma.
Directory of Open Access Journals (Sweden)
José Fernando García Molina
Full Text Available Robust detection of prostatic cancer is a challenge due to the multitude of variants and their representation in MR images. We propose a pattern recognition system with an incremental learning ensemble algorithm using support vector machines (SVM tackling this problem employing multimodal MR images and a texture-based information strategy. The proposed system integrates anatomic, texture, and functional features. The data set was preprocessed using B-Spline interpolation, bias field correction and intensity standardization. First- and second-order angular independent statistical approaches and rotation invariant local phase quantization (RI-LPQ were utilized to quantify texture information. An incremental learning ensemble SVM was implemented to suit working conditions in medical applications and to improve effectiveness and robustness of the system. The probability estimation of cancer structures was calculated using SVM and the corresponding optimization was carried out with a heuristic method together with a 3-fold cross-validation methodology. We achieved an average sensitivity of 0.844 ± 0.068 and a specificity of 0.780 ± 0.038, which yielded superior or similar performance to current state of the art using a total database of only 41 slices from twelve patients with histological confirmed information, including cancerous, unhealthy non-cancerous and healthy prostate tissue. Our results show the feasibility of an ensemble SVM being able to learn additional information from new data while preserving previously acquired knowledge and preventing unlearning. The use of texture descriptors provides more salient discriminative patterns than the functional information used. Furthermore, the system improves selection of information, efficiency and robustness of the classification. The generated probability map enables radiologists to have a lower variability in diagnosis, decrease false negative rates and reduce the time to recognize and
Predicting Robust Vocabulary Growth from Measures of Incremental Learning
Frishkoff, Gwen A.; Perfetti, Charles A.; Collins-Thompson, Kevyn
2011-01-01
We report a study of incremental learning of new word meanings over multiple episodes. A new method called MESA (Markov Estimation of Semantic Association) tracked this learning through the automated assessment of learner-generated definitions. The multiple word learning episodes varied in the strength of contextual constraint provided by…
浅谈增量学习支持向量机图像识别算法的设计%Incremental Support Vector Machine Learning Image Recognition Algorithm Design
Institute of Scientific and Technical Information of China (English)
廖隽婷; 施荣华
2011-01-01
This paper proposed an incremental learning algorithm for support vector machine image recognition is performed in two stages：the first stage is to update the probability distribution of hyperplane parameters,the second stage is to update the output probability distribution,and repeated execution each layer of the update process,the next two phases of the structure,respectively, a detailed description.%本文所提出的增量学习支持向量机图像识别算法是分为两阶段来执行：第一阶段是更新超平面参数的概率分布，第二阶段是更新输出值的概率分布，并反复的执行每一层更新的过程，接下来分别对这两阶段的架构做详细的说明。
A Fast Incremental Learning for Radial Basis Function Networks Using Local Linear Regression
Ozawa, Seiichi; Okamoto, Keisuke
To avoid the catastrophic interference in incremental learning, we have proposed Resource Allocating Network with Long Term Memory (RAN-LTM). In RAN-LTM, not only new training data but also some memory items stored in long-term memory are trained either by a gradient descent algorithm or by solving a linear regression problem. In the latter approach, radial basis function (RBF) centers are not trained but selected based on output errors when connection weights are updated. The proposed incremental learning algorithm belongs to the latter approach where the errors not only for a training data but also for several retrieved memory items and pseudo training data are minimized to suppress the catastrophic interference. The novelty of the proposed algorithm is that connection weights to be learned are restricted based on RBF activation in order to improve the efficiency in learning time and memory size. We evaluate the performance of the proposed algorithm in one-dimensional and multi-dimensional function approximation problems in terms of approximation accuracy, learning time, and average memory size. The experimental results demonstrate that the proposed algorithm can learn fast and have good performance with less memory size compared to memory-based learning methods.
Unsupervised incremental online learning and prediction of musical audio signals
DEFF Research Database (Denmark)
Marxer, Richard; Purwins, Hendrik
2016-01-01
Guided by the idea that musical human-computer interaction may become more effective, intuitive, and creative when basing its computer part on cognitively more plausible learning principles, we employ unsupervised incremental online learning (i.e. clustering) to build a system that predicts...... the next event in a musical sequence, given as audio input. The flow of the system is as follows: 1) segmentation by onset detection, 2) timbre representation of each segment by Mel frequency cepstrum coefficients, 3) discretization by incremental clustering, yielding a tree of different sound classes (e...
Incremental Bayesian Category Learning from Natural Language
Frermann, Lea; Lapata, Mirella
2016-01-01
Models of category learning have been extensively studied in cognitive science and primarily tested on perceptual abstractions or artificial stimuli. In this paper, we focus on categories acquired from natural language stimuli, that is, words (e.g., "chair" is a member of the furniture category). We present a Bayesian model that, unlike…
Algorithms for Reinforcement Learning
Szepesvari, Csaba
2010-01-01
Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a long-term objective. What distinguishes reinforcement learning from supervised learning is that only partial feedback is given to the learner about the learner's predictions. Further, the predictions may have long term effects through influencing the future state of the controlled system. Thus, time plays a special role. The goal in reinforcement learning is to develop efficient learning algorithms, as well as to understand the algorithms'
Structurally enhanced incremental neural learning for image classification with subgraph extraction.
Yang, Yu-Bin; Li, Ya-Nan; Gao, Yang; Yin, Hujun; Tang, Ye
2014-11-01
In this paper, a structurally enhanced incremental neural learning technique is proposed to learn a discriminative codebook representation of images for effective image classification applications. In order to accommodate the relationships such as structures and distributions among visual words into the codebook learning process, we develop an online codebook graph learning method based on a novel structurally enhanced incremental learning technique, called as "visualization-induced self-organized incremental neural network (ViSOINN)". The hidden structural information in the images is embedded into the graph representation evolving dynamically with the adaptive and competitive learning mechanism. Afterwards, image features can be coded using a sub-graph extraction process based on the learned codebook graph, and a classifier is subsequently used to complete the image classification task. Compared with other codebook learning algorithms originated from the classical Bag-of-Features (BoF) model, ViSOINN holds the following advantages: (1) it learns codebook efficiently and effectively from a small training set; (2) it models the relationships among visual words in metric scaling fashion, so preserving high discriminative power; (3) it automatically learns the codebook without a fixed pre-defined size; and (4) it enhances and preserves better the structure of the data. These characteristics help to improve image classification performance and make it more suitable for handling large-scale image classification tasks. Experimental results on the widely used Caltech-101 and Caltech-256 benchmark datasets demonstrate that ViSOINN achieves markedly improved performance and reduces the computational cost considerably.
Incremental Sampling Algorithms for Robust Propulsion Control Project
National Aeronautics and Space Administration — Aurora Flight Sciences proposes to develop a system for robust engine control based on incremental sampling, specifically Rapidly-Expanding Random Tree (RRT)...
Incremental concept learning with few training examples and hierarchical classification
Bouma, H.; Eendebak, P.T.; Schutte, K.; Azzopardi, G.; Burghouts, G.J.
2015-01-01
Object recognition and localization are important to automatically interpret video and allow better querying on its content. We propose a method for object localization that learns incrementally and addresses four key aspects. Firstly, we show that for certain applications, recognition is feasible
Incremental concept learning with few training examples and hierarchical classification
Bouma, H.; Eendebak, P.T.; Schutte, K.; Azzopardi, G.; Burghouts, G.J.
2015-01-01
Object recognition and localization are important to automatically interpret video and allow better querying on its content. We propose a method for object localization that learns incrementally and addresses four key aspects. Firstly, we show that for certain applications, recognition is feasible w
Incremental learning by message passing in hierarchical temporal memory.
Rehn, Erik M; Maltoni, Davide
2014-08-01
Hierarchical temporal memory (HTM) is a biologically inspired framework that can be used to learn invariant representations of patterns in a wide range of applications. Classical HTM learning is mainly unsupervised, and once training is completed, the network structure is frozen, thus making further training (i.e., incremental learning) quite critical. In this letter, we develop a novel technique for HTM (incremental) supervised learning based on gradient descent error minimization. We prove that error backpropagation can be naturally and elegantly implemented through native HTM message passing based on belief propagation. Our experimental results demonstrate that a two-stage training approach composed of unsupervised pretraining and supervised refinement is very effective (both accurate and efficient). This is in line with recent findings on other deep architectures.
Directory of Open Access Journals (Sweden)
M. A. Zotov
2016-01-01
forward and greedy ones, moreover in the 10-170 load sets power range this finding is statistically significant (97% level. The results of experiments are visualized using a graphs library Highcharts. The developed incremental algorithm is designed for application in problems solving of algebraic Bayesian networks machine learning.
A Parallel and Incremental Approach for Data-Intensive Learning of Bayesian Networks.
Yue, Kun; Fang, Qiyu; Wang, Xiaoling; Li, Jin; Liu, Weiyi
2015-12-01
Bayesian network (BN) has been adopted as the underlying model for representing and inferring uncertain knowledge. As the basis of realistic applications centered on probabilistic inferences, learning a BN from data is a critical subject of machine learning, artificial intelligence, and big data paradigms. Currently, it is necessary to extend the classical methods for learning BNs with respect to data-intensive computing or in cloud environments. In this paper, we propose a parallel and incremental approach for data-intensive learning of BNs from massive, distributed, and dynamically changing data by extending the classical scoring and search algorithm and using MapReduce. First, we adopt the minimum description length as the scoring metric and give the two-pass MapReduce-based algorithms for computing the required marginal probabilities and scoring the candidate graphical model from sample data. Then, we give the corresponding strategy for extending the classical hill-climbing algorithm to obtain the optimal structure, as well as that for storing a BN by pairs. Further, in view of the dynamic characteristics of the changing data, we give the concept of influence degree to measure the coincidence of the current BN with new data, and then propose the corresponding two-pass MapReduce-based algorithms for BNs incremental learning. Experimental results show the efficiency, scalability, and effectiveness of our methods.
Unsupervised learning algorithms
Aydin, Kemal
2016-01-01
This book summarizes the state-of-the-art in unsupervised learning. The contributors discuss how with the proliferation of massive amounts of unlabeled data, unsupervised learning algorithms, which can automatically discover interesting and useful patterns in such data, have gained popularity among researchers and practitioners. The authors outline how these algorithms have found numerous applications including pattern recognition, market basket analysis, web mining, social network analysis, information retrieval, recommender systems, market research, intrusion detection, and fraud detection. They present how the difficulty of developing theoretically sound approaches that are amenable to objective evaluation have resulted in the proposal of numerous unsupervised learning algorithms over the past half-century. The intended audience includes researchers and practitioners who are increasingly using unsupervised learning algorithms to analyze their data. Topics of interest include anomaly detection, clustering,...
Application of incremental algorithms to CT image reconstruction for sparse-view, noisy data
Rose, Sean; Andersen, Martin Skovgaard; Sidky, Emil Y.; Pan, Xiaochuan
2014-01-01
This conference contribution adapts an incremental framework for solving optimization problems of interest for sparse-view CT. From the incremental framework two algorithms are derived: one that combines a damped form of the algebraic reconstruction technique (ART) with a total-variation (TV) projection, and one that employs a modified damped ART, accounting for a weighted-quadratic data fidelity term, combined with TV projection. The algorithms are demonstrated on simulated, noisy, sparsevie...
Incremental Learning of Skill Collections based on Intrinsic Motivation
Directory of Open Access Journals (Sweden)
Jan Hendrik Metzen
2013-07-01
Full Text Available Life-long learning of reusable, versatile skills is a key prerequisite forembodied agents that act in a complex, dynamic environment and are faced withdifferent tasks over their lifetime. We address the question of how an agentcan learn useful skills efficiently during a developmental period,i.e., when no task is imposed on him and no external reward signal is provided.Learning of skills in a developmental period needs to be incremental andself-motivated. We propose a new incremental, task-independent skill discoveryapproach that is suited for continuous domains. Furthermore, the agent learnsspecific skills based on intrinsic motivation mechanisms thatdetermine on which skills learning is focused at a given point in time. Weevaluate the approach in a reinforcement learning setup in two continuousdomains with complex dynamics. We show that an intrinsically motivated, skilllearning agent outperforms an agent which learns task solutions from scratch.Furthermore, we compare different intrinsic motivation mechanisms and howefficiently they make use of the agent's developmental period.
基于RB F神经网络的集成增量学习算法%RESEARCH ON RBF NEURAL NETWORK-BASED ENSEMBLE INCREMENTAL LEARNING ALGORITHM
Institute of Scientific and Technical Information of China (English)
彭玉青; 赵翠翠; 高晴晴
2016-01-01
针对增量学习的遗忘性问题和集成增量学习的网络增长过快问题，提出基于径向基神经网络（RBF）的集成增量学习方法。为了避免网络的遗忘性，每次学习新类别知识时都训练一个RBF神经网络，把新训练的RBF神经网络加入到集成系统中，从而组建成一个大的神经网络系统。分别采用最近中心法、最大概率法、最近中心与最大概率相结合的方法进行确定获胜子网络，最终结果由获胜子网络进行输出。在最大概率法中引入自组织映（SOM）的原型向量来解决类中心相近问题。为了验证网络的增量学习，用UCI机器学习库中Statlog（Landsat Satellite）数据集做实验，结果显示该网络在学习新类别知识后，既获得了新类别的知识也没有遗忘已学知识。%Aiming at the forgetfulness problem of incremental learning and the excessive network growth problem of the integrated incremental learning,this paper proposes an integrated incremental learning method which is based on the radial basis function (RBF)neural network.In order to avoid the forgetfulness of the network,for each knowledge learning of new category we all trained an RBF neural network,and added the newly trained RBF neural network to the integrated system so as to form a large system of neural networks.To determine the winning sub-network,we adopted the nearest centre method,the maximum probability method and the combination of these two methods,and the final result was outputted by the winning sub-network.Moreover,we introduced the prototype vectors of self-organising map to maximum probability method for solving the problem of class centre similarity.For verifying the proposed network incremental learning,we made the experiments using the Statlog (Landsat Satellite)dataset in UCI machine learning library.Experimental results showed that after learning the knowledge of new category,this network could accept the new without
Application of incremental algorithms to CT image reconstruction for sparse-view, noisy data
DEFF Research Database (Denmark)
Rose, Sean; Andersen, Martin Skovgaard; Sidky, Emil Y.;
2014-01-01
This conference contribution adapts an incremental framework for solving optimization problems of interest for sparse-view CT. From the incremental framework two algorithms are derived: one that combines a damped form of the algebraic reconstruction technique (ART) with a total-variation (TV) pro......) projection, and one that employs a modified damped ART, accounting for a weighted-quadratic data fidelity term, combined with TV projection. The algorithms are demonstrated on simulated, noisy, sparseview CT data.......This conference contribution adapts an incremental framework for solving optimization problems of interest for sparse-view CT. From the incremental framework two algorithms are derived: one that combines a damped form of the algebraic reconstruction technique (ART) with a total-variation (TV...
Is It that Difficult to Find a Good Preference Order for the Incremental Algorithm?
Krahmer, Emiel; Koolen, Ruud; Theune, Mariet
2012-01-01
In a recent article published in this journal (van Deemter, Gatt, van der Sluis, & Power, 2012), the authors criticize the Incremental Algorithm (a well-known algorithm for the generation of referring expressions due to Dale & Reiter, 1995, also in this journal) because of its strong reliance on a pre-determined, domain-dependent Preference Order.…
Incremental Structured Dictionary Learning for Video Sensor-Based Object Tracking
Directory of Open Access Journals (Sweden)
Ming Xue
2014-02-01
Full Text Available To tackle robust object tracking for video sensor-based applications, an online discriminative algorithm based on incremental discriminative structured dictionary learning (IDSDL-VT is presented. In our framework, a discriminative dictionary combining both positive, negative and trivial patches is designed to sparsely represent the overlapped target patches. Then, a local update (LU strategy is proposed for sparse coefficient learning. To formulate the training and classification process, a multiple linear classifier group based on a K-combined voting (KCV function is proposed. As the dictionary evolves, the models are also trained to timely adapt the target appearance variation. Qualitative and quantitative evaluations on challenging image sequences compared with state-of-the-art algorithms demonstrate that the proposed tracking algorithm achieves a more favorable performance. We also illustrate its relay application in visual sensor networks.
Force-Based Incremental Algorithm for Mining Community Structure in Dynamic Network
Institute of Scientific and Technical Information of China (English)
Bo Yang; Da-You Liu
2006-01-01
Community structure is an important property of network. Being able to identify communities can provide invaluable help in exploiting and understanding both social and non-social networks. Several algorithms have been developed up till now. However, all these algorithms can work well only with small or moderate networks with vertexes of order 104.Besides, all the existing algorithms are off-line and cannot work well with highly dynamic networks such as web, in which web pages are updated frequently. When an already clustered network is updated, the entire network including original and incremental parts has to be recalculated, even though only slight changes are involved. To address this problem, an incremental algorithm is proposed, which allows for mining community structure in large-scale and dynamic networks. Based on the community structure detected previously, the algorithm takes little time to reclassify the entire network including both the original and incremental parts. Furthermore, the algorithm is faster than most of the existing algorithms such as Girvan and Newman's algorithm and its improved versions. Also, the algorithm can help to visualize these community structures in network and provide a new approach to research on the evolving process of dynamic networks.
Online Pairwise Learning Algorithms.
Ying, Yiming; Zhou, Ding-Xuan
2016-04-01
Pairwise learning usually refers to a learning task that involves a loss function depending on pairs of examples, among which the most notable ones are bipartite ranking, metric learning, and AUC maximization. In this letter we study an online algorithm for pairwise learning with a least-square loss function in an unconstrained setting of a reproducing kernel Hilbert space (RKHS) that we refer to as the Online Pairwise lEaRning Algorithm (OPERA). In contrast to existing works (Kar, Sriperumbudur, Jain, & Karnick, 2013 ; Wang, Khardon, Pechyony, & Jones, 2012 ), which require that the iterates are restricted to a bounded domain or the loss function is strongly convex, OPERA is associated with a non-strongly convex objective function and learns the target function in an unconstrained RKHS. Specifically, we establish a general theorem that guarantees the almost sure convergence for the last iterate of OPERA without any assumptions on the underlying distribution. Explicit convergence rates are derived under the condition of polynomially decaying step sizes. We also establish an interesting property for a family of widely used kernels in the setting of pairwise learning and illustrate the convergence results using such kernels. Our methodology mainly depends on the characterization of RKHSs using its associated integral operators and probability inequalities for random variables with values in a Hilbert space.
A Learning Algorithm based on High School Teaching Wisdom
Philip, Ninan Sajeeth
2010-01-01
A learning algorithm based on primary school teaching and learning is presented. The methodology is to continuously evaluate a student and to give them training on the examples for which they repeatedly fail, until, they can correctly answer all types of questions. This incremental learning procedure produces better learning curves by demanding the student to optimally dedicate their learning time on the failed examples. When used in machine learning, the algorithm is found to train a machine on a data with maximum variance in the feature space so that the generalization ability of the network improves. The algorithm has interesting applications in data mining, model evaluations and rare objects discovery.
Incremental DataGrid Mining Algorithm for Mobility Prediction of Mobile Users
Directory of Open Access Journals (Sweden)
U. Sakthi
2009-01-01
Full Text Available Problem statement: Mobility prediction is the important issue in Personal Communication Systems (PCS. Mobile users moving logs are stored in data grid located in different locations. Distributed data mining algorithm is applied on this moving logs to generate the mobility pattern of mobile users. As new moving logs are added to the data grid, existing mobility pattern becomes invalid and it should be updated. One of the existing work to derive the new mobility pattern is re-executing the algorithm from scratch results in excessive computation. Approach: We had designed new incremental algorithm by maintaining infrequent mobility patterns, which avoids unnecessary scan of full database. Incremental data mining algorithm taken lesser time to compute new mobility patterns. The discovered location patterns can be used to provide various location based services to the mobile user by the application server in mobile computing environment. Data grid provided geographically distributed database for computational grid which implements incremental data mining algorithm. We built data grid system on a cluster of workstation using open source globus toolkit 4.0 and Message Passing Interface extended with Grid Services (MPICH-G2. Results: The experiments were conducted on original data sets and data were added incrementally and the computation time was recorded for each data sets. The performance improvement for increment size of 100 K was about 55% for 0.20% support count and it is increased to 60% for 0.25% support count. The performance is increased about 65% for the support count 0.30%. Conclusion: We analyzed our results with various sizes of data sets and the proof shows the time taken to generate mobility pattern by incremental mining algorithm is less than re-computing approach. In future the execution time can further be reduced by balancing the workload of grid nodes.
Incremental online object learning in a vehicular radar-vision fusion framework
Energy Technology Data Exchange (ETDEWEB)
Ji, Zhengping [Los Alamos National Laboratory; Weng, Juyang [Los Alamos National Laboratory; Luciw, Matthew [IEEE; Zeng, Shuqing [IEEE
2010-10-19
In this paper, we propose an object learning system that incorporates sensory information from an automotive radar system and a video camera. The radar system provides a coarse attention for the focus of visual analysis on relatively small areas within the image plane. The attended visual areas are coded and learned by a 3-layer neural network utilizing what is called in-place learning, where every neuron is responsible for the learning of its own signal processing characteristics within its connected network environment, through inhibitory and excitatory connections with other neurons. The modeled bottom-up, lateral, and top-down connections in the network enable sensory sparse coding, unsupervised learning and supervised learning to occur concurrently. The presented work is applied to learn two types of encountered objects in multiple outdoor driving settings. Cross validation results show the overall recognition accuracy above 95% for the radar-attended window images. In comparison with the uncoded representation and purely unsupervised learning (without top-down connection), the proposed network improves the recognition rate by 15.93% and 6.35% respectively. The proposed system is also compared with other learning algorithms favorably. The result indicates that our learning system is the only one to fit all the challenging criteria for the development of an incremental and online object learning system.
Incremental concept learning with few training examples and hierarchical classification
Bouma, Henri; Eendebak, Pieter T.; Schutte, Klamer; Azzopardi, George; Burghouts, Gertjan J.
2015-10-01
Object recognition and localization are important to automatically interpret video and allow better querying on its content. We propose a method for object localization that learns incrementally and addresses four key aspects. Firstly, we show that for certain applications, recognition is feasible with only a few training samples. Secondly, we show that novel objects can be added incrementally without retraining existing objects, which is important for fast interaction. Thirdly, we show that an unbalanced number of positive training samples leads to biased classifier scores that can be corrected by modifying weights. Fourthly, we show that the detector performance can deteriorate due to hard-negative mining for similar or closely related classes (e.g., for Barbie and dress, because the doll is wearing a dress). This can be solved by our hierarchical classification. We introduce a new dataset, which we call TOSO, and use it to demonstrate the effectiveness of the proposed method for the localization and recognition of multiple objects in images.
Institute of Scientific and Technical Information of China (English)
CHEN Yunkai; LU Zhengding; LI Ruixuan; LI Yuhua; SUN Xiaolin
2006-01-01
Considering the constantly increasing of data in large databases such as wire transfer database, incremental clustering algorithms play a more and more important role in Data Mining (DM). However, Few of the traditional clustering algorithms can not only handle the categorical data, but also explain its output clearly. Based on the idea of dynamic clustering, an incremental conceptive clustering algorithm is proposed in this paper. Which introduces the Semantic Core Tree (SCT) to deal with large volume of categorical wire transfer data for the detecting money laundering. In addition, the rule generation algorithm is presented here to express the clustering result by the format of knowledge. When we apply this idea in financial data mining, the efficiency of searching the characters of money laundering data will be improved.
Sung, Chul
2013-08-01
Accurate estimation of neuronal count and distribution is central to the understanding of the organization and layout of cortical maps in the brain, and changes in the cell population induced by brain disorders. High-throughput 3D microscopy techniques such as Knife-Edge Scanning Microscopy (KESM) are enabling whole-brain survey of neuronal distributions. Data from such techniques pose serious challenges to quantitative analysis due to the massive, growing, and sparsely labeled nature of the data. In this paper, we present a scalable, incremental learning algorithm for cell body detection that can address these issues. Our algorithm is computationally efficient (linear mapping, non-iterative) and does not require retraining (unlike gradient-based approaches) or retention of old raw data (unlike instance-based learning). We tested our algorithm on our rat brain Nissl data set, showing superior performance compared to an artificial neural network-based benchmark, and also demonstrated robust performance in a scenario where the data set is rapidly growing in size. Our algorithm is also highly parallelizable due to its incremental nature, and we demonstrated this empirically using a MapReduce-based implementation of the algorithm. We expect our scalable, incremental learning approach to be widely applicable to medical imaging domains where there is a constant flux of new data. © 2013 IEEE.
MOD* Lite: An Incremental Path Planning Algorithm Taking Care of Multiple Objectives.
Oral, Tugcem; Polat, Faruk
2016-01-01
The need for determining a path from an initial location to a target one is a crucial task in many applications, such as virtual simulations, robotics, and computer games. Almost all of the existing algorithms are designed to find optimal or suboptimal solutions considering only a single objective, namely path length. However, in many real life application path length is not the sole criteria for optimization, there are more than one criteria to be optimized that cannot be transformed to each other. In this paper, we introduce a novel multiobjective incremental algorithm, multiobjective D* lite (MOD* lite) built upon a well-known path planning algorithm, D* lite. A number of experiments are designed to compare the solution quality and execution time requirements of MOD* lite with the multiobjective A* algorithm, an alternative genetic algorithm we developed multiobjective genetic path planning and the strength Pareto evolutionary algorithm.
Directory of Open Access Journals (Sweden)
Kaifeng Yang
2014-01-01
Full Text Available A novel hybrid multiobjective algorithm is presented in this paper, which combines a new multiobjective estimation of distribution algorithm, an efficient local searcher and ε-dominance. Besides, two multiobjective problems with variable linkages strictly based on manifold distribution are proposed. The Pareto set to the continuous multiobjective optimization problems, in the decision space, is a piecewise low-dimensional continuous manifold. The regularity by the manifold features just build probability distribution model by globally statistical information from the population, yet, the efficiency of promising individuals is not well exploited, which is not beneficial to search and optimization process. Hereby, an incremental tournament local searcher is designed to exploit local information efficiently and accelerate convergence to the true Pareto-optimal front. Besides, since ε-dominance is a strategy that can make multiobjective algorithm gain well distributed solutions and has low computational complexity, ε-dominance and the incremental tournament local searcher are combined here. The novel memetic multiobjective estimation of distribution algorithm, MMEDA, was proposed accordingly. The algorithm is validated by experiment on twenty-two test problems with and without variable linkages of diverse complexities. Compared with three state-of-the-art multiobjective optimization algorithms, our algorithm achieves comparable results in terms of convergence and diversity metrics.
Incremental approach for radial basis functions mesh deformation with greedy algorithm
Selim, Mohamed M.; Koomullil, Roy P.; Shehata, Ahmed S.
2017-07-01
Mesh Deformation is an important element of any fluid-structure interaction simulation. In this article, a new methodology is presented for the deformation of volume meshes using incremental radial basis function (RBF) based interpolation. A greedy algorithm is used to select a small subset of the surface nodes iteratively. Two incremental approaches are introduced to solve the RBF system of equations: 1) block matrix inversion based approach and 2) modified LU decomposition approach. The use of incremental approach decreased the computational complexity of solving the system of equations within each greedy algorithm's iteration from O (n3) to O (n2). Results are presented from an accuracy study using specified deformations on a 2D surface. Mesh deformations for bending and twisting of a 3D rectangular supercritical wing have been demonstrated. Outcomes showed the incremental approaches reduce the CPU time up to 67% as compared to a traditional RBF matrix solver. Finally, the proposed mesh deformation approach was integrated within a fluid-structure interaction solver for investigating a flow induced cantilever beam vibration.
Institute of Scientific and Technical Information of China (English)
LI Hong-wei; YANG He; SUN Zhi-chao
2006-01-01
Computational stability and efficiency are the key problems for numerical modeling of crystal plasticity,which will limit its development and application in finite element (FE) simulation evidently. Since implicit iterative algorithms are inefficient and have difficulty to determine initial values,an explicit incremental-update algorithm for the elasto-viscoplastic constitutive relation was developed in the intermediate frame by using the second Piola-Kirchoff (P-K) stress and Green stain. The increment of stress and slip resistance were solved by a calculation loop of linear equations sets. The reorientation of the crystal as well as the elastic strain can be obtained from a polar decomposition of the elastic deformation gradient. User material subroutine VUMAT was developed to combine crystal elasto-viscoplastic constitutive model with ABAQUS/Explicit. Numerical studies were performed on a cubic upset model with OFHC material (FCC crystal). The comparison of the numerical results with those obtained by implicit iterative algorithm and those from experiments demonstrates that the explicit algorithm is reliable. Furthermore,the effect rules of material anisotropy,rate sensitivity coefficient (RSC) and loading speeds on the deformation were studied. The numerical studies indicate that the explicit algorithm is suitable and efficient for large deformation analyses where anisotropy due to texture is important.
Directory of Open Access Journals (Sweden)
O. Ahmed
2011-01-01
Full Text Available Packet classification plays a crucial role for a number of network services such as policy-based routing, firewalls, and traffic billing, to name a few. However, classification can be a bottleneck in the above-mentioned applications if not implemented properly and efficiently. In this paper, we propose PCIU, a novel classification algorithm, which improves upon previously published work. PCIU provides lower preprocessing time, lower memory consumption, ease of incremental rule update, and reasonable classification time compared to state-of-the-art algorithms. The proposed algorithm was evaluated and compared to RFC and HiCut using several benchmarks. Results obtained indicate that PCIU outperforms these algorithms in terms of speed, memory usage, incremental update capability, and preprocessing time. The algorithm, furthermore, was improved and made more accessible for a variety of applications through implementation in hardware. Two such implementations are detailed and discussed in this paper. The results indicate that a hardware/software codesign approach results in a slower, but easier to optimize and improve within time constraints, PCIU solution. A hardware accelerator based on an ESL approach using Handel-C, on the other hand, resulted in a 31x speed-up over a pure software implementation running on a state of the art Xeon processor.
Incremental Learning of Context Free Grammars by Parsing-Based Rule Generation and Rule Set Search
Nakamura, Katsuhiko; Hoshina, Akemi
This paper discusses recent improvements and extensions in Synapse system for inductive inference of context free grammars (CFGs) from sample strings. Synapse uses incremental learning, rule generation based on bottom-up parsing, and the search for rule sets. The form of production rules in the previous system is extended from Revised Chomsky Normal Form A→βγ to Extended Chomsky Normal Form, which also includes A→B, where each of β and γ is either a terminal or nonterminal symbol. From the result of bottom-up parsing, a rule generation mechanism synthesizes minimum production rules required for parsing positive samples. Instead of inductive CYK algorithm in the previous version of Synapse, the improved version uses a novel rule generation method, called ``bridging,'' which bridges the lacked part of the derivation tree for the positive string. The improved version also employs a novel search strategy, called serial search in addition to minimum rule set search. The synthesis of grammars by the serial search is faster than the minimum set search in most cases. On the other hand, the size of the generated CFGs is generally larger than that by the minimum set search, and the system can find no appropriate grammar for some CFL by the serial search. The paper shows experimental results of incremental learning of several fundamental CFGs and compares the methods of rule generation and search strategies.
An Improved Incremental Learning Approach for KPI Prognosis of Dynamic Fuel Cell System.
Yin, Shen; Xie, Xiaochen; Lam, James; Cheung, Kie Chung; Gao, Huijun
2016-12-01
The key performance indicator (KPI) has an important practical value with respect to the product quality and economic benefits for modern industry. To cope with the KPI prognosis issue under nonlinear conditions, this paper presents an improved incremental learning approach based on available process measurements. The proposed approach takes advantage of the algorithm overlapping of locally weighted projection regression (LWPR) and partial least squares (PLS), implementing the PLS-based prognosis in each locally linear model produced by the incremental learning process of LWPR. The global prognosis results including KPI prediction and process monitoring are obtained from the corresponding normalized weighted means of all the local models. The statistical indicators for prognosis are enhanced as well by the design of novel KPI-related and KPI-unrelated statistics with suitable control limits for non-Gaussian data. For application-oriented purpose, the process measurements from real datasets of a proton exchange membrane fuel cell system are employed to demonstrate the effectiveness of KPI prognosis. The proposed approach is finally extended to a long-term voltage prediction for potential reference of further fuel cell applications.
Polyceptron: A Polyhedral Learning Algorithm
Manwani, Naresh
2011-01-01
In this paper we propose a new algorithm for learning polyhedral classifiers which we call as Polyceptron. It is a Perception like algorithm which updates the parameters only when the current classifier misclassifies any training data. We give both batch and online version of Polyceptron algorithm. Finally we give experimental results to show the effectiveness of our approach.
Incremental Density-Based Link Clustering Algorithm for Community Detection in Dynamic Networks
Directory of Open Access Journals (Sweden)
Fanrong Meng
2016-01-01
Full Text Available Community detection in complex networks has become a research hotspot in recent years. However, most of the existing community detection algorithms are designed for the static networks; namely, the connections between the nodes are invariable. In this paper, we propose an incremental density-based link clustering algorithm for community detection in dynamic networks, iDBLINK. This algorithm is an extended version of DBLINK which is proposed in our previous work. It can update the local link community structure in the current moment through the change of similarity between the edges at the adjacent moments, which includes the creation, growth, merging, deletion, contraction, and division of link communities. Extensive experimental results demonstrate that iDBLINK not only has a great time efficiency, but also maintains a high quality community detection performance when the network topology is changing.
A parallel and incremental algorithm for efficient unique signature discovery on DNA databases
Directory of Open Access Journals (Sweden)
Lee Hsiao
2010-03-01
Full Text Available Abstract Background DNA signatures are distinct short nucleotide sequences that provide valuable information that is used for various purposes, such as the design of Polymerase Chain Reaction primers and microarray experiments. Biologists usually use a discovery algorithm to find unique signatures from DNA databases, and then apply the signatures to microarray experiments. Such discovery algorithms require to set some input factors, such as signature length l and mismatch tolerance d, which affect the discovery results. However, suggestions about how to select proper factor values are rare, especially when an unfamiliar DNA database is used. In most cases, biologists typically select factor values based on experience, or even by guessing. If the discovered result is unsatisfactory, biologists change the input factors of the algorithm to obtain a new result. This process is repeated until a proper result is obtained. Implicit signatures under the discovery condition (l, d are defined as the signatures of length ≤ l with mismatch tolerance ≥ d. A discovery algorithm that could discover all implicit signatures, such that those that meet the requirements concerning the results, would be more helpful than one that depends on trial and error. However, existing discovery algorithms do not address the need to discover all implicit signatures. Results This work proposes two discovery algorithms - the consecutive multiple discovery (CMD algorithm and the parallel and incremental signature discovery (PISD algorithm. The PISD algorithm is designed for efficiently discovering signatures under a certain discovery condition. The algorithm finds new results by using previously discovered results as candidates, rather than by using the whole database. The PISD algorithm further increases discovery efficiency by applying parallel computing. The CMD algorithm is designed to discover implicit signatures efficiently. It uses the PISD algorithm as a kernel
Institute of Scientific and Technical Information of China (English)
蔚承建; 何振亚; 张毅锋; 杨绿溪
2000-01-01
本文扩展了基于人口的增量学习算法使其每个基因可呈现多个品质值，这反映了自然演化系统中基因型和表现型的多向性和多源性，提出了用熵来判断进化过程的可进化性.用该方法求解典型的组合优化问题—旅行推销员问题，多数结果优于最好的进化算法结果.%In this paper the population-based incremental learning method is extended to a form of multiple traits for one gene to reflect pleiotropic and polygenic characters in natural evolved systems and the entropy of a probability distribution is used to decide the evolvability of the system.This method is used to solve a typical combinatorial optimization problem- the symmetric traveling salesman problem.Some results are better than the best existing algorithm of evolutionary algorithms for the problem.
Peña, M.
2016-10-01
Achieving acceptable signal-to-noise ratio (SNR) can be difficult when working in sparsely populated waters and/or when species have low scattering such as fluid filled animals. The increasing use of higher frequencies and the study of deeper depths in fisheries acoustics, as well as the use of commercial vessels, is raising the need to employ good denoising algorithms. The use of a lower Sv threshold to remove noise or unwanted targets is not suitable in many cases and increases the relative background noise component in the echogram, demanding more effectiveness from denoising algorithms. The Adaptive Wiener Filter (AWF) denoising algorithm is presented in this study. The technique is based on the AWF commonly used in digital photography and video enhancement. The algorithm firstly increments the quality of the data with a variance-dependent smoothing, before estimating the noise level as the envelope of the Sv minima. The AWF denoising algorithm outperforms existing algorithms in the presence of gaussian, speckle and salt & pepper noise, although impulse noise needs to be previously removed. Cleaned echograms present homogenous echotraces with outlined edges.
Lelu, Alain; Cuxac, Pascal
2008-01-01
We address here two major challenges presented by dynamic data mining: 1) the stability challenge: we have implemented a rigorous incremental density-based clustering algorithm, independent from any initial conditions and ordering of the data-vectors stream, 2) the cognitive challenge: we have implemented a stringent selection process of association rules between clusters at time t-1 and time t for directly generating the main conclusions about the dynamics of a data-stream. We illustrate these points with an application to a two years and 2600 documents scientific information database.
Teramae, Tatsuya; Kushida, Daisuke; Takemori, Fumiaki; Kitamura, Akira
Authors proposed the estimation method combining k-means algorithm and NN for evaluating massage. However, this estimation method has a problem that discrimination ratio is decreased to new user. There are two causes of this problem. One is that generalization of NN is bad. Another one is that clustering result by k-means algorithm has not high correlation coefficient in a class. Then, this research proposes k-means algorithm according to correlation coefficient and incremental learning for NN. The proposed k-means algorithm is method included evaluation function based on correlation coefficient. Incremental learning is method that NN is learned by new data and initialized weight based on the existing data. The effect of proposed methods are verified by estimation result using EEG data when testee is given massage.
Directory of Open Access Journals (Sweden)
WANG Junshu
2015-09-01
Full Text Available An incremental classification algorithm INC_SPEC_MPext was proposed for hyperspectral remote sensing images based on spectral and spatial information. The spatial information was extracted by building morphological profiles based on several principle components of hyperspectral image. The morphological profiles were combined together in extended morphological profiles (MPext. Combine spectral and MPext to enrich knowledge and utilize the useful information of unlabeled data at the most extent to optimize the classifier. Pick out high confidence data and add to training set, then retrain the classifier with augmented training set to predict the rest samples. The process was performed iteratively. The proposed algorithm was tested on AVIRIS Indian Pines and Hyperion EO-1 Botswana data, which take on different covers, and experimental results show low classification cost and significant improvements in terms of accuracies and Kappa coefficient under limited training samples compared with the classification results based on spectral, MPext and the combination of sepctral and MPext.
An Incremental Classification Algorithm for Mining Data with Feature Space Heterogeneity
Directory of Open Access Journals (Sweden)
Yu Wang
2014-01-01
Full Text Available Feature space heterogeneity often exists in many real world data sets so that some features are of different importance for classification over different subsets. Moreover, the pattern of feature space heterogeneity might dynamically change over time as more and more data are accumulated. In this paper, we develop an incremental classification algorithm, Supervised Clustering for Classification with Feature Space Heterogeneity (SCCFSH, to address this problem. In our approach, supervised clustering is implemented to obtain a number of clusters such that samples in each cluster are from the same class. After the removal of outliers, relevance of features in each cluster is calculated based on their variations in this cluster. The feature relevance is incorporated into distance calculation for classification. The main advantage of SCCFSH lies in the fact that it is capable of solving a classification problem with feature space heterogeneity in an incremental way, which is favorable for online classification tasks with continuously changing data. Experimental results on a series of data sets and application to a database marketing problem show the efficiency and effectiveness of the proposed approach.
Automated test data generation for branch testing using incremental genetic algorithm
Indian Academy of Sciences (India)
T MANIKUMAR; A JOHN SANJEEV KUMAR; R MARUTHAMUTHU
2016-09-01
Cost of software testing can be reduced by automated test data generation to find a minimal set of data that has maximum coverage. Search-based software testing (SBST) is one of the techniques recently used for automated testing task. SBST makes use of control flow graph (CFG) and meta-heuristic search algorithms to accomplish the process. This paper focuses on test data generation for branch coverage. A major drawback in using meta-heuristic techniques is that the CFG paths have to be traversed from the starting node to end node for each automated test data. This kind of traversal could be improved by branch ordering, together with elitism. But still the population size and the number of iterations are maintained as the same to keep all the branches alive. In this paper, we present an incremental genetic algorithm (IGA) for branch coverage testing. Initially, a classical genetic algorithm (GA) is used to construct the population with the best parents for each branch node, and the IGA is started with these parents as the initial population. Hence, it is not necessary to maintain a huge population size and large number of iterations to cover all the branches. The performance is analyzed with five benchmark programs studied from the literature. The experimental results indicate that the proposed IGA search technique outperforms the other meta-heuristic search techniques in terms of memory usage and scalability.
Directory of Open Access Journals (Sweden)
Dhananjay Choudhary
2014-08-01
Full Text Available The two basic topologies of switch mode DC-DC converters (Buck and Boost are analyzed with a view of their use in PV (photovoltaic systems, as the photovoltaic generator exhibits non-linear characteristics due to the change in environmental condition and load variation. As the efficiency of PV panels is low it becomes mandatory to extract maximum power from the PV panel at a given period of time. Several MPPT algorithms with different types of converters are being proposed for extracting maximum power from the PV panel. It is found that the nature of load plays an important role in the choice of topology. This paper investigates the implementation issues of Incremental Conductance method with Buck and Boost Converters. Mathematical analysis and desirable steady-state operating point of the converters are derived to give satisfactory maximum power point tracking operation.
Novel Newton's learning algorithm of neural networks
Institute of Scientific and Technical Information of China (English)
Long Ning; Zhang Fengli
2006-01-01
Newton's learning algorithm of NN is presented and realized. In theory, the convergence rate of learning algorithm of NN based on Newton's method must be faster than BP's and other learning algorithms, because the gradient method is linearly convergent while Newton's method has second order convergence rate.The fast computing algorithm of Hesse matrix of the cost function of NN is proposed and it is the theory basis of the improvement of Newton's learning algorithm. Simulation results show that the convergence rate of Newton's learning algorithm is high and apparently faster than the traditional BP method's, and the robustness of Newton's learning algorithm is also better than BP method's.
Incremental Discriminant Analysis in Tensor Space
Chang, Liu; Weidong, Zhao; Tao, Yan; Qiang, Pu; Xiaodan, Du
2015-01-01
To study incremental machine learning in tensor space, this paper proposes incremental tensor discriminant analysis. The algorithm employs tensor representation to carry on discriminant analysis and combine incremental learning to alleviate the computational cost. This paper proves that the algorithm can be unified into the graph framework theoretically and analyzes the time and space complexity in detail. The experiments on facial image detection have shown that the algorithm not only achieves sound performance compared with other algorithms, but also reduces the computational issues apparently. PMID:26339229
A Self-Organizing Incremental Neural Network based on local distribution learning.
Xing, Youlu; Shi, Xiaofeng; Shen, Furao; Zhou, Ke; Zhao, Jinxi
2016-12-01
In this paper, we propose an unsupervised incremental learning neural network based on local distribution learning, which is called Local Distribution Self-Organizing Incremental Neural Network (LD-SOINN). The LD-SOINN combines the advantages of incremental learning and matrix learning. It can automatically discover suitable nodes to fit the learning data in an incremental way without a priori knowledge such as the structure of the network. The nodes of the network store rich local information regarding the learning data. The adaptive vigilance parameter guarantees that LD-SOINN is able to add new nodes for new knowledge automatically and the number of nodes will not grow unlimitedly. While the learning process continues, nodes that are close to each other and have similar principal components are merged to obtain a concise local representation, which we call a relaxation data representation. A denoising process based on density is designed to reduce the influence of noise. Experiments show that the LD-SOINN performs well on both artificial and real-word data. Copyright © 2016 Elsevier Ltd. All rights reserved.
A High-Performance Adaptive Incremental Conductance MPPT Algorithm for Photovoltaic Systems
Directory of Open Access Journals (Sweden)
Chendi Li
2016-04-01
Full Text Available The output characteristics of photovoltaic (PV arrays vary with the change of environment, and maximum power point (MPP tracking (MPPT techniques are thus employed to extract the peak power from PV arrays. Based on the analysis of existing MPPT methods, a novel incremental conductance (INC MPPT algorithm is proposed with an adaptive variable step size. The proposed algorithm automatically regulates the step size to track the MPP through a step size adjustment coefficient, and a user predefined constant is unnecessary for the convergence of the MPPT method, thus simplifying the design of the PV system. A tuning method of initial step sizes is also presented, which is derived from the approximate linear relationship between the open-circuit voltage and MPP voltage. Compared with the conventional INC method, the proposed method can achieve faster dynamic response and better steady state performance simultaneously under the conditions of extreme irradiance changes. A Matlab/Simulink model and a 5 kW PV system prototype controlled by a digital signal controller (TMS320F28035 were established. Simulations and experimental results further validate the effectiveness of the proposed method.
Incremental learning in trust-based vehicle control
Karlsen, Robert E.; Mikulski, Dariusz G.
2016-05-01
In many multi-agent teams, entities fully trust their teammates and the information that they provide. But we know that this can be a false assumption in many cases, which can lead to sub-optimal performance of the team. In this paper, we build off of prior work in developing a simple model of estimating and responding to different levels of trust between team members. We have chosen to use a vehicle convoy application to generate data and test the operation of the trust estimation algorithm and its evolution. We build on prior work, where a cruise control algorithm to maintain following distance was implemented, as were algorithms to adjust follow distance based on trust in the leader and the capability for a lead vehicle to "look back" and adjust its speed based on the follow distance of the vehicle behind. In this paper we introduce a mechanism, based on trust, which negotiates between two follow behaviors, either follow the vehicle ahead or drive towards a set of fixed waypoints. We also add a nonlinear relationship between trust and follow distance to provide a knob to adjust convoy performance and the paper shows that it does adjust performance, somewhat as expected.
A Novel Incremental Mining Algorithm of Frequent Patterns for Web Usage Mining
Institute of Scientific and Technical Information of China (English)
DONG Yihong; ZHUANG Yueting; TAI Xiaoying
2007-01-01
Because data warehouse is frequently changing, incremental data leads to old knowledge which is mined formerly unavailable. In order to maintain the discovered knowledge and patterns dynamically, this study presents a novel algorithm updating for global frequent patterns-IPARUC. A rapid clustering method is introduced to divide database into n parts in IPARUC firstly, where the data are similar in the same part. Then, the nodes in the tree are adjusted dynamically in inserting process by "pruning and laying back" to keep the frequency descending order so that they can be shared to approaching optimization. Finally local frequent itemsets mined from each local dataset are merged into global frequent itemsets. The results of experimental study are very encouraging. It is obvious from experiment that IPARUC is more effective and efficient than other two contrastive methods. Furthermore, there is significant application potential to a prototype of Web log Analyzer in web usage mining that can help us to discover useful knowledge effectively, even help managers making decision.
Gao, Yaozong; Zhan, Yiqiang
2015-01-01
Image-guided radiotherapy (IGRT) requires fast and accurate localization of the prostate in 3-D treatment-guided radiotherapy, which is challenging due to low tissue contrast and large anatomical variation across patients. On the other hand, the IGRT workflow involves collecting a series of computed tomography (CT) images from the same patient under treatment. These images contain valuable patient-specific information yet are often neglected by previous works. In this paper, we propose a novel learning framework, namely incremental learning with selective memory (ILSM), to effectively learn the patient-specific appearance characteristics from these patient-specific images. Specifically, starting with a population-based discriminative appearance model, ILSM aims to “personalize” the model to fit patient-specific appearance characteristics. The model is personalized with two steps: backward pruning that discards obsolete population-based knowledge and forward learning that incorporates patient-specific characteristics. By effectively combining the patient-specific characteristics with the general population statistics, the incrementally learned appearance model can localize the prostate of a specific patient much more accurately. This work has three contributions: 1) the proposed incremental learning framework can capture patient-specific characteristics more effectively, compared to traditional learning schemes, such as pure patient-specific learning, population-based learning, and mixture learning with patient-specific and population data; 2) this learning framework does not have any parametric model assumption, hence, allowing the adoption of any discriminative classifier; and 3) using ILSM, we can localize the prostate in treatment CTs accurately (DSC ∼0.89) and fast (∼4 s), which satisfies the real-world clinical requirements of IGRT. PMID:24495983
Gao, Yaozong; Zhan, Yiqiang; Shen, Dinggang
2014-02-01
Image-guided radiotherapy (IGRT) requires fast and accurate localization of the prostate in 3-D treatment-guided radiotherapy, which is challenging due to low tissue contrast and large anatomical variation across patients. On the other hand, the IGRT workflow involves collecting a series of computed tomography (CT) images from the same patient under treatment. These images contain valuable patient-specific information yet are often neglected by previous works. In this paper, we propose a novel learning framework, namely incremental learning with selective memory (ILSM), to effectively learn the patient-specific appearance characteristics from these patient-specific images. Specifically, starting with a population-based discriminative appearance model, ILSM aims to "personalize" the model to fit patient-specific appearance characteristics. The model is personalized with two steps: backward pruning that discards obsolete population-based knowledge and forward learning that incorporates patient-specific characteristics. By effectively combining the patient-specific characteristics with the general population statistics, the incrementally learned appearance model can localize the prostate of a specific patient much more accurately. This work has three contributions: 1) the proposed incremental learning framework can capture patient-specific characteristics more effectively, compared to traditional learning schemes, such as pure patient-specific learning, population-based learning, and mixture learning with patient-specific and population data; 2) this learning framework does not have any parametric model assumption, hence, allowing the adoption of any discriminative classifier; and 3) using ILSM, we can localize the prostate in treatment CTs accurately (DSC ∼ 0.89 ) and fast ( ∼ 4 s), which satisfies the real-world clinical requirements of IGRT.
Learning in Different Modes: The Interaction Between Incremental and Radical Change
DEFF Research Database (Denmark)
Petersen, Anders Hedegaard; Boer, Harry; Gertsen, Frank
2004-01-01
The objective of the study presented in this article is to contribute to the development of theory on continuous innovation, i.e. the combination of operationally effective exploitation and strategically flexible exploration. A longitudinal case study is presented of the interaction between...... incremental and radical change in Danish company, observed through the lens of organizational learning. The radical change process is described in five phases, each of which had its own effects on incremental change initiatives in the company. The research identified four factors explaining these effects, all...
Directory of Open Access Journals (Sweden)
Ting Wang
2015-01-01
Full Text Available Machine learning is a very important approach to pattern classification. This paper provides a better insight into Incremental Attribute Learning (IAL with further analysis as to why it can exhibit better performance than conventional batch training. IAL is a novel supervised machine learning strategy, which gradually trains features in one or more chunks. Previous research showed that IAL can obtain lower classification error rates than a conventional batch training approach. Yet the reason for that is still not very clear. In this study, the feasibility of IAL is verified by mathematical approaches. Moreover, experimental results derived by IAL neural networks on benchmarks also confirm the mathematical validation.
Energy Technology Data Exchange (ETDEWEB)
Baraldi, Piero, E-mail: piero.baraldi@polimi.i [Dipartimento di Energia - Sezione Ingegneria Nucleare, Politecnico di Milano, via Ponzio 34/3, 20133 Milano (Italy); Razavi-Far, Roozbeh [Dipartimento di Energia - Sezione Ingegneria Nucleare, Politecnico di Milano, via Ponzio 34/3, 20133 Milano (Italy); Zio, Enrico [Dipartimento di Energia - Sezione Ingegneria Nucleare, Politecnico di Milano, via Ponzio 34/3, 20133 Milano (Italy); Ecole Centrale Paris-Supelec, Paris (France)
2011-04-15
An important requirement for the practical implementation of empirical diagnostic systems is the capability of classifying transients in all plant operational conditions. The present paper proposes an approach based on an ensemble of classifiers for incrementally learning transients under different operational conditions. New classifiers are added to the ensemble where transients occurring in new operational conditions are not satisfactorily classified. The construction of the ensemble is made by bagging; the base classifier is a supervised Fuzzy C Means (FCM) classifier whose outcomes are combined by majority voting. The incremental learning procedure is applied to the identification of simulated transients in the feedwater system of a Boiling Water Reactor (BWR) under different reactor power levels.
Kompella, Varun Raj; Schmidhuber, Juergen
2011-01-01
Slow Feature Analysis (SFA) extracts features representing the underlying causes of changes within a temporally coherent high-dimensional raw sensory input signal. Our novel incremental version of SFA (IncSFA) combines incremental Principal Components Analysis and Minor Components Analysis. Unlike standard batch-based SFA, IncSFA adapts along with non-stationary environments, is amenable to episodic training, is not corrupted by outliers, and is covariance-free. These properties make IncSFA a generally useful unsupervised preprocessor for autonomous learning agents and robots. In IncSFA, the CCIPCA and MCA updates take the form of Hebbian and anti-Hebbian updating, extending the biological plausibility of SFA. In both single node and deep network versions, IncSFA learns to encode its input streams (such as high-dimensional video) by informative slow features representing meaningful abstract environmental properties. It can handle cases where batch SFA fails.
Stable force-myographic control of a prosthetic hand using incremental learning.
Rasouli, Mahdi; Ghosh, Rohan; Lee, Wang Wei; Thakor, Nitish V; Kukreja, Sunil
2015-08-01
Force myography has been proposed as an appealing alternative to electromyography for control of upper limb prosthesis. A limitation of this technique is the non-stationary nature of the recorded force data. Force patterns vary under influence of various factors such as change in orientation and position of the prosthesis. We hereby propose an incremental learning method to overcome this limitation. We use an online sequential extreme learning machine where occasional updates allow continual adaptation to signal changes. The applicability and effectiveness of this approach is demonstrated for predicting the hand status from forearm muscle forces at various arm positions. The results show that incremental updates are indeed effective to maintain a stable level of performance, achieving an average classification accuracy of 98.75% for two subjects.
Efficient Learning Algorithms with Limited Information
De, Anindya
2013-01-01
The thesis explores efficient learning algorithms in settings which are more restrictive than the PAC model of learning (Valiant) in one of the following two senses: (i) The learning algorithm has a very weak access to the unknown function, as in, it does not get labeled samples for the unknown function (ii) The error guarantee required from the…
Exploitation of linkage learning in evolutionary algorithms
Chen, Ying-ping
2010-01-01
The exploitation of linkage learning is enhancing the performance of evolutionary algorithms. This monograph examines recent progress in linkage learning, with a series of focused technical chapters that cover developments and trends in the field.
Incremental learning of 3D-DCT compact representations for robust visual tracking.
Li, Xi; Dick, Anthony; Shen, Chunhua; van den Hengel, Anton; Wang, Hanzi
2013-04-01
Visual tracking usually requires an object appearance model that is robust to changing illumination, pose, and other factors encountered in video. Many recent trackers utilize appearance samples in previous frames to form the bases upon which the object appearance model is built. This approach has the following limitations: 1) The bases are data driven, so they can be easily corrupted, and 2) it is difficult to robustly update the bases in challenging situations. In this paper, we construct an appearance model using the 3D discrete cosine transform (3D-DCT). The 3D-DCT is based on a set of cosine basis functions which are determined by the dimensions of the 3D signal and thus independent of the input video data. In addition, the 3D-DCT can generate a compact energy spectrum whose high-frequency coefficients are sparse if the appearance samples are similar. By discarding these high-frequency coefficients, we simultaneously obtain a compact 3D-DCT-based object representation and a signal reconstruction-based similarity measure (reflecting the information loss from signal reconstruction). To efficiently update the object representation, we propose an incremental 3D-DCT algorithm which decomposes the 3D-DCT into successive operations of the 2D discrete cosine transform (2D-DCT) and 1D discrete cosine transform (1D-DCT) on the input video data. As a result, the incremental 3D-DCT algorithm only needs to compute the 2D-DCT for newly added frames as well as the 1D-DCT along the third dimension, which significantly reduces the computational complexity. Based on this incremental 3D-DCT algorithm, we design a discriminative criterion to evaluate the likelihood of a test sample belonging to the foreground object. We then embed the discriminative criterion into a particle filtering framework for object state inference over time. Experimental results demonstrate the effectiveness and robustness of the proposed tracker.
DEFF Research Database (Denmark)
Wang, Ting; Guan, Sheng-Uei; Puthusserypady, Sadasivan;
2014-01-01
estimation. Moreover, a criterion that summarizes all the produced values of AD is employed with a GA (Genetic Algorithm)-based approach to obtain the optimum feature ordering for classification problems based on neural networks by means of IAL. Compared with the feature ordering obtained by other approaches......, the method proposed in this paper exhibits better performance in the final classification results. Such a phenomenon indicates that, (i) the feature discrimination ability should be incrementally estimated in IAL, and (ii) the feature ordering derived by AD and its corresponding approaches are applicable...
An Algorithm for Learning the Essential Graph
Noble, John M
2010-01-01
This article presents an algorithm for learning the essential graph of a Bayesian network. The basis of the algorithm is the Maximum Minimum Parents and Children algorithm developed by previous authors, with three substantial modifications. The MMPC algorithm is the first stage of the Maximum Minimum Hill Climbing algorithm for learning the directed acyclic graph of a Bayesian network, introduced by previous authors. The MMHC algorithm runs in two phases; firstly, the MMPC algorithm to locate the skeleton and secondly an edge orientation phase. The computationally expensive part is the edge orientation phase. The first modification introduced to the MMPC algorithm, which requires little additional computational cost, is to obtain the immoralities and hence the essential graph. This renders the edge orientation phase, the computationally expensive part, unnecessary, since the entire Markov structure that can be derived from data is present in the essential graph. Secondly, the MMPC algorithm can accept indepen...
Indexing Density Models for Incremental Learning and Anytime Classification on Data Streams
DEFF Research Database (Denmark)
Seidl, Thomas; Assent, Ira; Kranen, Philipp
2009-01-01
Classification of streaming data faces three basic challenges: it has to deal with huge amounts of data, the varying time between two stream data items must be used best possible (anytime classification) and additional training data must be incrementally learned (anytime learning) for applying...... the classifier consistently to fast data streams. In this work, we propose a novel index-based technique that can handle all three of the above challenges using the established Bayes classifier on effective kernel density estimators. Our novel Bayes tree automatically generates (adapted efficiently...... point of interruption. Moreover, we propose a novel evaluation method for anytime classification using Poisson streams and demonstrate the anytime learning performance of the Bayes tree....
Learning Intelligent Genetic Algorithms Using Japanese Nonograms
Tsai, Jinn-Tsong; Chou, Ping-Yi; Fang, Jia-Cen
2012-01-01
An intelligent genetic algorithm (IGA) is proposed to solve Japanese nonograms and is used as a method in a university course to learn evolutionary algorithms. The IGA combines the global exploration capabilities of a canonical genetic algorithm (CGA) with effective condensed encoding, improved fitness function, and modified crossover and…
Learning Intelligent Genetic Algorithms Using Japanese Nonograms
Tsai, Jinn-Tsong; Chou, Ping-Yi; Fang, Jia-Cen
2012-01-01
An intelligent genetic algorithm (IGA) is proposed to solve Japanese nonograms and is used as a method in a university course to learn evolutionary algorithms. The IGA combines the global exploration capabilities of a canonical genetic algorithm (CGA) with effective condensed encoding, improved fitness function, and modified crossover and…
Learning from nature: Nature-inspired algorithms
DEFF Research Database (Denmark)
Albeanu, Grigore; Madsen, Henrik; Popentiu-Vladicescu, Florin
2016-01-01
During last decade, the nature has inspired researchers to develop new algorithms. The largest collection of nature-inspired algorithms is biology-inspired: swarm intelligence (particle swarm optimization, ant colony optimization, cuckoo search, bees' algorithm, bat algorithm, firefly algorithm etc...... on collective social behaviour of organisms, researchers have developed optimization strategies taking into account not only the individuals, but also groups and environment. However, learning from nature, new classes of approaches can be identified, tested and compared against already available algorithms....... This work reviews the most effective nature-inspired algorithms and describes learning strategies based on nature oriented thinking. Examples and the benefits obtained from applying nature-inspired strategies in test generation, learners group optimization, and artificial immune systems for learning...
Indian Academy of Sciences (India)
Sachin Vrajlal Rajani; Vivek J Pandya
2015-02-01
Solar energy is a clean, green and renewable source of energy. It is available in abundance in nature. Solar cells by photovoltaic action are able to convert the solar energy into electric current. The output power of solar cell depends upon factors such as solar irradiation (insolation), temperature and other climatic conditions. Present commercial efficiency of solar cells is not greater than 15% and therefore the available efficiency is to be exploited to the maximum possible value and the maximum power point tracking (MPPT) with the aid of power electronics to solar array can make this possible. There are many algorithms proposed to realize maximum power point tracking. These algorithms have their own merits and limitations. In this paper, an attempt is made to understand the basic functionality of the two most popular algorithms viz. Perturb and Observe (P & O) algorithm and Incremental conductance algorithm. These algorithms are compared by simulating a 100 kW solar power generating station connected to grid. MATLAB M-files are generated to understand MPPT and its dependency on insolation and temperature. MATLAB Simulink software is used to simulate the MPPT systems. Simulation results are presented to verify these assumptions.
Directory of Open Access Journals (Sweden)
Simon Fong
2015-01-01
Full Text Available A prime objective in constructing data streaming mining models is to achieve good accuracy, fast learning, and robustness to noise. Although many techniques have been proposed in the past, efforts to improve the accuracy of classification models have been somewhat disparate. These techniques include, but are not limited to, feature selection, dimensionality reduction, and the removal of noise from training data. One limitation common to all of these techniques is the assumption that the full training dataset must be applied. Although this has been effective for traditional batch training, it may not be practical for incremental classifier learning, also known as data stream mining, where only a single pass of the data stream is seen at a time. Because data streams can amount to infinity and the so-called big data phenomenon, the data preprocessing time must be kept to a minimum. This paper introduces a new data preprocessing strategy suitable for the progressive purging of noisy data from the training dataset without the need to process the whole dataset at one time. This strategy is shown via a computer simulation to provide the significant benefit of allowing for the dynamic removal of bad records from the incremental classifier learning process.
Directory of Open Access Journals (Sweden)
Yoo-Geun Ham
2016-01-01
Full Text Available This study introduces a modified version of the incremental analysis updates (IAU, called the nonstationary IAU (NIAU method, to improve the assimilation accuracy of the IAU while keeping the continuity of the analysis. Similar to the IAU, the NIAU is designed to add analysis increments at every model time step to improve the continuity in the intermittent data assimilation. However, unlike the IAU, the NIAU procedure uses time-evolved forcing using the forward operator as corrections to the model. The solution of the NIAU is superior to that of the forward IAU, of which analysis is performed at the beginning of the time window for adding the IAU forcing, in terms of the accuracy of the analysis field. It is because, in the linear systems, the NIAU solution equals that in an intermittent data assimilation method at the end of the assimilation interval. To have the filtering property in the NIAU, a forward operator to propagate the increment is reconstructed with only dominant singular vectors. An illustration of those advantages of the NIAU is given using the simple 40-variable Lorenz model.
Validation and incremental value of the hybrid algorithm for CTO PCI.
Pershad, Ashish; Eddin, Moneer; Girotra, Sudhakar; Cotugno, Richard; Daniels, David; Lombardi, William
2014-10-01
To evaluate the outcomes and benefits of using the hybrid algorithm for chronic total occlusion (CTO) percutaneous coronary intervention (PCI). The hybrid algorithm harmonizes antegrade and retrograde techniques for performing CTO PCI. It has the potential to increase success rates and improve efficiency for CTO PCI. No previous data have analyzed the impact of this algorithm on CTO PCI success rates and procedural efficiency. Retrospective analysis of contemporary CTO PCI performed at two high-volume centers with adoption of the hybrid technique was compared to previously published CTO outcomes in a well matched group of patients and lesion subsets. After adoption of the hybrid algorithm, technical success was significantly higher in the post hybrid algorithm group 189/198 (95.4%) vs the pre-algorithm group 367/462 (79.4%) (P CTO PCI. © 2014 Wiley Periodicals, Inc.
Reinforcement Learning Algorithms in Humanoid Robotics
Katic, Dusko; Vukobratovic, Miomir
2007-01-01
This study considers a optimal solutions for application of reinforcement learning in humanoid robotics Humanoid Robotics is a very challenging domain for reinforcement learning, Reinforcement learning control algorithms represents general framework to take traditional robotics towards true autonomy and versatility. The reinforcement learning paradigm described above has been successfully implemented for some special type of humanoid robots in the last 10 years. Reinforcement learning is well...
Stable Myoelectric Control of a Hand Prosthesis using Non-Linear Incremental Learning
Directory of Open Access Journals (Sweden)
Arjan eGijsberts
2014-02-01
Full Text Available Stable myoelectric control of hand prostheses remains an open problem. The only successful human-machine interface is surface electromyography, typically allowing control of a few degrees of freedom. Machine learning techniques may have the potential to remove these limitations, but their performance is thus far inadequate: myoelectric signals change over time under the influence of various factors, deteriorating control performance. It is therefore necessary, in the standard approach, to regularly retrain a new model from scratch.We hereby propose a non-linear incremental learning method in which occasional updates with a modest amount of novel training data allow continual adaptation to the changes in the signals. In particular, Incremental Ridge Regression and an approximation of the Gaussian Kernel known as Random Fourier Features are combined to predict finger forces from myoelectric signals, both finger-by-finger and grouped in grasping patterns.We show that the approach is effective and practically applicable to this problem by first analyzing its performance while predicting single-finger forces. Surface electromyography and finger forces were collected from 10 intact subjects during four sessions spread over two different days; the results of the analysis show that small incremental updates are indeed effective to maintain a stable level of performance.Subsequently, we employed the same method on-line to teleoperate a humanoid robotic arm equipped with a state-of-the-art commercial prosthetic hand. The subject could reliably grasp, carry and release everyday-life objects, enforcing stable grasping irrespective of the signal changes, hand/arm movements and wrist pronation and supination.
Stable myoelectric control of a hand prosthesis using non-linear incremental learning
Gijsberts, Arjan; Bohra, Rashida; Sierra González, David; Werner, Alexander; Nowak, Markus; Caputo, Barbara; Roa, Maximo A.; Castellini, Claudio
2014-01-01
Stable myoelectric control of hand prostheses remains an open problem. The only successful human–machine interface is surface electromyography, typically allowing control of a few degrees of freedom. Machine learning techniques may have the potential to remove these limitations, but their performance is thus far inadequate: myoelectric signals change over time under the influence of various factors, deteriorating control performance. It is therefore necessary, in the standard approach, to regularly retrain a new model from scratch. We hereby propose a non-linear incremental learning method in which occasional updates with a modest amount of novel training data allow continual adaptation to the changes in the signals. In particular, Incremental Ridge Regression and an approximation of the Gaussian Kernel known as Random Fourier Features are combined to predict finger forces from myoelectric signals, both finger-by-finger and grouped in grasping patterns. We show that the approach is effective and practically applicable to this problem by first analyzing its performance while predicting single-finger forces. Surface electromyography and finger forces were collected from 10 intact subjects during four sessions spread over two different days; the results of the analysis show that small incremental updates are indeed effective to maintain a stable level of performance. Subsequently, we employed the same method on-line to teleoperate a humanoid robotic arm equipped with a state-of-the-art commercial prosthetic hand. The subject could reliably grasp, carry and release everyday-life objects, enforcing stable grasping irrespective of the signal changes, hand/arm movements and wrist pronation and supination. PMID:24616697
Stable myoelectric control of a hand prosthesis using non-linear incremental learning.
Gijsberts, Arjan; Bohra, Rashida; Sierra González, David; Werner, Alexander; Nowak, Markus; Caputo, Barbara; Roa, Maximo A; Castellini, Claudio
2014-01-01
Stable myoelectric control of hand prostheses remains an open problem. The only successful human-machine interface is surface electromyography, typically allowing control of a few degrees of freedom. Machine learning techniques may have the potential to remove these limitations, but their performance is thus far inadequate: myoelectric signals change over time under the influence of various factors, deteriorating control performance. It is therefore necessary, in the standard approach, to regularly retrain a new model from scratch. We hereby propose a non-linear incremental learning method in which occasional updates with a modest amount of novel training data allow continual adaptation to the changes in the signals. In particular, Incremental Ridge Regression and an approximation of the Gaussian Kernel known as Random Fourier Features are combined to predict finger forces from myoelectric signals, both finger-by-finger and grouped in grasping patterns. We show that the approach is effective and practically applicable to this problem by first analyzing its performance while predicting single-finger forces. Surface electromyography and finger forces were collected from 10 intact subjects during four sessions spread over two different days; the results of the analysis show that small incremental updates are indeed effective to maintain a stable level of performance. Subsequently, we employed the same method on-line to teleoperate a humanoid robotic arm equipped with a state-of-the-art commercial prosthetic hand. The subject could reliably grasp, carry and release everyday-life objects, enforcing stable grasping irrespective of the signal changes, hand/arm movements and wrist pronation and supination.
Learning theory of distributed spectral algorithms
Guo, Zheng-Chu; Lin, Shao-Bo; Zhou, Ding-Xuan
2017-07-01
Spectral algorithms have been widely used and studied in learning theory and inverse problems. This paper is concerned with distributed spectral algorithms, for handling big data, based on a divide-and-conquer approach. We present a learning theory for these distributed kernel-based learning algorithms in a regression framework including nice error bounds and optimal minimax learning rates achieved by means of a novel integral operator approach and a second order decomposition of inverse operators. Our quantitative estimates are given in terms of regularity of the regression function, effective dimension of the reproducing kernel Hilbert space, and qualification of the filter function of the spectral algorithm. They do not need any eigenfunction or noise conditions and are better than the existing results even for the classical family of spectral algorithms.
An incremental procedure model for e-learning projects at universities
Directory of Open Access Journals (Sweden)
Pahlke, Friedrich
2006-11-01
Full Text Available E-learning projects at universities are produced under different conditions than in industry. The main characteristic of many university projects is that these are realized quasi in a solo effort. In contrast, in private industry the different, interdisciplinary skills that are necessary for the development of e-learning are typically supplied by a multimedia agency.A specific procedure tailored for the use at universities is therefore required to facilitate mastering the amount and complexity of the tasks.In this paper an incremental procedure model is presented, which describes the proceeding in every phase of the project. It allows a high degree of flexibility and emphasizes the didactical concept – instead of the technical implementation. In the second part, we illustrate the practical use of the theoretical procedure model based on the project “Online training in Genetic Epidemiology”.
Ensemble Learning for Free with Evolutionary Algorithms ?
Gagné, Christian; Schoenauer, Marc; Tomassini, Marco
2007-01-01
Evolutionary Learning proceeds by evolving a population of classifiers, from which it generally returns (with some notable exceptions) the single best-of-run classifier as final result. In the meanwhile, Ensemble Learning, one of the most efficient approaches in supervised Machine Learning for the last decade, proceeds by building a population of diverse classifiers. Ensemble Learning with Evolutionary Computation thus receives increasing attention. The Evolutionary Ensemble Learning (EEL) approach presented in this paper features two contributions. First, a new fitness function, inspired by co-evolution and enforcing the classifier diversity, is presented. Further, a new selection criterion based on the classification margin is proposed. This criterion is used to extract the classifier ensemble from the final population only (Off-line) or incrementally along evolution (On-line). Experiments on a set of benchmark problems show that Off-line outperforms single-hypothesis evolutionary learning and state-of-art ...
Kernel learning algorithms for face recognition
Li, Jun-Bao; Pan, Jeng-Shyang
2013-01-01
Kernel Learning Algorithms for Face Recognition covers the framework of kernel based face recognition. This book discusses the advanced kernel learning algorithms and its application on face recognition. This book also focuses on the theoretical deviation, the system framework and experiments involving kernel based face recognition. Included within are algorithms of kernel based face recognition, and also the feasibility of the kernel based face recognition method. This book provides researchers in pattern recognition and machine learning area with advanced face recognition methods and its new
TV-constrained incremental algorithms for low-intensity CT image reconstruction
DEFF Research Database (Denmark)
Rose, Sean D.; Andersen, Martin S.; Sidky, Emil Y.
2015-01-01
constraint can be guided by an image reconstructed by filtered backprojection (FBP). We apply our algorithm to low-dose synchrotron X-ray CT data from the Advanced Photon Source (APS) at Argonne National Labs (ANL) to demonstrate its potential utility. We find that the algorithm provides a means of edge......-preserving regularization with the potential to generate useful images at low iteration number in low-dose CT....
A new decision tree learning algorithm
Institute of Scientific and Technical Information of China (English)
FANG Yong; QI Fei-hu
2005-01-01
In order to improve the generalization ability of binary decision trees, a new learning algorithm, the MMDT algorithm, is presented. Based on statistical learning theory the generalization performance of binary decision trees is analyzed, and the assessment rule is proposed. Under the direction of the assessment rule, the MMDT algorithm is implemented. The algorithm maps training examples from an original space to a high dimension featurespace, and constructs a decision tree in it. In the feature space, a new decision node splitting criterion, the max-min rule, is used, and the margin of each decision node is maximized using a support vector machine, to improve the generalization performance. Experimental results show that the new learning algorithm is much superior to others such as C4. 5 and OC1.
Lane Detection Based on Machine Learning Algorithm
National Research Council Canada - National Science Library
Chao Fan; Jingbo Xu; Shuai Di
2013-01-01
In order to improve accuracy and robustness of the lane detection in complex conditions, such as the shadows and illumination changing, a novel detection algorithm was proposed based on machine learning...
Visualizing output for a data learning algorithm
Carson, Daniel; Graham, James; Ternovskiy, Igor
2016-05-01
This paper details the process we went through to visualize the output for our data learning algorithm. We have been developing a hierarchical self-structuring learning algorithm based around the general principles of the LaRue model. One example of a proposed application of this algorithm would be traffic analysis, chosen because it is conceptually easy to follow and there is a significant amount of already existing data and related research material with which to work with. While we choose the tracking of vehicles for our initial approach, it is by no means the only target of our algorithm. Flexibility is the end goal, however, we still need somewhere to start. To that end, this paper details our creation of the visualization GUI for our algorithm, the features we included and the initial results we obtained from our algorithm running a few of the traffic based scenarios we designed.
Schmidhuber, J.; Zhao, J.; Wiering, M.A.
1997-01-01
We study task sequences that allow for speeding up the learners average reward intake through appropriate shifts of inductive bias changes of the learner's policy. To evaluate long-term effects of bias shifts setting the stage for later bias shifts we use the "success-story algorithm" (SSA).SSA is
Top Tagging by Deep Learning Algorithm
Akil, Ali
2015-01-01
In this report I will show the application of a deep learning algorithm on a Monte Carlo simulation sample to test its performance in tagging hadronic decays of boosted top quarks and compare what we get with the results of the application of some other algorithms.
Parallelization of TMVA Machine Learning Algorithms
Hajili, Mammad
2017-01-01
This report reflects my work on Parallelization of TMVA Machine Learning Algorithms integrated to ROOT Data Analysis Framework during summer internship at CERN. The report consists of 4 impor- tant part - data set used in training and validation, algorithms that multiprocessing applied on them, parallelization techniques and re- sults of execution time changes due to number of workers.
LEARNING ALGORITHM OF STAGE CONTROL NBP NETWORK
Institute of Scientific and Technical Information of China (English)
Yan Lixiang; Qin Zheng
2003-01-01
This letter analyzes the reasons why the known Neural Back Promulgation (NBP)network learning algorithm has slower speed and greater sample error. Based on the analysis and experiment, the training group descending Enhanced Combination Algorithm (ECA) is proposed.The analysis of the generalized property and sample error shows that the ECA can heighten the study speed and reduce individual error.
Automating parallel implementation of neural learning algorithms.
Rana, O F
2000-06-01
Neural learning algorithms generally involve a number of identical processing units, which are fully or partially connected, and involve an update function, such as a ramp, a sigmoid or a Gaussian function for instance. Some variations also exist, where units can be heterogeneous, or where an alternative update technique is employed, such as a pulse stream generator. Associated with connections are numerical values that must be adjusted using a learning rule, and and dictated by parameters that are learning rule specific, such as momentum, a learning rate, a temperature, amongst others. Usually, neural learning algorithms involve local updates, and a global interaction between units is often discouraged, except in instances where units are fully connected, or involve synchronous updates. In all of these instances, concurrency within a neural algorithm cannot be fully exploited without a suitable implementation strategy. A design scheme is described for translating a neural learning algorithm from inception to implementation on a parallel machine using PVM or MPI libraries, or onto programmable logic such as FPGAs. A designer must first describe the algorithm using a specialised Neural Language, from which a Petri net (PN) model is constructed automatically for verification, and building a performance model. The PN model can be used to study issues such as synchronisation points, resource sharing and concurrency within a learning rule. Specialised constructs are provided to enable a designer to express various aspects of a learning rule, such as the number and connectivity of neural nodes, the interconnection strategies, and information flows required by the learning algorithm. A scheduling and mapping strategy is then used to translate this PN model onto a multiprocessor template. We demonstrate our technique using a Kohonen and backpropagation learning rules, implemented on a loosely coupled workstation cluster, and a dedicated parallel machine, with PVM libraries.
2014-01-01
The two basic topologies of switch mode DC-DC converters (Buck and Boost) are analyzed with a view of their use in PV (photovoltaic) systems, as the photovoltaic generator exhibits non-linear characteristics due to the change in environmental condition and load variation. As the efficiency of PV panels is low it becomes mandatory to extract maximum power from the PV panel at a given period of time. Several MPPT algorithms with different types of converters are being proposed f...
Algorithmic learning in a random world
Vovk, Vladimir; Shafer, Glenn
2005-01-01
A new scientific monograph developing significant new algorithmic foundations in machine learning theory. Researchers and postgraduates in CS, statistics, and A.I. will find the book an authoritative and formal presentation of some of the most promising theoretical developments in machine learning.
EEG Eye State Identification Using Incremental Attribute Learning with Time-Series Classification
Directory of Open Access Journals (Sweden)
Ting Wang
2014-01-01
Full Text Available Eye state identification is a kind of common time-series classification problem which is also a hot spot in recent research. Electroencephalography (EEG is widely used in eye state classification to detect human's cognition state. Previous research has validated the feasibility of machine learning and statistical approaches for EEG eye state classification. This paper aims to propose a novel approach for EEG eye state identification using incremental attribute learning (IAL based on neural networks. IAL is a novel machine learning strategy which gradually imports and trains features one by one. Previous studies have verified that such an approach is applicable for solving a number of pattern recognition problems. However, in these previous works, little research on IAL focused on its application to time-series problems. Therefore, it is still unknown whether IAL can be employed to cope with time-series problems like EEG eye state classification. Experimental results in this study demonstrates that, with proper feature extraction and feature ordering, IAL can not only efficiently cope with time-series classification problems, but also exhibit better classification performance in terms of classification error rates in comparison with conventional and some other approaches.
Learning Algorithms of Multilayer Neural Networks
Fujiki, Sumiyoshi; FUJIKI, Nahomi, M.
1996-01-01
A positive reinforcement type learning algorithm is formulated for a stochastic feed-forward multilayer neural network, with far interlayer synaptic connections, and we obtain a learning rule similar to that of the Boltzmann machine on the same multilayer structure. By applying a mean field approximation to the stochastic feed-forward neural network, the generalized error back-propagation learning rule is derived for a deterministic analog feed-forward multilayer network with the far interlay...
Stochastic Descent Analysis of Representation Learning Algorithms
Golden, Richard M.
2014-01-01
Although stochastic approximation learning methods have been widely used in the machine learning literature for over 50 years, formal theoretical analyses of specific machine learning algorithms are less common because stochastic approximation theorems typically possess assumptions which are difficult to communicate and verify. This paper presents a new stochastic approximation theorem for state-dependent noise with easily verifiable assumptions applicable to the analysis and design of import...
A Learning Algorithm for Multimodal Grammar Inference.
D'Ulizia, A; Ferri, F; Grifoni, P
2011-12-01
The high costs of development and maintenance of multimodal grammars in integrating and understanding input in multimodal interfaces lead to the investigation of novel algorithmic solutions in automating grammar generation and in updating processes. Many algorithms for context-free grammar inference have been developed in the natural language processing literature. An extension of these algorithms toward the inference of multimodal grammars is necessary for multimodal input processing. In this paper, we propose a novel grammar inference mechanism that allows us to learn a multimodal grammar from its positive samples of multimodal sentences. The algorithm first generates the multimodal grammar that is able to parse the positive samples of sentences and, afterward, makes use of two learning operators and the minimum description length metrics in improving the grammar description and in avoiding the over-generalization problem. The experimental results highlight the acceptable performances of the algorithm proposed in this paper since it has a very high probability of parsing valid sentences.
Orthogonal least squares learning algorithm for radial basis function networks
Energy Technology Data Exchange (ETDEWEB)
Chen, S.; Cowan, C.F.N.; Grant, P.M. (Dept. of Electrical Engineering, Univ. of Edinburgh, Mayfield Road, Edinburgh EH9 3JL, Scotland (GB))
1991-03-01
The radial basis function network offers a viable alternative to the two-layer neural network in many applications of signal processing. A common learning algorithm for radial basis function networks is based on first choosing randomly some data points as radial basis function centers and then using singular value decomposition to solve for the weights of the network. Such a procedure has several drawbacks and, in particular, an arbitrary selection of centers is clearly unsatisfactory. The paper proposes an alternative learning procedure based on the orthogonal least squares method. The procedure choose radial basis function centers one by one in a rational way until an adequate network has been constructed. The algorithm has the property that each selected center maximizes the increment to the explained variance or energy of the desired output and does not suffer numerical ill-conditioning problems. The orthogonal least squares learning strategy provides a simple and efficient means for fitting radial basis function networks, and this is illustrated using examples taken from two different signal processing applications.
Orthogonal least squares learning algorithm for radial basis function networks.
Chen, S; Cowan, C N; Grant, P M
1991-01-01
The radial basis function network offers a viable alternative to the two-layer neural network in many applications of signal processing. A common learning algorithm for radial basis function networks is based on first choosing randomly some data points as radial basis function centers and then using singular-value decomposition to solve for the weights of the network. Such a procedure has several drawbacks, and, in particular, an arbitrary selection of centers is clearly unsatisfactory. The authors propose an alternative learning procedure based on the orthogonal least-squares method. The procedure chooses radial basis function centers one by one in a rational way until an adequate network has been constructed. In the algorithm, each selected center maximizes the increment to the explained variance or energy of the desired output and does not suffer numerical ill-conditioning problems. The orthogonal least-squares learning strategy provides a simple and efficient means for fitting radial basis function networks. This is illustrated using examples taken from two different signal processing applications.
PADDLE: Proximal Algorithm for Dual Dictionaries LEarning
Basso, Curzio; Verri, Alessandro; Villa, Silvia
2010-01-01
Recently, considerable research efforts have been devoted to the design of methods to learn from data overcomplete dictionaries for sparse coding. However, learned dictionaries require the solution of an optimization problem for coding new data. In order to overcome this drawback, we propose an algorithm aimed at learning both a dictionary and its dual: a linear mapping directly performing the coding. By leveraging on proximal methods, our algorithm jointly minimizes the reconstruction error of the dictionary and the coding error of its dual; the sparsity of the representation is induced by an $\\ell_1$-based penalty on its coefficients. The results obtained on synthetic data and real images show that the algorithm is capable of recovering the expected dictionaries. Furthermore, on a benchmark dataset, we show that the image features obtained from the dual matrix yield state-of-the-art classification performance while being much less computational intensive.
Paradigms for Realizing Machine Learning Algorithms.
Agneeswaran, Vijay Srinivas; Tonpay, Pranay; Tiwary, Jayati
2013-12-01
The article explains the three generations of machine learning algorithms-with all three trying to operate on big data. The first generation tools are SAS, SPSS, etc., while second generation realizations include Mahout and RapidMiner (that work over Hadoop), and the third generation paradigms include Spark and GraphLab, among others. The essence of the article is that for a number of machine learning algorithms, it is important to look beyond the Hadoop's Map-Reduce paradigm in order to make them work on big data. A number of promising contenders have emerged in the third generation that can be exploited to realize deep analytics on big data.
Incremental Tensor Principal Component Analysis for Handwritten Digit Recognition
Directory of Open Access Journals (Sweden)
Chang Liu
2014-01-01
Full Text Available To overcome the shortcomings of traditional dimensionality reduction algorithms, incremental tensor principal component analysis (ITPCA based on updated-SVD technique algorithm is proposed in this paper. This paper proves the relationship between PCA, 2DPCA, MPCA, and the graph embedding framework theoretically and derives the incremental learning procedure to add single sample and multiple samples in detail. The experiments on handwritten digit recognition have demonstrated that ITPCA has achieved better recognition performance than that of vector-based principal component analysis (PCA, incremental principal component analysis (IPCA, and multilinear principal component analysis (MPCA algorithms. At the same time, ITPCA also has lower time and space complexity.
An efficient incremental learning mechanism for tracking concept drift in spam filtering
Sheu, Jyh-Jian; Chu, Ko-Tsung; Li, Nien-Feng; Lee, Cheng-Chi
2017-01-01
This research manages in-depth analysis on the knowledge about spams and expects to propose an efficient spam filtering method with the ability of adapting to the dynamic environment. We focus on the analysis of email’s header and apply decision tree data mining technique to look for the association rules about spams. Then, we propose an efficient systematic filtering method based on these association rules. Our systematic method has the following major advantages: (1) Checking only the header sections of emails, which is different from those spam filtering methods at present that have to analyze fully the email’s content. Meanwhile, the email filtering accuracy is expected to be enhanced. (2) Regarding the solution to the problem of concept drift, we propose a window-based technique to estimate for the condition of concept drift for each unknown email, which will help our filtering method in recognizing the occurrence of spam. (3) We propose an incremental learning mechanism for our filtering method to strengthen the ability of adapting to the dynamic environment. PMID:28182691
Incremental Beliefs of Ability, Achievement Emotions and Learning of Singapore Students
Luo, Wenshu; Lee, Kerry; Ng, Pak Tee; Ong, Joanne Xiao Wei
2014-01-01
This study investigated the relationships of students' incremental beliefs of math ability to their achievement emotions, classroom engagement and math achievement. A sample of 273 secondary students in Singapore were administered measures of incremental beliefs of math ability, math enjoyment, pride, boredom and anxiety, as well as math classroom…
Aldawish, Abeer
2017-01-01
Incremental Rehearsal (IR) is an effective, evidence-based intervention for teaching words that uses high repetition and a high ratio of unknown and known items. The purpose of the present research study was to evaluate the effectiveness of using Incremental Rehearsal to improve the fluency in reading sight words for three elementary students…
Incremental Beliefs of Ability, Achievement Emotions and Learning of Singapore Students
Luo, Wenshu; Lee, Kerry; Ng, Pak Tee; Ong, Joanne Xiao Wei
2014-01-01
This study investigated the relationships of students' incremental beliefs of math ability to their achievement emotions, classroom engagement and math achievement. A sample of 273 secondary students in Singapore were administered measures of incremental beliefs of math ability, math enjoyment, pride, boredom and anxiety, as well as math…
Implementing Kernel Methods Incrementally by Incremental Nonlinear Projection Trick.
Kwak, Nojun
2016-05-20
Recently, the nonlinear projection trick (NPT) was introduced enabling direct computation of coordinates of samples in a reproducing kernel Hilbert space. With NPT, any machine learning algorithm can be extended to a kernel version without relying on the so called kernel trick. However, NPT is inherently difficult to be implemented incrementally because an ever increasing kernel matrix should be treated as additional training samples are introduced. In this paper, an incremental version of the NPT (INPT) is proposed based on the observation that the centerization step in NPT is unnecessary. Because the proposed INPT does not change the coordinates of the old data, the coordinates obtained by INPT can directly be used in any incremental methods to implement a kernel version of the incremental methods. The effectiveness of the INPT is shown by applying it to implement incremental versions of kernel methods such as, kernel singular value decomposition, kernel principal component analysis, and kernel discriminant analysis which are utilized for problems of kernel matrix reconstruction, letter classification, and face image retrieval, respectively.
Institute of Scientific and Technical Information of China (English)
顾晔; 吕红兵
2011-01-01
As a kind of programs and algorithms, recommendation systems provide personalized recommendations by measuring the preference levels of users (customers) on the given commodities.More broadly, recommender systems attempt to profile user preferences and model the interaction between users and products. Compared with other singular value decomposition methods,the improved incremental singular value decompositon allows the singular value decomposition of a user-item rating matrix to be learned based on single observation presented serially, and produces singular vector pairs one at a time, each time forms the most significant one at present. The algorithm has minimal memory requirements,high scalabillty and is particularly suitable for handling large data sets. The technique is demonstrated on the Netflix dataset.%推荐系统作为一种程序算法,是通过度量用户对给定商品的的喜好程度做个性化推荐.广泛地说,推荐系统试图总结出用户的个人喜好,并在用户和商品之间建立一种关系模型.与其他奇异值分解方法相比,改进的增量奇异值分解协同过滤算法基于一系列评分值对用户.商品矩阵进行分解,每次产生一对当前最重要的特征向量.算法有着最小的内存需求,扩展性高,特别适合处理大规模数据集;算法的有效性在Netflix数据集上得到了验证.
Multi-Agent Reinforcement Learning Algorithm Based on Action Prediction
Institute of Scientific and Technical Information of China (English)
TONG Liang; LU Ji-lian
2006-01-01
Multi-agent reinforcement learning algorithms are studied. A prediction-based multi-agent reinforcement learning algorithm is presented for multi-robot cooperation task. The multi-robot cooperation experiment based on multi-agent inverted pendulum is made to test the efficency of the new algorithm, and the experiment results show that the new algorithm can achieve the cooperation strategy much faster than the primitive multiagent reinforcement learning algorithm.
An Experimental Method for the Active Learning of Greedy Algorithms
Velazquez-Iturbide, J. Angel
2013-01-01
Greedy algorithms constitute an apparently simple algorithm design technique, but its learning goals are not simple to achieve.We present a didacticmethod aimed at promoting active learning of greedy algorithms. The method is focused on the concept of selection function, and is based on explicit learning goals. It mainly consists of an…
An Experimental Method for the Active Learning of Greedy Algorithms
Velazquez-Iturbide, J. Angel
2013-01-01
Greedy algorithms constitute an apparently simple algorithm design technique, but its learning goals are not simple to achieve.We present a didacticmethod aimed at promoting active learning of greedy algorithms. The method is focused on the concept of selection function, and is based on explicit learning goals. It mainly consists of an…
Clark, Richard M.; Adjei, Osei; Johal, Harpal
2001-11-01
This paper proposes a fast, effective and also very adaptable incremental learning system for identifying textures based on features extracted from Gabor space. The Gabor transform is a useful technique for feature extraction since it exhibits properties that are similar to biologically visual sensory systems such as those found in the mammalian visual cortex. Although two-dimensional Gabor filters have been applied successfully to a variety of tasks such as text segmentation, object detection and fingerprint analysis, the work of this paper extends previous work by incorporating incremental learning to facilitate easier training. The proposed system transforms textural images into Gabor space and a non-linear threshold function is then applied to extract feature vectors that bear signatures of the textural images. The mean and variance of each training group is computed followed by a technique that uses the Kohonen network to cluster these features. The centers of these clusters form the basis of an incremental learning paradigm that allows new information to be integrated into the existing knowledge. A number of experiments are conducted for real-time identification or discrimination of textural images.
Directory of Open Access Journals (Sweden)
Jian Luo
2016-01-01
Full Text Available A cloud based health care system is proposed in this paper for the elderly by providing abnormal gait behavior detection, classification, online diagnosis, and remote aid service. Intelligent mobile terminals with triaxial acceleration sensor embedded are used to capture the movement and ambulation information of elderly. The collected signals are first enhanced by a Kalman filter. And the magnitude of signal vector features is then extracted and decomposed into a linear combination of enhanced Gabor atoms. The Wigner-Ville analysis method is introduced and the problem is studied by joint time-frequency analysis. In order to solve the large-scale abnormal behavior data lacking problem in training process, a cloud based incremental SVM (CI-SVM learning method is proposed. The original abnormal behavior data are first used to get the initial SVM classifier. And the larger abnormal behavior data of elderly collected by mobile devices are then gathered in cloud platform to conduct incremental training and get the new SVM classifier. By the CI-SVM learning method, the knowledge of SVM classifier could be accumulated due to the dynamic incremental learning. Experimental results demonstrate that the proposed method is feasible and can be applied to aged care, emergency aid, and related fields.
A Decomposition Algorithm for Learning Bayesian Network Structures from Data
DEFF Research Database (Denmark)
Zeng, Yifeng; Cordero Hernandez, Jorge
2008-01-01
It is a challenging task of learning a large Bayesian network from a small data set. Most conventional structural learning approaches run into the computational as well as the statistical problems. We propose a decomposition algorithm for the structure construction without having to learn...... the complete network. The new learning algorithm firstly finds local components from the data, and then recover the complete network by joining the learned components. We show the empirical performance of the decomposition algorithm in several benchmark networks....
Rho-learning: a robotics oriented reinforcement learning algorithm
Porta Pleite, Josep Maria
2000-01-01
We present a new reinforcement learning system more suitable to be used in robotics than existing ones. Existing reinforcement learning algorithms are not specifically tailored for robotics and so they do not take advantage of the robotic perception characteristics as well as of the expected complexity of the task that robots are likely to face. In a robot, the information about the environment comes from a set of qualitatively different sensors and in the main par of tasks small subsets of t...
Image Recovery Algorithm Based on Learned Dictionary
Directory of Open Access Journals (Sweden)
Xinghui Zhu
2014-01-01
Full Text Available We proposed a recovery scheme for image deblurring. The scheme is under the framework of sparse representation and it has three main contributions. Firstly, considering the sparse property of natural image, the nonlocal overcompleted dictionaries are learned for image patches in our scheme. And, then, we coded the patches in each nonlocal clustering with the corresponding learned dictionary to recover the whole latent image. In addition, for some practical applications, we also proposed a method to evaluate the blur kernel to make the algorithm usable in blind image recovery. The experimental results demonstrated that the proposed scheme is competitive with some current state-of-the-art methods.
Directory of Open Access Journals (Sweden)
Lázaro Janier González-Soler
2015-12-01
Full Text Available Spanish abstract Existen diversos problemas en el Reconocimiento de Patrones y en la Minería de Datos que, por su naturaleza, consideran que los objetos pueden pertenecer a más de una clase o grupo. DClustR es un algoritmo dinámico de agrupamiento con traslape que ha mostrado, en tareas de agrupamiento de documentos, el mejor balance entre calidad de los grupos y eficiencia entre los algoritmos dinámicos de agrupamiento con traslape reportados en la literatura. A pesar de obtener buenos resultados, DClustR puede ser poco útil en aplicaciones que trabajen con grandes colecciones de documentos, debido a que tiene una complejidad computacional y a la cantidad de memoria que utiliza para el procesamiento de las colecciones. En este trabajo se presenta una versión paralela basada en GPU del algoritmo DClustR, llamada CUDA-DClus, para mejorar la eficiencia de DClustR en aplicaciones que lidien con largas colecciones de documentos. Los experimentos fueron realizados sobre varias colecciones estándares de documentos y en ellos se muestra el buen rendimiento de CUDA-DClus en términos de eficiencia y consumo de memoria. English abstract There are several problems in Pattern Recognition and Data Mining that, by its inherent nature, consider that the objects can belong to more than a class or cluster. DClustR is a dynamic overlapping clustering algorithm that has shown, in document clustering tasks, the best trade-off between cluster’s quality and efficiency among existing dynamic overlapping clustering algorithms. However, DClustR could be less useful when working in applications that deal with large data collections, due to its computational complexity and memory demanded for processing them. In this paper, a GPU-based parallel algorithm of DClustR, named CUDA-DClus is suggested to enhance DClustR efficiency in applications dealing with large data collections. The experimental phase conducted over various standard data collections showed that
Lane Detection Based on Machine Learning Algorithm
Directory of Open Access Journals (Sweden)
Chao Fan
2013-09-01
Full Text Available In order to improve accuracy and robustness of the lane detection in complex conditions, such as the shadows and illumination changing, a novel detection algorithm was proposed based on machine learning. After pretreatment, a set of haar-like filters were used to calculate the eigenvalue in the gray image f(x,y and edge e(x,y. Then these features were trained by using improved boosting algorithm and the final class function g(x was obtained, which was used to judge whether the point x belonging to the lane or not. To avoid the over fitting in traditional boosting, Fisher discriminant analysis was used to initialize the weights of samples. After testing by many road in all conditions, it showed that this algorithm had good robustness and real-time to recognize the lane in all challenging conditions.
Ozone ensemble forecast with machine learning algorithms
Mallet, Vivien; Stoltz, Gilles; Mauricette, Boris
2009-01-01
International audience; We apply machine learning algorithms to perform sequential aggregation of ozone forecasts. The latter rely on a multimodel ensemble built for ozone forecasting with the modeling system Polyphemus. The ensemble simulations are obtained by changes in the physical parameterizations, the numerical schemes, and the input data to the models. The simulations are carried out for summer 2001 over western Europe in order to forecast ozone daily peaks and ozone hourly concentrati...
Learning algorithms for perceptrons from statistical physics
Gordon, Mirta B.; Peretto, Pierre; Berchier, Dominique
1993-02-01
Learning algorithms for perceptrons are deduced from statistical mechanics. Thermodynamical quantities are used as cost functions which may be extremalized by gradient dynamics to find the synaptic efficacies that store the learning set of patterns. The learning rules so obtained are classified in two categories, following the statistics used to derive the cost functions, namely, Boltzmann statistics, and Fermi statistics. In the limits of zero or infinite temperatures some of the rules behave like already known algorithms, but new strategies for learning are obtained at finite temperatures, which minimize the number of errors on the training set. Nous déduisons des algorithmes d'apprentissage pour des perceptrons à partir de considérations de mécanique statistique. Des quantités thermodynamiques sont considérées comme des fonctions de coût, dont on obtient, par une dynamique de gradient, les efficacités synaptiques qui apprennent l'ensemble d'apprentissage. Les règles ainsi obtenues sont classées en deux catégories suivant les statistiques, de Boltzmann ou de Fermi, utilisées pour dériver les fonctions de coût. Dans les limites de températures nulle ou infinie, la plupart des règles trouvées tendent vers les algorithmes connus, mais à température finie on trouve des stratégies nouvelles, qui minimisent le nombre d'erreurs dans l'ensemble d'apprentissage.
A Probability-based Evolutionary Algorithm with Mutations to Learn Bayesian Networks
Directory of Open Access Journals (Sweden)
Sho Fukuda
2014-12-01
Full Text Available Bayesian networks are regarded as one of the essential tools to analyze causal relationship between events from data. To learn the structure of highly-reliable Bayesian networks from data as quickly as possible is one of the important problems that several studies have been tried to achieve. In recent years, probability-based evolutionary algorithms have been proposed as a new efficient approach to learn Bayesian networks. In this paper, we target on one of the probability-based evolutionary algorithms called PBIL (Probability-Based Incremental Learning, and propose a new mutation operator. Through performance evaluation, we found that the proposed mutation operator has a good performance in learning Bayesian networks
Incremental and evolutionary manifold learning: a survey%增量与演化流形学习综述
Institute of Scientific and Technical Information of China (English)
谈超; 关佶红; 周水庚
2012-01-01
Manifold learning is to find the low-dimensional smooth manifold of observation data embedded in high-dimensional data space. In recent years, exploring the intrinsic low-dimensional manifold structure online or incrementally becomes a hot research topic in manifold learning area. This paper surveys the state of the art of incremental and evolutionary manifold learning, including the mechanisms and features of major existing incremental and evolutionary manifold learning methods, their advantages and disadvantages, and highlights the open research issues and future research directions.%流形学习的目标是发现观测数据嵌入在高维数据空间中的低维光滑流形.近年来,在线或增量地发现内在低维流形结构成为流形学习的研究热点.从增量学习和演化学习2个方面入手,对该领域已有研究进展进行综述.增量流形学习较之传统的批量流形学习方法具有动态增量的能力,而演化流形学习能够在线地发现海量动态数据的内在规律,有利于进行维数约简和数据分析.文中对主要的增量与演化流形学习算法的基本原理、特点进行了阐述,分析了各自的优点与不足,指出了该领域的开放问题,并对进一步的研究方向进行了展望.
A new learning algorithm with reference-following variables
Institute of Scientific and Technical Information of China (English)
Baiquan L(u); Yuan CAO
2004-01-01
A learning algorithm is presented for the learning of neural networks,in which the learning trajectory is convergence without any over-learning by changing of topological construction of the algorithm near any local minimum points of learning error.Because the topological construction is not convergent for some functions by usual BP method near some local minimum points,there is an over-learning phenomenon.To avoid the over-learning phenomenon, reference-following variables are used to change the topological construction of this algorithm.The theoretical analysis and the simulation results indicate that the proposed method is simple and useful.
Directory of Open Access Journals (Sweden)
SUN Wenbin
2016-11-01
Full Text Available In order to improve the accuracy of low frequency (sampling interval greater than 1 minute trajectory data matching algorithm, this paper proposed a novel matching algorithm termed HMDP-Q (History Markov Decision Processes Q-learning. The new algorithm is based on reinforced learning on historic trajectory. First, we extract historic trajectory data according to incremental matching algorithm as historical reference, and filter the trajectory dataset through the historic reference, the shortest trajectory and the reachability. Then we model the map matching process as the Markov decision process, and build up reward function using deflected distance between trajectory points and historic trajectories. The largest reward value of the Markov decision process was calculated by using the reinforced learning algorithm, which is the optimal matching result of trajectory and road. Finally we calibrate the algorithm by utilizing city's floating cars data to experiment. The results show that this algorithm can improve the accuracy between trajectory data and road. The matching accuracy is 89.2% within 1 minute low-frequency sampling interval, and the matching accuracy is 61.4% when the sampling frequency is 16 minutes. Compared with IVVM (Interactive Voting-based Map Matching, HMDP-Q has a higher matching accuracy and computing efficiency. Especially, when the sampling frequency is 16 minutes, HMDP-Q improves the matching accuracy by 26%.
Bayesian online algorithms for learning in discrete Hidden Markov Models
Alamino, Roberto C.; Caticha, Nestor
2008-01-01
We propose and analyze two different Bayesian online algorithms for learning in discrete Hidden Markov Models and compare their performance with the already known Baldi-Chauvin Algorithm. Using the Kullback-Leibler divergence as a measure of generalization we draw learning curves in simplified situations for these algorithms and compare their performances.
支持在线学习的增量式极端随机森林分类器%Incremental Learning Extremely Random Forest Classifier for Online Learning
Institute of Scientific and Technical Information of China (English)
王爱平; 万国伟; 程志全; 李思昆
2011-01-01
This paper proposes an incremental extremely random forest (IERF) algorithm, dealing with online learning classification with streaming data, especially with small streaming data. In this method, newly arrived examples are stored at the leaf nodes and used to determine when to split the leaf nodes combined with Gini index, so the trees can be expanded efficiently and fast with a few examples. The proposed online IERF algorithm gives more competitive or even better performance, than the offline extremely random forest (ERF) method, based on the UCI data experiment. On the moderate training datasets, the IERF algorithm beats the decision tree reconstruction algorithm and other incremental learning algorithms on the performance. Finally, the IERF algorithm is used to solve online video object tracking (multi-object tracking also included) problems, and the results on the challenging video sequences demonstrate its effectiveness and robustness.%提出了一种增量式极端随机森林分类器(incremental extremely random forest,简称IERF),用于处理数据流,特别是小样本数据流的在线学习问题.IERF算法中新到达的样本将被存储到相应的叶节点,并通过Gini系数来确定是否对当前叶节点进行分裂扩展,在给定有限数量,甚至是少量样本的情况下,IERF算法能够快速高效地完成分类器的增量构造.UCI数据集的实验证明,提出的IERF算法具有与离线批量学习的极端随机森林(extremely random forest,简称ERF)算法相当甚至更优的性能,在适度规模的样本集上,性能优于贪婪决策树重构算法和其他几种主要的增量学习算法.最后,提出的IERF算法被应用于解决视频在线跟踪(包含多目标跟踪)问题,基于多个真实视频数据的实验充分验证了算法的有效性和稳定性.
Diard, Julien; Gilet, Estelle; Simonin, Éva; Bessière, Pierre
2010-12-01
This paper concerns the incremental learning of hierarchies of representations of space in artificial or natural cognitive systems. We propose a mathematical formalism for defining space representations (Bayesian Maps) and modelling their interaction in hierarchies of representations (sensorimotor interaction operator). We illustrate our formalism with a robotic experiment. Starting from a model based on the proximity to obstacles, we learn a new one related to the direction of the light source. It provides new behaviours, like phototaxis and photophobia. We then combine these two maps so as to identify parts of the environment where the way the two modalities interact is recognisable. This classification is a basis for learning a higher level of abstraction map that describes the large-scale structure of the environment. In the final model, the perception-action cycle is modelled by a hierarchy of sensorimotor models of increasing time and space scales, which provide navigation strategies of increasing complexities.
Machine Learning Algorithms in Web Page Classification
Directory of Open Access Journals (Sweden)
W.A.AWAD
2012-11-01
Full Text Available In this paper we use machine learning algorithms like SVM, KNN and GIS to perform a behaviorcomparison on the web pages classifications problem, from the experiment we see in the SVM with smallnumber of negative documents to build the centroids has the smallest storage requirement and the least online test computation cost. But almost all GIS with different number of nearest neighbors have an evenhigher storage requirement and on line test computation cost than KNN. This suggests that some futurework should be done to try to reduce the storage requirement and on list test cost of GIS.
Self-Learning Algorithm for Coiling Temperature Controlling
Institute of Scientific and Technical Information of China (English)
WANG Jun; WANG Guo-dong; LIU Xiang-hua; ZHANG Dian-hua
2004-01-01
In order to establish a mathematical model for strip laminar cooling, the self-learning algorithm was introduced with the level learning for obvious heat flux fluctuation and the pattern learning for small heat flux fluctuation. The short self-learning calculation steps of water cooling and air cooling, and the long self-learning formula were given with some results.
Learning Bayesian network structure with immune algorithm
Institute of Scientific and Technical Information of China (English)
Zhiqiang Cai; Shubin Si; Shudong Sun; Hongyan Dui
2015-01-01
Finding out reasonable structures from bulky data is one of the difficulties in modeling of Bayesian network (BN), which is also necessary in promoting the application of BN. This pa-per proposes an immune algorithm based method (BN-IA) for the learning of the BN structure with the idea of vaccination. Further-more, the methods on how to extract the effective vaccines from local optimal structure and root nodes are also described in details. Final y, the simulation studies are implemented with the helicopter convertor BN model and the car start BN model. The comparison results show that the proposed vaccines and the BN-IA can learn the BN structure effectively and efficiently.
Improved Bounds on Quantum Learning Algorithms
Atici, A; Atici, Alp; Servedio, Rocco A.
2004-01-01
In this article we give several new results on the complexity of algorithms that learn Boolean functions from quantum queries and quantum examples. Hunziker et al. conjectured that for any class C of Boolean functions, the number of quantum black-box queries which are required to exactly identify an unknown function from C is at most $O(\\frac{\\log |C|}{\\sqrt{{\\hat{\\gamma}}^{C}}})$, where $\\hat{\\gamma}^{C}$ is a combinatorial parameter of the class C. We essentially resolve this conjecture in the affirmative by giving a quantum algorithm that, for any class C, identifies any unknown function from C using at most $O(\\frac{\\log |C| \\log \\log |C|}{\\sqrt{{\\hat{\\gamma}}^{C}}})$ quantum black-box queries. We consider a range of natural problems intermediate between the exact learning problem (in which the learner must obtain all bits of information about the black-box function) and the usual problem of computing a predicate (in which the learner must obtain only one bit of information about the black-box function). ...
Optimization of Evolutionary Neural Networks Using Hybrid Learning Algorithms
Abraham, Ajith
2004-01-01
Evolutionary artificial neural networks (EANNs) refer to a special class of artificial neural networks (ANNs) in which evolution is another fundamental form of adaptation in addition to learning. Evolutionary algorithms are used to adapt the connection weights, network architecture and learning algorithms according to the problem environment. Even though evolutionary algorithms are well known as efficient global search algorithms, very often they miss the best local solutions in the complex s...
Research of incremental extraction based on MD5 and HASH algorithm%融入MD5的HASH线性获取增量算法研究
Institute of Scientific and Technical Information of China (English)
郭亮; 杨金民
2014-01-01
To achieve rapid incremental extraction of database, an algorithm which is blended MD5 in HASH linear scan-ning to obtain increment is put forward based on analyzing the traditional incremental extraction. Each record in database can be seen as a character string and it can be generated into hash table as duplicate record, which is explored in hash table through traditional record to obtain increment and decrease frequency of comparison. Meanwhile, the fingerprint of each record can be generated with using MD5 algorithm, which reduces the length of character string in every HASH algorithm and comparison and improves efficiency. This algorithm is applicably tested in ORACLE database and the result shows that it is improved on calculative efficiency at a large extent compared with traditional algorithm.%为了实现数据库中的快速增量提取，在剖析传统的增量提取方法上，提出了一种融入MD5的HASH线性扫描来获取增量的算法。数据库中的每条记录都可视为一个字符串，利用HASH算法生成备份记录的散列表，通过原始记录去散列表中探测来达到线性扫描就能获取增量的目的，减少了比对次数；同时利用MD5算法生成每条记录的“指纹”，降低了每次HASH运算和比对的字符串长度，提高了效率。对所提出算法在ORACLE数据库上进行了应用测试，结果表明该算法效率较传统方法有很大提高。
Efficient Algorithms for Bayesian Network Parameter Learning from Incomplete Data
2015-07-01
Efficient Algorithms for Bayesian Network Parameter Learning from Incomplete Data Guy Van den Broeck∗ and Karthika Mohan∗ and Arthur Choi and Adnan...We propose a family of efficient algorithms for learning the parameters of a Bayesian network from incomplete data. Our approach is based on recent...algorithms like EM (which require inference). 1 INTRODUCTION When learning the parameters of a Bayesian network from data with missing values, the
A Competency-Based Guided-Learning Algorithm Applied on Adaptively Guiding E-Learning
Hsu, Wei-Chih; Li, Cheng-Hsiu
2015-01-01
This paper presents a new algorithm called competency-based guided-learning algorithm (CBGLA), which can be applied on adaptively guiding e-learning. Computational process analysis and mathematical derivation of competency-based learning (CBL) were used to develop the CBGLA. The proposed algorithm could generate an effective adaptively guiding…
A Hybrid Constructive Algorithm for Single-Layer Feedforward Networks Learning.
Wu, Xing; Rózycki, Paweł; Wilamowski, Bogdan M
2015-08-01
Single-layer feedforward networks (SLFNs) have been proven to be a universal approximator when all the parameters are allowed to be adjustable. It is widely used in classification and regression problems. The SLFN learning involves two tasks: determining network size and training the parameters. Most current algorithms could not be satisfactory to both sides. Some algorithms focused on construction and only tuned part of the parameters, which may not be able to achieve a compact network. Other gradient-based optimization algorithms focused on parameters tuning while the network size has to be preset by the user. Therefore, trial-and-error approach has to be used to search the optimal network size. Because results of each trial cannot be reused in another trial, it costs much computation. In this paper, a hybrid constructive (HC)algorithm is proposed for SLFN learning, which can train all the parameters and determine the network size simultaneously. At first, by combining Levenberg-Marquardt algorithm and least-square method, a hybrid algorithm is presented for training SLFN with fixed network size. Then,with the hybrid algorithm, an incremental constructive scheme is proposed. A new randomly initialized neuron is added each time when the training entrapped into local minima. Because the training continued on previous results after adding new neurons, the proposed HC algorithm works efficiently. Several practical problems were given for comparison with other popular algorithms. The experimental results demonstrated that the HC algorithm worked more efficiently than those optimization methods with trial and error, and could achieve much more compact SLFN than those construction algorithms.
Institute of Scientific and Technical Information of China (English)
余荣平; 张心光; 王岩松; 郭辉
2015-01-01
通过对轨道车辆车内含噪样本数据的分析，应用步长因子μ(n)与误差信号e(n)呈正弦函数关系的变步长LMS算法。分别对自适应滤波器中的权向量按照最速下降算法进行更新，并利用建立的自适应滤波器进行车内噪声主动控制。结果表明，提出的变步长LMS算法解决了LMS算法因固定步长不能同时兼顾算法收敛速度和稳态误差的固有缺陷，具有更快的算法收敛速度和较小的稳态误差。%By analyzing the noise signal sample inside the railway vehicle, the plain LMS algorithm and the LMS algo-rithm with variable-incremental-steps were applied respectively to update the weight vectors in the adaptive filtering based on the steepest descent algorithm. The relation between step factor μ(n) and error signal e(n) is a sinusoidal function in the variable-step LMS algorithm. The adaptive filter was used for active internal noise control for the vehicle. Result shows that the proposed variable-step LMS algorithm can overcome the inherent contradiction in the plain LMS algorithm between al-gorithm convergence speed and steady-state error, and has faster algorithm convergence speed and less steady-state error si-multaneously.
Challenges in the Verification of Reinforcement Learning Algorithms
Van Wesel, Perry; Goodloe, Alwyn E.
2017-01-01
Machine learning (ML) is increasingly being applied to a wide array of domains from search engines to autonomous vehicles. These algorithms, however, are notoriously complex and hard to verify. This work looks at the assumptions underlying machine learning algorithms as well as some of the challenges in trying to verify ML algorithms. Furthermore, we focus on the specific challenges of verifying reinforcement learning algorithms. These are highlighted using a specific example. Ultimately, we do not offer a solution to the complex problem of ML verification, but point out possible approaches for verification and interesting research opportunities.
Location-Aware Mobile Learning of Spatial Algorithms
Karavirta, Ville
2013-01-01
Learning an algorithm--a systematic sequence of operations for solving a problem with given input--is often difficult for students due to the abstract nature of the algorithms and the data they process. To help students understand the behavior of algorithms, a subfield in computing education research has focused on algorithm…
A new accelerating algorithm for multi-agent reinforcement learning
Institute of Scientific and Technical Information of China (English)
ZHANG Ru-bo; ZHONG Yu; GU Guo-chang
2005-01-01
In multi-agent systems, joint-action must be employed to achieve cooperation because the evaluation of the behavior of an agent often depends on the other agents' behaviors. However, joint-action reinforcement learning algorithms suffer the slow convergence rate because of the enormous learning space produced by jointaction. In this article, a prediction-based reinforcement learning algorithm is presented for multi-agent cooperation tasks, which demands all agents to learn predicting the probabilities of actions that other agents may execute. A multi-robot cooperation experiment is run to test the efficacy of the new algorithm, and the experiment results show that the new algorithm can achieve the cooperation policy much faster than the primitive reinforcement learning algorithm.
Iterative Compilation Method Based on Incremental Instance Learning%一种基于增量式实例学习的迭代编译方法
Institute of Scientific and Technical Information of China (English)
马晓东; 李中升; 漆锋滨; 尉红梅
2012-01-01
For the purpose of making the compiler more adaptive and dealing with complex architecture, a compiler framework is proposed which combines iterative compilation and instance-based learning. On one hand, the compiler can search the optimization space and save the best compiler options into the knowledge library; on the other hand, the compiler can learn from the library to get the best compiler options for the current program. The incremental algorithm can make full use of the accumulated data of the compilation. The algorithms are proposed which can keep the redundant instance out of the knowledge library and filter the noise from the library.%为提高编译器的自适应性,以应对复杂的体系结构,提出一个结合迭代编译和机器学习的编译框架.编译器可将在优化空间中搜索到的最佳编译选项信息保存到知识库中,并能从知识库中学习获得适合当前程序的最佳编译选项.实例学习算法具有增量式的特点,可有效利用编译过程中积累的数据.通过避免冗余实例入库以及从库中剔除噪声实例,保证学习的精度与效率.
Incremental Sequential Learning for Fuzzy Neural Networks%一种连续增量学习模糊神经网络*
Institute of Scientific and Technical Information of China (English)
胡蓉; 徐蔚鸿; 甘岚
2013-01-01
为获得快速、准确而精简的模糊神经网络，提出一种连续增量学习模糊神经网络( ISL-FNN)。将修剪策略引入到神经元的产生过程，用错误下降率定义输入数据对系统输出的影响并应用于神经元的增长过程。在参数的学习阶段，所有隐含层神经元(无论是新增还是已有)的参数使用扩展的卡尔曼算法更新。通过仿真实验，该算法在达到与其它算法性能相当甚至更好的情况下，能获得更精简的结构。%To gain a fast, accurate and parsimonious fuzzy neural network, an effective incremental sequential learning algorithm for parsimonious fuzzy neural networks ( ISL-FNN) is proposed. The pruning strategy is introduced into the generation of neurons. The error reduction ratio is used to define the influence of input data on the output and the influence is utilized for the generation of neurons. In the parameter learning phase, all the free parameters of hidden units, including the newly created and the originally existing, are updated by the extended Kalman filter method. The performance of ISL-FNN is compared with several existing algorithms on some benchmark problems. Result indicates that ISL-FNN produces similar or even better accuracies with less number of rules.
Clonal Selection Algorithm Based Iterative Learning Control with Random Disturbance
Directory of Open Access Journals (Sweden)
Yuanyuan Ju
2013-01-01
Full Text Available Clonal selection algorithm is improved and proposed as a method to solve optimization problems in iterative learning control. And a clonal selection algorithm based optimal iterative learning control algorithm with random disturbance is proposed. In the algorithm, at the same time, the size of the search space is decreased and the convergence speed of the algorithm is increased. In addition a model modifying device is used in the algorithm to cope with the uncertainty in the plant model. In addition a model is used in the algorithm cope with the uncertainty in the plant model. Simulations show that the convergence speed is satisfactory regardless of whether or not the plant model is precise nonlinear plants. The simulation test verify the controlled system with random disturbance can reached to stability by using improved iterative learning control law but not the traditional control law.
Gnadt, William; Grossberg, Stephen
2008-06-01
How do reactive and planned behaviors interact in real time? How are sequences of such behaviors released at appropriate times during autonomous navigation to realize valued goals? Controllers for both animals and mobile robots, or animats, need reactive mechanisms for exploration, and learned plans to reach goal objects once an environment becomes familiar. The SOVEREIGN (Self-Organizing, Vision, Expectation, Recognition, Emotion, Intelligent, Goal-oriented Navigation) animat model embodies these capabilities, and is tested in a 3D virtual reality environment. SOVEREIGN includes several interacting subsystems which model complementary properties of cortical What and Where processing streams and which clarify similarities between mechanisms for navigation and arm movement control. As the animat explores an environment, visual inputs are processed by networks that are sensitive to visual form and motion in the What and Where streams, respectively. Position-invariant and size-invariant recognition categories are learned by real-time incremental learning in the What stream. Estimates of target position relative to the animat are computed in the Where stream, and can activate approach movements toward the target. Motion cues from animat locomotion can elicit head-orienting movements to bring a new target into view. Approach and orienting movements are alternately performed during animat navigation. Cumulative estimates of each movement are derived from interacting proprioceptive and visual cues. Movement sequences are stored within a motor working memory. Sequences of visual categories are stored in a sensory working memory. These working memories trigger learning of sensory and motor sequence categories, or plans, which together control planned movements. Predictively effective chunk combinations are selectively enhanced via reinforcement learning when the animat is rewarded. Selected planning chunks effect a gradual transition from variable reactive exploratory
Automated training for algorithms that learn from genomic data.
Cilingir, Gokcen; Broschat, Shira L
2015-01-01
Supervised machine learning algorithms are used by life scientists for a variety of objectives. Expert-curated public gene and protein databases are major resources for gathering data to train these algorithms. While these data resources are continuously updated, generally, these updates are not incorporated into published machine learning algorithms which thereby can become outdated soon after their introduction. In this paper, we propose a new model of operation for supervised machine learning algorithms that learn from genomic data. By defining these algorithms in a pipeline in which the training data gathering procedure and the learning process are automated, one can create a system that generates a classifier or predictor using information available from public resources. The proposed model is explained using three case studies on SignalP, MemLoci, and ApicoAP in which existing machine learning models are utilized in pipelines. Given that the vast majority of the procedures described for gathering training data can easily be automated, it is possible to transform valuable machine learning algorithms into self-evolving learners that benefit from the ever-changing data available for gene products and to develop new machine learning algorithms that are similarly capable.
Directory of Open Access Journals (Sweden)
Chie eHabagishi
2014-02-01
Full Text Available In daily life, we encounter situations where we must quickly decide which hand to use for a motor action. Here, we investigated whether the hand chosen for a motor action varied over a short timescale (i.e., hours with changes in arm dynamics. Participants performed a reaching task in which they moved a specified hand to reach a target on a virtual reality display. During the task, a resistive viscous force field was abruptly applied to only the dominant hand. To evaluate changes in hand choice caused by this perturbation, participants performed an interleaved choice test in which they could freely choose either hand for reaching. Furthermore, to investigate the effect of temporal changes on arm dynamics and hand choice, we exposed the same participants to another condition in which the force field was introduced gradually. When the abrupt force was applied, use of the perturbed hand significantly decreased and not changed during the training. In contrast, when the incremental force was applied, use of the perturbed hand gradually decreased as force increased. Surprisingly, even though the final amount of force was identical between the two conditions, hand choice was significantly biased toward the unperturbed hand in the gradual condition. These results suggest that time-varying changes in arm dynamics may have a greater influence on hand choice than the amplitude of the resistant force itself.
Lodhi, Ehtisham; Lodhi, Zeeshan; Noman Shafqat, Rana; Chen, Fieda
2017-07-01
Photovoltaic (PV) system usually employed The Maximum power point tracking (MPPT) techniques for increasing its efficiency. The performance of the PV system perhaps boosts by controlling at its apex point of power, in this way maximal power can be given to load. The proficiency of a PV system usually depends upon irradiance, temperature and array architecture. PV array shows a non-linear style for V-I curve and maximal power point on V-P curve also varies with changing environmental conditions. MPPT methods grantees that a PV module is regulated at reference voltage and to produce entire usage of the maximal output power. This paper gives analysis between two widely employed Perturb and Observe (P&O) and Incremental Conductance (INC) MPPT techniques. Their performance is evaluated and compared through theoretical analysis and digital simulation on the basis of response time and efficiency under varying irradiance and temperature condition using Matlab/Simulink.
Incremental Gaussian Processes
DEFF Research Database (Denmark)
Quiñonero-Candela, Joaquin; Winther, Ole
2002-01-01
In this paper, we consider Tipping's relevance vector machine (RVM) and formalize an incremental training strategy as a variant of the expectation-maximization (EM) algorithm that we call subspace EM. Working with a subset of active basis functions, the sparsity of the RVM solution will ensure th...
Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification
Directory of Open Access Journals (Sweden)
R. Sathya
2013-02-01
Full Text Available This paper presents a comparative account of unsupervised and supervised learning models and their pattern classification evaluations as applied to the higher education scenario. Classification plays a vital role in machine based learning algorithms and in the present study, we found that, though the error back-propagation learning algorithm as provided by supervised learning model is very efficient for a number of non-linear real-time problems, KSOM of unsupervised learning model, offers efficient solution and classification in the present study.
Human resource recommendation algorithm based on ensemble learning and Spark
Cong, Zihan; Zhang, Xingming; Wang, Haoxiang; Xu, Hongjie
2017-08-01
Aiming at the problem of “information overload” in the human resources industry, this paper proposes a human resource recommendation algorithm based on Ensemble Learning. The algorithm considers the characteristics and behaviours of both job seeker and job features in the real business circumstance. Firstly, the algorithm uses two ensemble learning methods-Bagging and Boosting. The outputs from both learning methods are then merged to form user interest model. Based on user interest model, job recommendation can be extracted for users. The algorithm is implemented as a parallelized recommendation system on Spark. A set of experiments have been done and analysed. The proposed algorithm achieves significant improvement in accuracy, recall rate and coverage, compared with recommendation algorithms such as UserCF and ItemCF.
An efficient learning algorithm for associative memories.
Wu, Y; Batalama, S N
2000-01-01
Associative memories (AMs) can be implemented using networks with or without feedback. In this paper we utilize a two-layer feedforward neural network and propose a new learning algorithm that efficiently implements the association rule of a bipolar AM. The hidden layer of the network employs p neurons where p is the number of prototype patterns. In the first layer, the input pattern activates at most one hidden layer neuron or "winner." In the second layer, the "winner" associates the input pattern to the corresponding prototype pattern. The underlying association principle is minimum Hamming distance and the proposed scheme can be viewed also as an approximately minimum Hamming distance decoder. Theoretical analysis supported by simulations indicates that, in comparison with other suboptimum minimum Hamming distance association schemes, the proposed structure exhibits the following favorable characteristics: 1) It operates in one-shot which implies no convergence-time requirements; 2) it does not require any feedback; and 3) our case studies show that it exhibits superior performance than the popular linear system in a saturated mode (LSSM). The network also exhibits 4) exponential capacity and 5) easy performance assessment (no asymptotic analysis is necessary). Finally, since it does not require any hidden layer interconnections or tree-search operations, it exhibits low structural as well as operational complexity.
Stable myoelectric control of a hand prosthesis using non-linear incremental learning
2014-01-01
Stable myoelectric control of hand prostheses remains an open problem. The only successful human–machine interface is surface electromyography, typically allowing control of a few degrees of freedom. Machine learning techniques may have the potential to remove these limitations, but their performance is thus far inadequate: myoelectric signals change over time under the influence of various factors, deteriorating control performance. It is therefore necessary, in the standard approach, to reg...
Linkage intensity learning approach with genetic algorithm for causality diagram
Institute of Scientific and Technical Information of China (English)
WANG Cheng-liang; CHEN Juan-juan
2007-01-01
The causality diagram theory, which adopts graphical expression of knowledge and direct intensity of causality, overcomes some shortages in belief network and has evolved into a mixed causality diagram methodology for discrete and continuous variable. But to give linkage intensity of causality diagram is difficult, particularly in many working conditions in which sampling data are limited or noisy. The classic learning algorithm is hard to be adopted. We used genetic algorithm to learn linkage intensity from limited data. The simulation results demonstrate that this algorithm is more suitable than the classic algorithm in the condition of sample shortage such as space shuttle's fault diagnoisis.
A Sparse Bayesian Learning Algorithm for Longitudinal Image Data.
Sabuncu, Mert R
2015-10-01
Longitudinal imaging studies, where serial (multiple) scans are collected on each individual, are becoming increasingly widespread. The field of machine learning has in general neglected the longitudinal design, since many algorithms are built on the assumption that each datapoint is an independent sample. Thus, the application of general purpose machine learning tools to longitudinal image data can be sub-optimal. Here, we present a novel machine learning algorithm designed to handle longitudinal image datasets. Our approach builds on a sparse Bayesian image-based prediction algorithm. Our empirical results demonstrate that the proposed method can offer a significant boost in prediction performance with longitudinal clinical data.
Directory of Open Access Journals (Sweden)
Seyed Meysam Seyedbarzegar
2015-03-01
Full Text Available Abstract: in this paper the optimal placement of spacers in surge arrester column is presented in order to achieve temperature reduction and surge arrester thermal stability against power losses due to the overvoltage in power system. The simulation is done by using genetic algorithm in MATLAB software that it is linked by numerical analysis, i.e., Finite Element Method (FEM. First, electro thermal analysis is performed according to the IEC60099-4 standard on selected population in certain interval and, then the required data is applied to the genetic algorithm for the optimal placement of spacers. Simulation results show that the placement of spacers has great influence on surge arrester temperature variations. Finally, the optimal model of surge arrester is simulated in COMSOL software and the results of this model are compared with conventional model results.
Incremental Learning of Medical Data for Multi-Step Patient Health Classification
DEFF Research Database (Denmark)
Kranen, Philipp; Müller, Emmanuel; Assent, Ira;
2010-01-01
-step classification in health surveillance. By supporting anytime learning and anytime classification the presented Bayes tree technique can handle huge amounts of data, which makes it a consistent solution for the described medical scenario. Moreover, as we laid out in this chapter, the Bayes tree fulfills all...... requirements which are crucial for classifying medical patient data in a scalable health surveillance. Future challenges include extending the existing framework and evaluating the Bayes tree classifier based on sensor measurements in a broad health surveillance project. This project will include extensions...
GEOLOGICAL MAPPING USING MACHINE LEARNING ALGORITHMS
Directory of Open Access Journals (Sweden)
A. S. Harvey
2016-06-01
Full Text Available Remotely sensed spectral imagery, geophysical (magnetic and gravity, and geodetic (elevation data are useful in a variety of Earth science applications such as environmental monitoring and mineral exploration. Using these data with Machine Learning Algorithms (MLA, which are widely used in image analysis and statistical pattern recognition applications, may enhance preliminary geological mapping and interpretation. This approach contributes towards a rapid and objective means of geological mapping in contrast to conventional field expedition techniques. In this study, four supervised MLAs (naïve Bayes, k-nearest neighbour, random forest, and support vector machines are compared in order to assess their performance for correctly identifying geological rocktypes in an area with complete ground validation information. Geological maps of the Sudbury region are used for calibration and validation. Percent of correct classifications was used as indicators of performance. Results show that random forest is the best approach. As expected, MLA performance improves with more calibration clusters, i.e. a more uniform distribution of calibration data over the study region. Performance is generally low, though geological trends that correspond to a ground validation map are visualized. Low performance may be the result of poor spectral images of bare rock which can be covered by vegetation or water. The distribution of calibration clusters and MLA input parameters affect the performance of the MLAs. Generally, performance improves with more uniform sampling, though this increases required computational effort and time. With the achievable performance levels in this study, the technique is useful in identifying regions of interest and identifying general rocktype trends. In particular, phase I geological site investigations will benefit from this approach and lead to the selection of sites for advanced surveys.
Geological Mapping Using Machine Learning Algorithms
Harvey, A. S.; Fotopoulos, G.
2016-06-01
Remotely sensed spectral imagery, geophysical (magnetic and gravity), and geodetic (elevation) data are useful in a variety of Earth science applications such as environmental monitoring and mineral exploration. Using these data with Machine Learning Algorithms (MLA), which are widely used in image analysis and statistical pattern recognition applications, may enhance preliminary geological mapping and interpretation. This approach contributes towards a rapid and objective means of geological mapping in contrast to conventional field expedition techniques. In this study, four supervised MLAs (naïve Bayes, k-nearest neighbour, random forest, and support vector machines) are compared in order to assess their performance for correctly identifying geological rocktypes in an area with complete ground validation information. Geological maps of the Sudbury region are used for calibration and validation. Percent of correct classifications was used as indicators of performance. Results show that random forest is the best approach. As expected, MLA performance improves with more calibration clusters, i.e. a more uniform distribution of calibration data over the study region. Performance is generally low, though geological trends that correspond to a ground validation map are visualized. Low performance may be the result of poor spectral images of bare rock which can be covered by vegetation or water. The distribution of calibration clusters and MLA input parameters affect the performance of the MLAs. Generally, performance improves with more uniform sampling, though this increases required computational effort and time. With the achievable performance levels in this study, the technique is useful in identifying regions of interest and identifying general rocktype trends. In particular, phase I geological site investigations will benefit from this approach and lead to the selection of sites for advanced surveys.
Incremental Learning of Medical Data for Multi-Step Patient Health Classification
DEFF Research Database (Denmark)
Kranen, Philipp; Müller, Emmanuel; Assent, Ira
2010-01-01
of textile sensors, body sensors and preprocessing techniques as well as the integration and merging of sensor data in electronic health record systems. Emergency detection on multiple levels will show the benefits of multi-step classification and further enhance the scalability of emergency detection......In this chapter we presented major challenges derived out of next generation mobile health surveillance. For the emergency detection task we highlighted semi-automated classification as ongoing research in this field. We showed how novel index-based classifiers build the core for multivariate multi......-step classification in health surveillance. By supporting anytime learning and anytime classification the presented Bayes tree technique can handle huge amounts of data, which makes it a consistent solution for the described medical scenario. Moreover, as we laid out in this chapter, the Bayes tree fulfills all...
Risk-sensitive reinforcement learning algorithms with generalized average criterion
Institute of Scientific and Technical Information of China (English)
YIN Chang-ming; WANG Han-xing; ZHAO Fei
2007-01-01
A new algorithm is proposed, which immolates the optimality of control policies potentially to obtain the robusticity of solutions. The robusticity of solutions maybe becomes a very important property for a learning system when there exists non-matching between theory models and practical physical system, or the practical system is not static,or the availability of a control action changes along with the variety of time. The main contribution is that a set of approximation algorithms and their convergence results are given. A generalized average operator instead of the general optimal operator max (or min) is applied to study a class of important learning algorithms, dynamic programming algorithms, and discuss their convergences from theoretic point of view. The purpose for this research is to improve the robusticity of reinforcement learning algorithms theoretically.
Multi-agent reinforcement learning using modular neural network Q-learning algorithms
Institute of Scientific and Technical Information of China (English)
YANG Yin-xian; FANG Kai
2005-01-01
Reinforcement learning is an excellent approach which is used in artificial intelligence,automatic control, etc. However, ordinary reinforcement learning algorithm, such as Q-learning with lookup table cannot cope with extremely complex and dynamic environment due to the huge state space. To reduce the state space, modular neural network Q-learning algorithm is proposed, which combines Q-learning algorithm with neural network and module method. Forward feedback neural network, Elman neural network and radius-basis neural network are separately employed to construct such algorithm. It is revealed that Elman neural network Q-learning algorithm has the best performance under the condition that the same neural network training method, i.e. gradient descent error back-propagation algorithm is applied.
Two Novel On-policy Reinforcement Learning Algorithms based on TD(lambda)-methods
Wiering, M.A.; Hasselt, H. van
2007-01-01
This paper describes two novel on-policy reinforcement learning algorithms, named QV(lambda)-learning and the actor critic learning automaton (ACLA). Both algorithms learn a state value-function using TD(lambda)-methods. The difference between the algorithms is that QV-learning uses the learned
Teaching learning based optimization algorithm and its engineering applications
Rao, R Venkata
2016-01-01
Describing a new optimization algorithm, the “Teaching-Learning-Based Optimization (TLBO),” in a clear and lucid style, this book maximizes reader insights into how the TLBO algorithm can be used to solve continuous and discrete optimization problems involving single or multiple objectives. As the algorithm operates on the principle of teaching and learning, where teachers influence the quality of learners’ results, the elitist version of TLBO algorithm (ETLBO) is described along with applications of the TLBO algorithm in the fields of electrical engineering, mechanical design, thermal engineering, manufacturing engineering, civil engineering, structural engineering, computer engineering, electronics engineering, physics and biotechnology. The book offers a valuable resource for scientists, engineers and practitioners involved in the development and usage of advanced optimization algorithms.
Information theoretic derivation of network architecture and learning algorithms
Energy Technology Data Exchange (ETDEWEB)
Jones, R.D.; Barnes, C.W.; Lee, Y.C.; Mead, W.C.
1991-01-01
Using variational techniques, we derive a feedforward network architecture that minimizes a least squares cost function with the soft constraint that the mutual information between input and output be maximized. This permits optimum generalization for a given accuracy. A set of learning algorithms are also obtained. The network and learning algorithms are tested on a set of test problems which emphasize time series prediction. 6 refs., 1 fig.
On stochastic approximation algorithms for classes of PAC learning problems
Energy Technology Data Exchange (ETDEWEB)
Rao, N.S.V.; Uppuluri, V.R.R.; Oblow, E.M.
1994-03-01
The classical stochastic approximation methods are shown to yield algorithms to solve several formulations of the PAC learning problem defined on the domain [o,1]{sup d}. Under some assumptions on different ability of the probability measure functions, simple algorithms to solve some PAC learning problems are proposed based on networks of non-polynomial units (e.g. artificial neural networks). Conditions on the sizes of these samples required to ensure the error bounds are derived using martingale inequalities.
Imbalanced learning foundations, algorithms, and applications
He, Haibo
2013-01-01
The first book of its kind to review the current status and future direction of the exciting new branch of machine learning/data mining called imbalanced learning Imbalanced learning focuses on how an intelligent system can learn when it is provided with imbalanced data. Solving imbalanced learning problems is critical in numerous data-intensive networked systems, including surveillance, security, Internet, finance, biomedical, defense, and more. Due to the inherent complex characteristics of imbalanced data sets, learning from such data requires new understandings, principles,
SelfieBoost: A Boosting Algorithm for Deep Learning
2014-01-01
We describe and analyze a new boosting algorithm for deep learning called SelfieBoost. Unlike other boosting algorithms, like AdaBoost, which construct ensembles of classifiers, SelfieBoost boosts the accuracy of a single network. We prove a $\\log(1/\\epsilon)$ convergence rate for SelfieBoost under some "SGD success" assumption which seems to hold in practice.
Online semi-supervised learning: algorithm and application in metagenomics
S. Imangaliyev; B. Keijser; W. Crielaard; E. Tsivtsivadze
2013-01-01
As the amount of metagenomic data grows rapidly, online statistical learning algorithms are poised to play key role in metagenome analysis tasks. Frequently, data are only partially labeled, namely dataset contains partial information about the problem of interest. This work presents an algorithm an
Online Semi-Supervised Learning: Algorithm and Application in Metagenomics
Imangaliyev, S.; Keijser, B.J.F.; Crielaard, W.; Tsivtsivadze, E.
2013-01-01
As the amount of metagenomic data grows rapidly, online statistical learning algorithms are poised to play key rolein metagenome analysis tasks. Frequently, data are only partially labeled, namely dataset contains partial information about the problem of interest. This work presents an algorithm and
Online learning algorithm for ensemble of decision rules
Chikalov, Igor
2011-01-01
We describe an online learning algorithm that builds a system of decision rules for a classification problem. Rules are constructed according to the minimum description length principle by a greedy algorithm or using the dynamic programming approach. © 2011 Springer-Verlag.
SelfieBoost: A Boosting Algorithm for Deep Learning
Shalev-Shwartz, Shai
2014-01-01
We describe and analyze a new boosting algorithm for deep learning called SelfieBoost. Unlike other boosting algorithms, like AdaBoost, which construct ensembles of classifiers, SelfieBoost boosts the accuracy of a single network. We prove a $\\log(1/\\epsilon)$ convergence rate for SelfieBoost under some "SGD success" assumption which seems to hold in practice.
Extreme learning machines 2013 algorithms and applications
Toh, Kar-Ann; Romay, Manuel; Mao, Kezhi
2014-01-01
In recent years, ELM has emerged as a revolutionary technique of computational intelligence, and has attracted considerable attentions. An extreme learning machine (ELM) is a single layer feed-forward neural network alike learning system, whose connections from the input layer to the hidden layer are randomly generated, while the connections from the hidden layer to the output layer are learned through linear learning methods. The outstanding merits of extreme learning machine (ELM) are its fast learning speed, trivial human intervene and high scalability. This book contains some selected papers from the International Conference on Extreme Learning Machine 2013, which was held in Beijing China, October 15-17, 2013. This conference aims to bring together the researchers and practitioners of extreme learning machine from a variety of fields including artificial intelligence, biomedical engineering and bioinformatics, system modelling and control, and signal and image processing, to promote research and discu...
Supervised learning algorithms for visual object categorization
bin Abdullah, A.
2010-01-01
This thesis presents novel techniques for image recognition systems for better understanding image content. More specifically, it looks at the algorithmic aspects and experimental verification to demonstrate the capability of the proposed algorithms. These techniques aim to improve the three major
Wrapped Progressive Sampling Search for Optimizing Learning Algorithm Parameters
Bosch, Antal van den
2005-01-01
We present a heuristic meta-learning search method for finding a set of optimized algorithmic parameters for a range of machine learning algo- rithms. The method, wrapped progressive sampling, is a combination of classifier wrapping and progressive sampling of training data. A series of experiments
Wrapped Progressive Sampling Search for Optimizing Learning Algorithm Parameters
Bosch, Antal van den
2005-01-01
We present a heuristic meta-learning search method for finding a set of optimized algorithmic parameters for a range of machine learning algo- rithms. The method, wrapped progressive sampling, is a combination of classifier wrapping and progressive sampling of training data. A series of experiments
Learning motor skills from algorithms to robot experiments
Kober, Jens
2014-01-01
This book presents the state of the art in reinforcement learning applied to robotics both in terms of novel algorithms and applications. It discusses recent approaches that allow robots to learn motor skills and presents tasks that need to take into account the dynamic behavior of the robot and its environment, where a kinematic movement plan is not sufficient. The book illustrates a method that learns to generalize parameterized motor plans which is obtained by imitation or reinforcement learning, by adapting a small set of global parameters, and appropriate kernel-based reinforcement learning algorithms. The presented applications explore highly dynamic tasks and exhibit a very efficient learning process. All proposed approaches have been extensively validated with benchmarks tasks, in simulation, and on real robots. These tasks correspond to sports and games but the presented techniques are also applicable to more mundane household tasks. The book is based on the first author’s doctoral thesis, which wo...
A Structure Learning Algorithm for Bayesian Network Using Prior Knowledge
Institute of Scientific and Technical Information of China (English)
徐俊刚; 赵越; 陈健; 韩超
2015-01-01
Learning structure from data is one of the most important fundamental tasks of Bayesian network research. Particularly, learning optional structure of Bayesian network is a non-deterministic polynomial-time (NP) hard problem. To solve this problem, many heuristic algorithms have been proposed, and some of them learn Bayesian network structure with the help of different types of prior knowledge. However, the existing algorithms have some restrictions on the prior knowledge, such as quality restriction and use restriction. This makes it diﬃcult to use the prior knowledge well in these algorithms. In this paper, we introduce the prior knowledge into the Markov chain Monte Carlo (MCMC) algorithm and propose an algorithm called Constrained MCMC (C-MCMC) algorithm to learn the structure of the Bayesian network. Three types of prior knowledge are defined: existence of parent node, absence of parent node, and distribution knowledge including the conditional probability distribution (CPD) of edges and the probability distribution (PD) of nodes. All of these types of prior knowledge are easily used in this algorithm. We conduct extensive experiments to demonstrate the feasibility and effectiveness of the proposed method C-MCMC.
Dynamical transitions in the evolution of learning algorithms by selection
Neirotti, J P; Neirotti, Juan Pablo; Caticha, Nestor
2002-01-01
We study the evolution of artificial learning systems by means of selection. Genetic programming is used to generate a sequence of populations of algorithms which can be used by neural networks for supervised learning of a rule that generates examples. In opposition to concentrating on final results, which would be the natural aim while designing good learning algorithms, we study the evolution process and pay particular attention to the temporal order of appearance of functional structures responsible for the improvements in the learning process, as measured by the generalization capabilities of the resulting algorithms. The effect of such appearances can be described as dynamical phase transitions. The concepts of phenotypic and genotypic entropies, which serve to describe the distribution of fitness in the population and the distribution of symbols respectively, are used to monitor the dynamics. In different runs the phase transitions might be present or not, with the system finding out good solutions, or ...
Machine learning algorithms for datasets popularity prediction
Kancys, Kipras
2016-01-01
This report represents continued study where ML algorithms were used to predict databases popularity. Three topics were covered. First of all, there was a discrepancy between old and new meta-data collection procedures, so a reason for that had to be found. Secondly, different parameters were analysed and dropped to make algorithms perform better. And third, it was decided to move modelling part on Spark.
A meta-learning system based on genetic algorithms
Pellerin, Eric; Pigeon, Luc; Delisle, Sylvain
2004-04-01
The design of an efficient machine learning process through self-adaptation is a great challenge. The goal of meta-learning is to build a self-adaptive learning system that is constantly adapting to its specific (and dynamic) environment. To that end, the meta-learning mechanism must improve its bias dynamically by updating the current learning strategy in accordance with its available experiences or meta-knowledge. We suggest using genetic algorithms as the basis of an adaptive system. In this work, we propose a meta-learning system based on a combination of the a priori and a posteriori concepts. A priori refers to input information and knowledge available at the beginning in order to built and evolve one or more sets of parameters by exploiting the context of the system"s information. The self-learning component is based on genetic algorithms and neural Darwinism. A posteriori refers to the implicit knowledge discovered by estimation of the future states of parameters and is also applied to the finding of optimal parameters values. The in-progress research presented here suggests a framework for the discovery of knowledge that can support human experts in their intelligence information assessment tasks. The conclusion presents avenues for further research in genetic algorithms and their capability to learn to learn.
QUEST: Eliminating Online Supervised Learning for Efficient Classification Algorithms
Directory of Open Access Journals (Sweden)
Ardjan Zwartjes
2016-10-01
Full Text Available In this work, we introduce QUEST (QUantile Estimation after Supervised Training, an adaptive classification algorithm for Wireless Sensor Networks (WSNs that eliminates the necessity for online supervised learning. Online processing is important for many sensor network applications. Transmitting raw sensor data puts high demands on the battery, reducing network life time. By merely transmitting partial results or classifications based on the sampled data, the amount of traffic on the network can be significantly reduced. Such classifications can be made by learning based algorithms using sampled data. An important issue, however, is the training phase of these learning based algorithms. Training a deployed sensor network requires a lot of communication and an impractical amount of human involvement. QUEST is a hybrid algorithm that combines supervised learning in a controlled environment with unsupervised learning on the location of deployment. Using the SITEX02 dataset, we demonstrate that the presented solution works with a performance penalty of less than 10% in 90% of the tests. Under some circumstances, it even outperforms a network of classifiers completely trained with supervised learning. As a result, the need for on-site supervised learning and communication for training is completely eliminated by our solution.
Evaluating the Security of Machine Learning Algorithms
2008-05-20
description of this setting and several results appear in Cesa -Bianchi and Lugosi [2006]. 2.5 Summary In this chapter we have presented a framework for...Learning Research (JMLR), 3:993–1022, 2003. ISSN 1533-7928. Nicolò Cesa -Bianchi and Gábor Lugosi. Prediction, Learning, and Games. Cambridge University
A Fast Incremental Placement Algorithm for Standard-Cells%标准单元模式下的一种快速增量式布局算法
Institute of Scientific and Technical Information of China (English)
姚波; 洪先龙; 于泓; 蔡懿慈; 顾钧
2001-01-01
Incremental placement or ECO placement is a new field in VLSIlayout to meet the demand of high performance design.It detects illegal cell positions and moves cells locally to find a feasible placement solution.This paper proposes an incremental placement algorithm for standard-cell design mode.It adopts row partitioning to cope with various placement constraints,and then inserts trouble cells one by one.An integer programming(IP)problem is constructed and solved to get the best solution of cell insertion.A dual diagonal searching(DDS)method is proposed to solve this special IP problem.We prove that DDS can always be the best solution and its time complexity is O(n).Experiments on a group of industrial test cases show that our algorithm is efficient and robust.It runs 10 times faster than a simple heuristic method and reduces more than 20 percent placement modification in average.%增量式布局是适应高性能设计要求的一种新的布局模式.它针对电路更改，局部地调整单元位置，重新获得合理的布局.本文提出了一种标准单元模式下的快速增量布局算法.算法采用单元行划分的方法处理布局约束，然后将布局调整归结为单元依次插入单元行的问题，并构造了一个数学规划求解最佳的插入方案.同时提出了复杂度为O(n)的双对角线搜索法求解这个特殊的数学规划.实际电路测试表明算法高效而稳定，比简单的启发式算法快十倍，并使布局修改减少20%以上.
Dynamic Prediction of Financial Distress Based on Incremental Learning System%基于增量学习系统的财务危机动态预警
Institute of Scientific and Technical Information of China (English)
时建中; 程龙生
2012-01-01
In view of the problems existing in most of models of predicting financial distress, such as the static modeling, the lack of incremental learning ability and so on, an incremental learning system based on the classifier ensemble is designed. Financial category-oriented knowledge is applied to realize the dynamic selection for the classifier ensemble subsystem. Then the dynamic prediction model of financial distress with incre- mental learning ability is build. Model experiments show that, the prediction model of financial distress based on the incremental learning system is stable and adaptable,which is an effective method of predicting financial distress.%针对目前多数财务危机预警模型为静态建模、模型的增量学习能力不足等问题,设计了一种基于分类器集成的增量学习系统,利用财务类别导向知识对集成子系统进行动态选择,构建了具有增量学习能力的财务危机动态预警模型。基于实际财务数据的实验表明,基于增量学习系统的财务危机预警模型是一种兼具稳定性和适应性的财务危机预警工具。
Dermoscopic Image Segmentation using Machine Learning Algorithm
Directory of Open Access Journals (Sweden)
L. P. Suresh
2011-01-01
Full Text Available Problem statement: Malignant melanoma is the most frequent type of skin cancer. Its incidence has been rapidly increasing over the last few decades. Medical image segmentation is the most essential and crucial process in order to facilitate the characterization and visualization of the structure of interest in medical images. Approach: This study explains the task of segmenting skin lesions in Dermoscopy images based on intelligent systems such as Fuzzy and Neural Networks clustering techniques for the early diagnosis of Malignant Melanoma. The various intelligent system based clustering techniques used are Fuzzy C Means Algorithm (FCM, Possibilistic C Means Algorithm (PCM, Hierarchical C Means Algorithm (HCM; C-mean based Fuzzy Hopfield Neural Network, Adaline Neural Network and Regression Neural Network. Results: The segmented images are compared with the ground truth image using various parameters such as False Positive Error (FPE, False Negative Error (FNE Coefficient of similarity, spatial overlap and their performance is evaluated. Conclusion: The experimental results show that the Hierarchical C Means algorithm( Fuzzy provides better segmentation than other (Fuzzy C Means, Possibilistic C Means, Adaline Neural Network, FHNN and GRNN clustering algorithms. Thus Hierarchical C Means approach can handle uncertainties that exist in the data efficiently and useful for the lesion segmentation in a computer aided diagnosis system to assist the clinical diagnosis of dermatologists.
A Linkage Learning Genetic Algorithm with Linkage Matrix
Institute of Scientific and Technical Information of China (English)
无
2006-01-01
The goal of linkage learning, or building block identification, is the creation of a more effective Genetic Algorithm (GA). This paper proposes a new Linkage Learning Genetic Algorithms, named m-LLGA. With the linkage learning module and the linkage-based genetic operation, m-LLGA is not only able to learn and record the linkage information among genes without any prior knowledge of the function being optimized. It also can use the linkage information stored in the linkage matrix to guide the selection of crossover point. The preliminary experiments on two kinds of bounded difficulty problems and a TSP problem validated the performance of m-LLGA. The m-LLGA learns the linkage of different building blocks parallel and therefore solves these problems effectively; it can also reasonably reduce the probability of building blocks being disrupted by crossover at the same time give attention to getting away from local minimum.
Implementing a self-structuring data learning algorithm
Graham, James; Carson, Daniel; Ternovskiy, Igor
2016-05-01
In this paper, we elaborate on what we did to implement our self-structuring data learning algorithm. To recap, we are working to develop a data learning algorithm that will eventually be capable of goal driven pattern learning and extrapolation of more complex patterns from less complex ones. At this point we have developed a conceptual framework for the algorithm, but have yet to discuss our actual implementation and the consideration and shortcuts we needed to take to create said implementation. We will elaborate on our initial setup of the algorithm and the scenarios we used to test our early stage algorithm. While we want this to be a general algorithm, it is necessary to start with a simple scenario or two to provide a viable development and testing environment. To that end, our discussion will be geared toward what we include in our initial implementation and why, as well as what concerns we may have. In the future, we expect to be able to apply our algorithm to a more general approach, but to do so within a reasonable time, we needed to pick a place to start.
Learning Bayesian networks using genetic algorithm
Institute of Scientific and Technical Information of China (English)
Chen Fei; Wang Xiufeng; Rao Yimei
2007-01-01
A new method to evaluate the fitness of the Bayesian networks according to the observed data is provided. The main advantage of this criterion is that it is suitable for both the complete and incomplete cases while the others not.Moreover it facilitates the computation greatly. In order to reduce the search space, the notation of equivalent class proposed by David Chickering is adopted. Instead of using the method directly, the novel criterion, variable ordering, and equivalent class are combined,moreover the proposed mthod avoids some problems caused by the previous one. Later, the genetic algorithm which allows global convergence, lack in the most of the methods searching for Bayesian network is applied to search for a good model in thisspace. To speed up the convergence, the genetic algorithm is combined with the greedy algorithm. Finally, the simulation shows the validity of the proposed approach.
A statistical learning algorithm for word segmentation
Van Aken, Jerry R
2011-01-01
In natural speech, the speaker does not pause between words, yet a human listener somehow perceives this continuous stream of phonemes as a series of distinct words. The detection of boundaries between spoken words is an instance of a general capability of the human neocortex to remember and to recognize recurring sequences. This paper describes a computer algorithm that is designed to solve the problem of locating word boundaries in blocks of English text from which the spaces have been removed. This problem avoids the complexities of processing speech but requires similar capabilities for detecting recurring sequences. The algorithm that is described in this paper relies entirely on statistical relationships between letters in the input stream to infer the locations of word boundaries. The source code for a C++ version of this algorithm is presented in an appendix.
Incremental Trust in Grid Computing
DEFF Research Database (Denmark)
Brinkløv, Michael Hvalsøe; Sharp, Robin
2007-01-01
This paper describes a comparative simulation study of some incremental trust and reputation algorithms for handling behavioural trust in large distributed systems. Two types of reputation algorithm (based on discrete and Bayesian evaluation of ratings) and two ways of combining direct trust and ...... of Grid computing systems....
An entropy-based unsupervised anomaly detection pattern learning algorithm
Institute of Scientific and Technical Information of China (English)
YANG Ying-jie; MA Fan-yuan
2005-01-01
Currently, most anomaly detection pattern learning algorithms require a set of purely normal data from which they train their model. If the data contain some intrusions buried within the training data, the algorithm may not detect these attacks because it will assume that they are normal. In reality, it is very hard to guarantee that there are no attack items in the collected training data. Focusing on this problem, in this paper,firstly a new anomaly detection measurement is proposed according to the probability characteristics of intrusion instances and normal instances. Secondly, on the basis of anomaly detection measure, we present a clusteringbased unsupervised anomaly detection patterns learning algorithm, which can overcome the shortage above. Finally, some experiments are conducted to verify the proposed algorithm is valid.
Optimization of circuits using a constructive learning algorithm
Energy Technology Data Exchange (ETDEWEB)
Beiu, V.
1997-05-01
The paper presents an application of a constructive learning algorithm to optimization of circuits. For a given Boolean function f. a fresh constructive learning algorithm builds circuits belonging to the smallest F{sub n,m} class of functions (n inputs and having m groups of ones in their truth table). The constructive proofs, which show how arbitrary Boolean functions can be implemented by this algorithm, are shortly enumerated An interesting aspect is that the algorithm can be used for generating both classical Boolean circuits and threshold gate circuits (i.e. analogue inputs and digital outputs), or a mixture of them, thus taking advantage of mixed analogue/digital technologies. One illustrative example is detailed The size and the area of the different circuits are compared (special cost functions can be used to closer estimate the area and the delay of VLSI implementations). Conclusions and further directions of research are ending the paper.
Learning algorithms for feedforward networks based on finite samples
Energy Technology Data Exchange (ETDEWEB)
Rao, N.S.V.; Protopopescu, V.; Mann, R.C.; Oblow, E.M.; Iyengar, S.S.
1994-09-01
Two classes of convergent algorithms for learning continuous functions (and also regression functions) that are represented by feedforward networks, are discussed. The first class of algorithms, applicable to networks with unknown weights located only in the output layer, is obtained by utilizing the potential function methods of Aizerman et al. The second class, applicable to general feedforward networks, is obtained by utilizing the classical Robbins-Monro style stochastic approximation methods. Conditions relating the sample sizes to the error bounds are derived for both classes of algorithms using martingale-type inequalities. For concreteness, the discussion is presented in terms of neural networks, but the results are applicable to general feedforward networks, in particular to wavelet networks. The algorithms can be directly adapted to concept learning problems.
Machine-Learning Algorithms to Code Public Health Spending Accounts.
Brady, Eoghan S; Leider, Jonathon P; Resnick, Beth A; Alfonso, Y Natalia; Bishai, David
Government public health expenditure data sets require time- and labor-intensive manipulation to summarize results that public health policy makers can use. Our objective was to compare the performances of machine-learning algorithms with manual classification of public health expenditures to determine if machines could provide a faster, cheaper alternative to manual classification. We used machine-learning algorithms to replicate the process of manually classifying state public health expenditures, using the standardized public health spending categories from the Foundational Public Health Services model and a large data set from the US Census Bureau. We obtained a data set of 1.9 million individual expenditure items from 2000 to 2013. We collapsed these data into 147 280 summary expenditure records, and we followed a standardized method of manually classifying each expenditure record as public health, maybe public health, or not public health. We then trained 9 machine-learning algorithms to replicate the manual process. We calculated recall, precision, and coverage rates to measure the performance of individual and ensembled algorithms. Compared with manual classification, the machine-learning random forests algorithm produced 84% recall and 91% precision. With algorithm ensembling, we achieved our target criterion of 90% recall by using a consensus ensemble of ≥6 algorithms while still retaining 93% coverage, leaving only 7% of the summary expenditure records unclassified. Machine learning can be a time- and cost-saving tool for estimating public health spending in the United States. It can be used with standardized public health spending categories based on the Foundational Public Health Services model to help parse public health expenditure information from other types of health-related spending, provide data that are more comparable across public health organizations, and evaluate the impact of evidence-based public health resource allocation.
Neural-Network-Biased Genetic Algorithms for Materials Design: Evolutionary Algorithms That Learn.
Patra, Tarak K; Meenakshisundaram, Venkatesh; Hung, Jui-Hsiang; Simmons, David S
2017-02-13
Machine learning has the potential to dramatically accelerate high-throughput approaches to materials design, as demonstrated by successes in biomolecular design and hard materials design. However, in the search for new soft materials exhibiting properties and performance beyond those previously achieved, machine learning approaches are frequently limited by two shortcomings. First, because they are intrinsically interpolative, they are better suited to the optimization of properties within the known range of accessible behavior than to the discovery of new materials with extremal behavior. Second, they require large pre-existing data sets, which are frequently unavailable and prohibitively expensive to produce. Here we describe a new strategy, the neural-network-biased genetic algorithm (NBGA), for combining genetic algorithms, machine learning, and high-throughput computation or experiment to discover materials with extremal properties in the absence of pre-existing data. Within this strategy, predictions from a progressively constructed artificial neural network are employed to bias the evolution of a genetic algorithm, with fitness evaluations performed via direct simulation or experiment. In effect, this strategy gives the evolutionary algorithm the ability to "learn" and draw inferences from its experience to accelerate the evolutionary process. We test this algorithm against several standard optimization problems and polymer design problems and demonstrate that it matches and typically exceeds the efficiency and reproducibility of standard approaches including a direct-evaluation genetic algorithm and a neural-network-evaluated genetic algorithm. The success of this algorithm in a range of test problems indicates that the NBGA provides a robust strategy for employing informatics-accelerated high-throughput methods to accelerate materials design in the absence of pre-existing data.
Chen, G Y; Tsai, W H
1998-01-01
An incremental learning by navigation approach to vision based autonomous land vehicle (ALV) guidance in indoor environments is proposed. The approach consists of three stages: initial learning, navigation, and model updating. In the initial learning stage, the ALV is driven manually, and environment images and other status data are recorded automatically. Then, an offline procedure is performed to build an initial environment model. In the navigation stage, the ALV moves along the learned environment automatically, locates itself by model matching, and records necessary information for model updating. In the model updating stage, an offline procedure is performed to refine the learned model. A more precise model is obtained after each navigation-and-update iteration. Used environment features are vertical straight lines in camera views. A multiweighted generalized Hough transform is proposed for model matching. A real ALV was used as the testbed, and successful navigation experiments show the feasibility of the proposed approach.
Evolutionary Pseudo-Relaxation Learning Algorithm for Bidirectional Associative Memory
Institute of Scientific and Technical Information of China (English)
Sheng-Zhi Du; Zeng-Qiang Chen; Zhu-Zhi Yuan
2005-01-01
This paper analyzes the sensitivity to noise in BAM (Bidirectional Associative Memory), and then proves the noise immunity of BAM relates not only to the minimum absolute value of net inputs (MAV) but also to the variance of weights associated with synapse connections. In fact, it is a positive monotonically increasing function of the quotient of MAV divided by the variance of weights. Besides, the performance of pseudo-relaxation method depends on learning parameters (λ and ζ), but the relation of them is not linear. So it is hard to find a best combination of λ and ζ which leads to the best BAM performance. And it is obvious that pseudo-relaxation is a kind of local optimization method, so it cannot guarantee to get the global optimal solution. In this paper, a novel learning algorithm EPRBAM (evolutionary psendo-relaxation learning algorithm for bidirectional association memory) employing genetic algorithm and pseudo-relaxation method is proposed to get feasible solution of BAM weight matrix. This algorithm uses the quotient as the fitness of each individual and employs pseudo-relaxation method to adjust individual solution when it does not satisfy constraining condition any more after genetic operation. Experimental results show this algorithm improves noise immunity of BAM greatly. At the same time, EPRBAM does not depend on learning parameters and can get global optimal solution.
An Initiative-Learning Algorithm Based on System Uncertainty
Institute of Scientific and Technical Information of China (English)
ZHAO Jun
2005-01-01
Initiative-learning algorithms are characterized by and hence advantageous for their independence of prior domain knowledge.Usually,their induced results could more objectively express the potential characteristics and patterns of information systems.Initiative-learning processes can be effectively conducted by system uncertainty,because uncertainty is an intrinsic common feature of and also an essential link between information systems and their induced results.Obviously,the effectiveness of such initiative-learning framework is heavily dependent on the accuracy of system uncertainty measurements.Herein,a more reasonable method for measuring system uncertainty is developed based on rough set theory and the conception of information entropy;then a new algorithm is developed on the bases of the new system uncertainty measurement and the Skowron's algorithm for mining propositional default decision rules.The proposed algorithm is typically initiative-learning.It is well adaptable to system uncertainty.As shown by simulation experiments,its comprehensive performances are much better than those of congeneric algorithms.
Gradient Learning Algorithms for Ontology Computing
Gao, Wei; Zhu, Linli
2014-01-01
The gradient learning model has been raising great attention in view of its promising perspectives for applications in statistics, data dimensionality reducing, and other specific fields. In this paper, we raise a new gradient learning model for ontology similarity measuring and ontology mapping in multidividing setting. The sample error in this setting is given by virtue of the hypothesis space and the trick of ontology dividing operator. Finally, two experiments presented on plant and humanoid robotics field verify the efficiency of the new computation model for ontology similarity measure and ontology mapping applications in multidividing setting. PMID:25530752
Gradient Learning Algorithms for Ontology Computing
Directory of Open Access Journals (Sweden)
Wei Gao
2014-01-01
Full Text Available The gradient learning model has been raising great attention in view of its promising perspectives for applications in statistics, data dimensionality reducing, and other specific fields. In this paper, we raise a new gradient learning model for ontology similarity measuring and ontology mapping in multidividing setting. The sample error in this setting is given by virtue of the hypothesis space and the trick of ontology dividing operator. Finally, two experiments presented on plant and humanoid robotics field verify the efficiency of the new computation model for ontology similarity measure and ontology mapping applications in multidividing setting.
Optimization of deep learning algorithms for object classification
Horváth, András.
2017-02-01
Deep learning is currently the state of the art algorithm for image classification. The complexity of these feedforward neural networks have overcome a critical point, resulting algorithmic breakthroughs in various fields. On the other hand their complexity makes them executable in tasks, where High-throughput computing powers are available. The optimization of these networks -considering computational complexity and applicability on embedded systems- has not yet been studied and investigated in details. In this paper I show some examples how this algorithms can be optimized and accelerated on embedded systems.
Manifold learning based registration algorithms applied to multimodal images.
Azampour, Mohammad Farid; Ghaffari, Aboozar; Hamidinekoo, Azam; Fatemizadeh, Emad
2014-01-01
Manifold learning algorithms are proposed to be used in image processing based on their ability in preserving data structures while reducing the dimension and the exposure of data structure in lower dimension. Multi-modal images have the same structure and can be registered together as monomodal images if only structural information is shown. As a result, manifold learning is able to transform multi-modal images to mono-modal ones and subsequently do the registration using mono-modal methods. Based on this application, in this paper novel similarity measures are proposed for multi-modal images in which Laplacian eigenmaps are employed as manifold learning algorithm and are tested against rigid registration of PET/MR images. Results show the feasibility of using manifold learning as a way of calculating the similarity between multimodal images.
A noise tolerant fine tuning algorithm for the Naïve Bayesian learning algorithm
Directory of Open Access Journals (Sweden)
Khalil El Hindi
2014-07-01
Full Text Available This work improves on the FTNB algorithm to make it more tolerant to noise. The FTNB algorithm augments the Naïve Bayesian (NB learning algorithm with a fine-tuning stage in an attempt to find better estimations of the probability terms involved. The fine-tuning stage has proved to be effective in improving the classification accuracy of the NB; however, it makes the NB algorithm more sensitive to noise in a training set. This work presents several modifications of the fine tuning stage to make it more tolerant to noise. Our empirical results using 47 data sets indicate that the proposed methods greatly enhance the algorithm tolerance to noise. Furthermore, one of the proposed methods improved the performance of the fine tuning method on many noise-free data sets.
Learning Sorting Algorithms through Visualization Construction
Cetin, Ibrahim; Andrews-Larson, Christine
2016-01-01
Recent increased interest in computational thinking poses an important question to researchers: What are the best ways to teach fundamental computing concepts to students? Visualization is suggested as one way of supporting student learning. This mixed-method study aimed to (i) examine the effect of instruction in which students constructed…
ICAS：An Incremental Concept Acquisition System Using Attribute—Based Description
Institute of Scientific and Technical Information of China (English)
陈世福; 陈彬; 等
1992-01-01
ICAS is an incremental comcept acquistion system using attribute-based description.It includes an algorithm for leaming concept,which induces a rule set from an example set based on the probability theory,and an algorithm for refining the rule set.This paper also introduces the learning cycles.a very useful idea of ICAS.In fact,concept acquisition by ICAS is an incremental process consisting of many such learning cyeles.Also the design and implementation of ICAS are gieven.
Using animation to help students learn computer algorithms.
Catrambone, Richard; Seay, A Fleming
2002-01-01
This paper compares the effects of graphical study aids and animation on the problem-solving performance of students learning computer algorithms. Prior research has found inconsistent effects of animation on learning, and we believe this is partly attributable to animations not being designed to convey key information to learners. We performed an instructional analysis of the to-be-learned algorithms and designed the teaching materials based on that analysis. Participants studied stronger or weaker text-based information about the algorithm, and then some participants additionally studied still frames or an animation. Across 2 studies, learners who studied materials based on the instructional analysis tended to outperform other participants on both near and far transfer tasks. Animation also aided performance, particularly for participants who initially read the weaker text. These results suggest that animation might be added to curricula as a way of improving learning without needing revisions of existing texts and materials. Actual or potential applications of this research include the development of animations for learning complex systems as well as guidelines for determining when animations can aid learning.
Chen, Limin; Liang, Yin; Wan, Guojin
2012-04-01
An regularization approach is introduced into the online identification of inverse model for predistortion. It is based on a modified backpropagation Levenberg-Marquardt algorithm with sliding window. Adaptive predistorter with feedback was identified respectively based on direct learning and indirect learning architectures. Length of the sliding window was discussed. Compared with the Recursive Prediction Error Method (RPEM) algorithm and Nonlinear Filtered Least-Mean-Square (NFxLMS) algorithm, the algorithm is tested by identification of infinite impulse response Wiener predistorter. It is found that the proposed algorithm is much more efficient than either of the other techniques. The values of the parameters are also smaller than those extracted by the ordinary least-squares algorithm since the proposed algorithm constrains the L2-norm of the parameters.
Interactive Algorithms for Unsupervised Machine Learning
2015-06-01
Copetas, and Diane Stidle who greatly enriched my life at CMU. I am thankful to Zeeshan Syed and Eu-Jin Goh who supported me during my internship at Google...for a fun and productive internship . I am looking forward to spending another year at MSR and continuing to collaborate with and learn from everyone at...the nuclear norm minimization program to exactly 1As before this could equivalently be the column space with assumption on the maximal row coherence. 12
Cascade Error Projection: A Learning Algorithm for Hardware Implementation
Duong, Tuan A.; Daud, Taher
1996-01-01
In this paper, we workout a detailed mathematical analysis for a new learning algorithm termed Cascade Error Projection (CEP) and a general learning frame work. This frame work can be used to obtain the cascade correlation learning algorithm by choosing a particular set of parameters. Furthermore, CEP learning algorithm is operated only on one layer, whereas the other set of weights can be calculated deterministically. In association with the dynamical stepsize change concept to convert the weight update from infinite space into a finite space, the relation between the current stepsize and the previous energy level is also given and the estimation procedure for optimal stepsize is used for validation of our proposed technique. The weight values of zero are used for starting the learning for every layer, and a single hidden unit is applied instead of using a pool of candidate hidden units similar to cascade correlation scheme. Therefore, simplicity in hardware implementation is also obtained. Furthermore, this analysis allows us to select from other methods (such as the conjugate gradient descent or the Newton's second order) one of which will be a good candidate for the learning technique. The choice of learning technique depends on the constraints of the problem (e.g., speed, performance, and hardware implementation); one technique may be more suitable than others. Moreover, for a discrete weight space, the theoretical analysis presents the capability of learning with limited weight quantization. Finally, 5- to 8-bit parity and chaotic time series prediction problems are investigated; the simulation results demonstrate that 4-bit or more weight quantization is sufficient for learning neural network using CEP. In addition, it is demonstrated that this technique is able to compensate for less bit weight resolution by incorporating additional hidden units. However, generation result may suffer somewhat with lower bit weight quantization.
Teachers' Use of a Verbally Governed Algorithm and Student Learning
Keohane, Dolleen-Day; Greer, R. Douglas
2005-01-01
The effects of instructing teachers in the use of a verbally governed algorithm to solve students' learning problems were measured. The teachers were taught to analyze students' responses to instruction using a strategic protocol, which included a series of verbally governed questions. The study was designed to determine whether the instructional…
LAHS: A novel harmony search algorithm based on learning automata
Enayatifar, Rasul; Yousefi, Moslem; Abdullah, Abdul Hanan; Darus, Amer Nordin
2013-12-01
This study presents a learning automata-based harmony search (LAHS) for unconstrained optimization of continuous problems. The harmony search (HS) algorithm performance strongly depends on the fine tuning of its parameters, including the harmony consideration rate (HMCR), pitch adjustment rate (PAR) and bandwidth (bw). Inspired by the spur-in-time responses in the musical improvisation process, learning capabilities are employed in the HS to select these parameters based on spontaneous reactions. An extensive numerical investigation is conducted on several well-known test functions, and the results are compared with the HS algorithm and its prominent variants, including the improved harmony search (IHS), global-best harmony search (GHS) and self-adaptive global-best harmony search (SGHS). The numerical results indicate that the LAHS is more efficient in finding optimum solutions and outperforms the existing HS algorithm variants.
Face detection based on multiple kernel learning algorithm
Sun, Bo; Cao, Siming; He, Jun; Yu, Lejun
2016-09-01
Face detection is important for face localization in face or facial expression recognition, etc. The basic idea is to determine whether there is a face in an image or not, and also its location, size. It can be seen as a binary classification problem, which can be well solved by support vector machine (SVM). Though SVM has strong model generalization ability, it has some limitations, which will be deeply analyzed in the paper. To access them, we study the principle and characteristics of the Multiple Kernel Learning (MKL) and propose a MKL-based face detection algorithm. In the paper, we describe the proposed algorithm in the interdisciplinary research perspective of machine learning and image processing. After analyzing the limitation of describing a face with a single feature, we apply several ones. To fuse them well, we try different kernel functions on different feature. By MKL method, the weight of each single function is determined. Thus, we obtain the face detection model, which is the kernel of the proposed method. Experiments on the public data set and real life face images are performed. We compare the performance of the proposed algorithm with the single kernel-single feature based algorithm and multiple kernels-single feature based algorithm. The effectiveness of the proposed algorithm is illustrated. Keywords: face detection, feature fusion, SVM, MKL
Generalized SMO algorithm for SVM-based multitask learning.
Cai, Feng; Cherkassky, Vladimir
2012-06-01
Exploiting additional information to improve traditional inductive learning is an active research area in machine learning. In many supervised-learning applications, training data can be naturally separated into several groups, and incorporating this group information into learning may improve generalization. Recently, Vapnik proposed a general approach to formalizing such problems, known as "learning with structured data" and its support vector machine (SVM) based optimization formulation called SVM+. Liang and Cherkassky showed the connection between SVM+ and multitask learning (MTL) approaches in machine learning, and proposed an SVM-based formulation for MTL called SVM+MTL for classification. Training the SVM+MTL classifier requires the solution of a large quadratic programming optimization problem which scales as O(n(3)) with sample size n. So there is a need to develop computationally efficient algorithms for implementing SVM+MTL. This brief generalizes Platt's sequential minimal optimization (SMO) algorithm to the SVM+MTL setting. Empirical results show that, for typical SVM+MTL problems, the proposed generalized SMO achieves over 100 times speed-up, in comparison with general-purpose optimization routines.
AN ENHANCED PRE-PROCESSING RESEARCH FRAMEWORK FOR WEB LOG DATA USING A LEARNING ALGORITHM
Directory of Open Access Journals (Sweden)
V.V.R. Maheswara Rao
2011-01-01
Full Text Available With the continued growth and proliferation of Web services and Web based information systems, the volumes of user data have reached astronomical proportions. Before analyzing such data using web mining techniques, the web log has to be pre processed, integrated and transformed. As the World Wide Web is continuously and rapidly growing, it is necessary for the web miners to utilize intelligent tools in order to find, extract, filter and evaluate the desired information. The data pre-processing stage is the most important phase for investigation of the web user usage behaviour. To do this one must extract the only human user accesses from weblog data which is critical and complex. The web log is incremental in nature, thus conventional data pre-processing techniques were proved to be not suitable. Hence an extensive learning algorithm is required in order to get the desired information.This paper introduces an extensive research frame work capable of pre processing web log data completely and efficiently. The learning algorithm of proposed research frame work can separates human user and search engine accesses intelligently, with less time. In order to create suitable target data, the further essential tasks of pre-processing Data Cleansing, User Identification, Sessionization and Path Completion are designed collectively. The framework reduces the error rate and improves significant learning performance of the algorithm. The work ensures the goodness of split by using popular measures like Entropy and Gini index. This framework helps to investigate the web user usage behaviour efficiently. The experimental results proving this claim are given in this paper.
Learning Algorithm for a Brachiating Robot
Directory of Open Access Journals (Sweden)
Hideki Kajima
2003-01-01
Full Text Available This paper introduces a new concept of multi-locomotion robot inspired by an animal. The robot, ‘Gorilla Robot II’, can select the appropriate locomotion (from biped locomotion, quadruped locomotion and brachiation according to an environment or task. We consider ‘brachiation’ to be one of the most dynamic of animal motions. To develop a brachiation controller, architecture of the hierarchical behaviour-based controller, which consists of behaviour controllers and behaviour coordinators, was used. To achieve better brachiation, an enhanced learning method for motion control, adjusting the timing of the behaviour coordination, is proposed. Finally, it is shown that the developed robot successfully performs two types of brachiation and continuous locomotion.
Backpropagation Learning Algorithms for Email Classification.
Directory of Open Access Journals (Sweden)
*David Ndumiyana and Tarirayi Mukabeta
2016-07-01
Full Text Available Today email has become one the fastest and most effective form of communication. The popularity of this mode of transmitting goods, information and services has motivated spammers to perfect their technical skills to fool spam filters. This development has worsened the problems faced by Internet users as they have to deal with email congestion, email overload and unprioritised email messages. The result was an exponential increase in the number of email classification management tools for the past few decades. In this paper we propose a new spam classifier using a learning process of multilayer neural network to implement back propagation technique. Our contribution to the body of knowledge is the use of an improved empirical analysis to choose an optimum, novel collection of attributes of a user’s email contents that allows a quick detection of most important words in emails. We also demonstrate the effectiveness of two equal sets of emails training and testing data.
Learning sorting algorithms through visualization construction
Cetin, Ibrahim; Andrews-Larson, Christine
2016-01-01
Recent increased interest in computational thinking poses an important question to researchers: What are the best ways to teach fundamental computing concepts to students? Visualization is suggested as one way of supporting student learning. This mixed-method study aimed to (i) examine the effect of instruction in which students constructed visualizations on students' programming achievement and students' attitudes toward computer programming, and (ii) explore how this kind of instruction supports students' learning according to their self-reported experiences in the course. The study was conducted with 58 pre-service teachers who were enrolled in their second programming class. They expect to teach information technology and computing-related courses at the primary and secondary levels. An embedded experimental model was utilized as a research design. Students in the experimental group were given instruction that required students to construct visualizations related to sorting, whereas students in the control group viewed pre-made visualizations. After the instructional intervention, eight students from each group were selected for semi-structured interviews. The results showed that the intervention based on visualization construction resulted in significantly better acquisition of sorting concepts. However, there was no significant difference between the groups with respect to students' attitudes toward computer programming. Qualitative data analysis indicated that students in the experimental group constructed necessary abstractions through their engagement in visualization construction activities. The authors of this study argue that the students' active engagement in the visualization construction activities explains only one side of students' success. The other side can be explained through the instructional approach, constructionism in this case, used to design instruction. The conclusions and implications of this study can be used by researchers and
Energy Technology Data Exchange (ETDEWEB)
Bornholdt, S. [Heidelberg Univ., (Germany). Inst., fuer Theoretische Physik; Graudenz, D. [Lawrence Berkeley Lab., CA (United States)
1993-07-01
A learning algorithm based on genetic algorithms for asymmetric neural networks with an arbitrary structure is presented. It is suited for the learning of temporal patterns and leads to stable neural networks with feedback.
Chen, Hsinchun
1995-01-01
Presents an overview of artificial-intelligence-based inductive learning techniques and their use in information science research. Three methods are discussed: the connectionist Hopfield network; the symbolic ID3/ID5R; evolution-based genetic algorithms. The knowledge representations and algorithms of these methods are examined in the context of…
Chen, Hsinchun
1995-01-01
Presents an overview of artificial-intelligence-based inductive learning techniques and their use in information science research. Three methods are discussed: the connectionist Hopfield network; the symbolic ID3/ID5R; evolution-based genetic algorithms. The knowledge representations and algorithms of these methods are examined in the context of…
Enabling Incremental Query Re-Optimization
Liu, Mengmeng; Ives, Zachary G.; Loo, Boon Thau
2017-01-01
As declarative query processing techniques expand to the Web, data streams, network routers, and cloud platforms, there is an increasing need to re-plan execution in the presence of unanticipated performance changes. New runtime information may affect which query plan we prefer to run. Adaptive techniques require innovation both in terms of the algorithms used to estimate costs, and in terms of the search algorithm that finds the best plan. We investigate how to build a cost-based optimizer that recomputes the optimal plan incrementally given new cost information, much as a stream engine constantly updates its outputs given new data. Our implementation especially shows benefits for stream processing workloads. It lays the foundations upon which a variety of novel adaptive optimization algorithms can be built. We start by leveraging the recently proposed approach of formulating query plan enumeration as a set of recursive datalog queries; we develop a variety of novel optimization approaches to ensure effective pruning in both static and incremental cases. We further show that the lessons learned in the declarative implementation can be equally applied to more traditional optimizer implementations. PMID:28659658
Enabling Incremental Query Re-Optimization.
Liu, Mengmeng; Ives, Zachary G; Loo, Boon Thau
2016-01-01
As declarative query processing techniques expand to the Web, data streams, network routers, and cloud platforms, there is an increasing need to re-plan execution in the presence of unanticipated performance changes. New runtime information may affect which query plan we prefer to run. Adaptive techniques require innovation both in terms of the algorithms used to estimate costs, and in terms of the search algorithm that finds the best plan. We investigate how to build a cost-based optimizer that recomputes the optimal plan incrementally given new cost information, much as a stream engine constantly updates its outputs given new data. Our implementation especially shows benefits for stream processing workloads. It lays the foundations upon which a variety of novel adaptive optimization algorithms can be built. We start by leveraging the recently proposed approach of formulating query plan enumeration as a set of recursive datalog queries; we develop a variety of novel optimization approaches to ensure effective pruning in both static and incremental cases. We further show that the lessons learned in the declarative implementation can be equally applied to more traditional optimizer implementations.
Denoising of gravitational wave signals via dictionary learning algorithms
Torres-Forné, Alejandro; Marquina, Antonio; Font, José A.; Ibáñez, José M.
2016-12-01
Gravitational wave astronomy has become a reality after the historical detections accomplished during the first observing run of the two advanced LIGO detectors. In the following years, the number of detections is expected to increase significantly with the full commissioning of the advanced LIGO, advanced Virgo and KAGRA detectors. The development of sophisticated data analysis techniques to improve the opportunities of detection for low signal-to-noise-ratio events is, hence, a most crucial effort. In this paper, we present one such technique, dictionary-learning algorithms, which have been extensively developed in the last few years and successfully applied mostly in the context of image processing. However, to the best of our knowledge, such algorithms have not yet been employed to denoise gravitational wave signals. By building dictionaries from numerical relativity templates of both binary black holes mergers and bursts of rotational core collapse, we show how machine-learning algorithms based on dictionaries can also be successfully applied for gravitational wave denoising. We use a subset of signals from both catalogs, embedded in nonwhite Gaussian noise, to assess our techniques with a large sample of tests and to find the best model parameters. The application of our method to the actual signal GW150914 shows promising results. Dictionary-learning algorithms could be a complementary addition to the gravitational wave data analysis toolkit. They may be used to extract signals from noise and to infer physical parameters if the data are in good enough agreement with the morphology of the dictionary atoms.
Video game for learning and metaphorization of recursive algorithms
Directory of Open Access Journals (Sweden)
Ricardo Inacio Alvares Silva
2013-09-01
Full Text Available The learning of recursive algorithms in computer programming is problematic, because its execution and resolution is not natural to the thinking way people are trained and used to since young. As with other topics in algorithms, we use metaphors to make parallels between the abstract and the concrete to help in understanding the operation of recursive algorithms. However, the classic metaphors employed in this area, such as calculating factorial recursively and Towers of Hanoi game, may just confuse more or be insufficient. In this work, we produced a computer game to assist students in computer courses in learning recursive algorithms. It was designed to have regular video game characteristics, with narrative and classical gameplay elements, commonly found in this kind of product. Aiding to education occurs through metaphorization, or in other words, through experiences provided by game situations that refer to recursive algorithms. To this end, we designed and imbued in the game four valid metaphors related to the theory, and other minor references to the subject.
Comparison of machine learning algorithms for detecting coral reef
Directory of Open Access Journals (Sweden)
Eduardo Tusa
2014-09-01
Full Text Available (Received: 2014/07/31 - Accepted: 2014/09/23This work focuses on developing a fast coral reef detector, which is used for an autonomous underwater vehicle, AUV. A fast detection secures the AUV stabilization respect to an area of reef as fast as possible, and prevents devastating collisions. We use the algorithm of Purser et al. (2009 because of its precision. This detector has two parts: feature extraction that uses Gabor Wavelet filters, and feature classification that uses machine learning based on Neural Networks. Due to the extensive time of the Neural Networks, we exchange for a classification algorithm based on Decision Trees. We use a database of 621 images of coral reef in Belize (110 images for training and 511 images for testing. We implement the bank of Gabor Wavelets filters using C++ and the OpenCV library. We compare the accuracy and running time of 9 machine learning algorithms, whose result was the selection of the Decision Trees algorithm. Our coral detector performs 70ms of running time in comparison to 22s executed by the algorithm of Purser et al. (2009.
Computer aided lung cancer diagnosis with deep learning algorithms
Sun, Wenqing; Zheng, Bin; Qian, Wei
2016-03-01
Deep learning is considered as a popular and powerful method in pattern recognition and classification. However, there are not many deep structured applications used in medical imaging diagnosis area, because large dataset is not always available for medical images. In this study we tested the feasibility of using deep learning algorithms for lung cancer diagnosis with the cases from Lung Image Database Consortium (LIDC) database. The nodules on each computed tomography (CT) slice were segmented according to marks provided by the radiologists. After down sampling and rotating we acquired 174412 samples with 52 by 52 pixel each and the corresponding truth files. Three deep learning algorithms were designed and implemented, including Convolutional Neural Network (CNN), Deep Belief Networks (DBNs), Stacked Denoising Autoencoder (SDAE). To compare the performance of deep learning algorithms with traditional computer aided diagnosis (CADx) system, we designed a scheme with 28 image features and support vector machine. The accuracies of CNN, DBNs, and SDAE are 0.7976, 0.8119, and 0.7929, respectively; the accuracy of our designed traditional CADx is 0.7940, which is slightly lower than CNN and DBNs. We also noticed that the mislabeled nodules using DBNs are 4% larger than using traditional CADx, this might be resulting from down sampling process lost some size information of the nodules.
Advanced Machine learning Algorithm Application for Rotating Machine Health Monitoring
Energy Technology Data Exchange (ETDEWEB)
Kanemoto, Shigeru; Watanabe, Masaya [The University of Aizu, Aizuwakamatsu (Japan); Yusa, Noritaka [Tohoku University, Sendai (Japan)
2014-08-15
The present paper tries to evaluate the applicability of conventional sound analysis techniques and modern machine learning algorithms to rotating machine health monitoring. These techniques include support vector machine, deep leaning neural network, etc. The inner ring defect and misalignment anomaly sound data measured by a rotating machine mockup test facility are used to verify the above various kinds of algorithms. Although we cannot find remarkable difference of anomaly discrimination performance, some methods give us the very interesting eigen patterns corresponding to normal and abnormal states. These results will be useful for future more sensitive and robust anomaly monitoring technology.
Developing a Learning Algorithm-Generated Empirical Relaxer
Energy Technology Data Exchange (ETDEWEB)
Mitchell, Wayne [Univ. of Colorado, Boulder, CO (United States). Dept. of Applied Math; Kallman, Josh [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Toreja, Allen [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Gallagher, Brian [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Jiang, Ming [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Laney, Dan [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
2016-03-30
One of the main difficulties when running Arbitrary Lagrangian-Eulerian (ALE) simulations is determining how much to relax the mesh during the Eulerian step. This determination is currently made by the user on a simulation-by-simulation basis. We present a Learning Algorithm-Generated Empirical Relaxer (LAGER) which uses a regressive random forest algorithm to automate this decision process. We also demonstrate that LAGER successfully relaxes a variety of test problems, maintains simulation accuracy, and has the potential to significantly decrease both the person-hours and computational hours needed to run a successful ALE simulation.
An Educational System for Learning Search Algorithms and Automatically Assessing Student Performance
Grivokostopoulou, Foteini; Perikos, Isidoros; Hatzilygeroudis, Ioannis
2017-01-01
In this paper, first we present an educational system that assists students in learning and tutors in teaching search algorithms, an artificial intelligence topic. Learning is achieved through a wide range of learning activities. Algorithm visualizations demonstrate the operational functionality of algorithms according to the principles of active…
An Educational System for Learning Search Algorithms and Automatically Assessing Student Performance
Grivokostopoulou, Foteini; Perikos, Isidoros; Hatzilygeroudis, Ioannis
2017-01-01
In this paper, first we present an educational system that assists students in learning and tutors in teaching search algorithms, an artificial intelligence topic. Learning is achieved through a wide range of learning activities. Algorithm visualizations demonstrate the operational functionality of algorithms according to the principles of active…
Incremental Image Classification Method Based on Semi-Supervised Learning%基于半监督学习的增量图像分类方法
Institute of Scientific and Technical Information of China (English)
梁鹏; 黎绍发; 覃姜维; 罗剑高
2012-01-01
In order to use large numbers of unlabeled images effectively, an image classification method is proposed based on semi-supervised learning. The proposed method bridges a large amount of unlabeled images and limited numbers of labeled images by exploiting the common topics. The classification accuracy is improved by using the must-link constraint and cannot-link constraint of labeled images. The experimental results on Caltech-101 and 7-classes image dataset demonstrate that the classification accuracy improves about 10% by the proposed method. Furthermore, due to the present semi-supervised image classification methods lacking of incremental learning ability, an incremental implementation of our method is proposed. Comparing with non-incremental learning model in literature, the incrementallearning method improves the computation efficiency of nearly 90%.%为有效使用大量未标注的图像进行分类,提出一种基于半监督学习的图像分类方法.通过共同的隐含话题桥接少量已标注的图像和大量未标注的图像,利用已标注图像的Must-link约束和Cannot-link约束提高未标注图像分类的精度.实验结果表明,该方法有效提高Caltech-101数据集和7类图像集约10％的分类精度.此外,针对目前绝大部分半监督图像分类方法不具备增量学习能力这一缺点,提出该方法的增量学习模型.实验结果表明,增量学习模型相比无增量学习模型提高近90％的计算效率.
Alignment of Custom Standards by Machine Learning Algorithms
Directory of Open Access Journals (Sweden)
Adela Sirbu
2010-09-01
Full Text Available Building an efficient model for automatic alignment of terminologies would bring a significant improvement to the information retrieval process. We have developed and compared two machine learning based algorithms whose aim is to align 2 custom standards built on a 3 level taxonomy, using kNN and SVM classifiers that work on a vector representation consisting of several similarity measures. The weights utilized by the kNN were optimized with an evolutionary algorithm, while the SVM classifier's hyper-parameters were optimized with a grid search algorithm. The database used for train was semi automatically obtained by using the Coma++ tool. The performance of our aligners is shown by the results obtained on the test set.
An Analysis of Learning Algorithms in Complex Stochastic Environments
2007-06-01
speakers saying vowel phrases and resulted in a significant improvement in predictions during the refinement phase when contexts were added to the...with parameters for the agent, to both take actions and write the percepts it receives to a separate file. These two programs ran in tandem for...sensations, due to the recency threshold limiting the total number of percepts. A comparison of these two learning algorithms shows contrasting styles of
Towards the compression of parton densities through machine learning algorithms
Carrazza, Stefano
2016-01-01
One of the most fascinating challenges in the context of parton density function (PDF) is the determination of the best combined PDF uncertainty from individual PDF sets. Since 2014 multiple methodologies have been developed to achieve this goal. In this proceedings we first summarize the strategy adopted by the PDF4LHC15 recommendation and then, we discuss about a new approach to Monte Carlo PDF compression based on clustering through machine learning algorithms.
[A new algorithm for NIR modeling based on manifold learning].
Hong, Ming-Jian; Wen, Zhi-Yu; Zhang, Xiao-Hong; Wen, Quan
2009-07-01
Manifold learning is a new kind of algorithm originating from the field of machine learning to find the intrinsic dimensionality of numerous and complex data and to extract most important information from the raw data to develop a regression or classification model. The basic assumption of the manifold learning is that the high-dimensional data measured from the same object using some devices must reside on a manifold with much lower dimensions determined by a few properties of the object. While NIR spectra are characterized by their high dimensions and complicated band assignment, the authors may assume that the NIR spectra of the same kind of substances with different chemical concentrations should reside on a manifold with much lower dimensions determined by the concentrations, according to the above assumption. As one of the best known algorithms of manifold learning, locally linear embedding (LLE) further assumes that the underlying manifold is locally linear. So, every data point in the manifold should be a linear combination of its neighbors. Based on the above assumptions, the present paper proposes a new algorithm named least square locally weighted regression (LS-LWR), which is a kind of LWR with weights determined by the least squares instead of a predefined function. Then, the NIR spectra of glucose solutions with various concentrations are measured using a NIR spectrometer and LS-LWR is verified by predicting the concentrations of glucose solutions quantitatively. Compared with the existing algorithms such as principal component regression (PCR) and partial least squares regression (PLSR), the LS-LWR has better predictability measured by the standard error of prediction (SEP) and generates an elegant model with good stability and efficiency.
Behavioral Profiling of Scada Network Traffic Using Machine Learning Algorithms
2014-03-27
encryption [37]. As an alternative to traditional classification approaches, machine learning (ML) algorithms (e.g., Naı̈ve Bayes) have successfully used...systems, and conducting physical security surveys of remote sites. Eliminating possible backdoor entry into a SCADA network can be a daunting task...notify the master of an issue. Furthermore, SCADA protocols generally lack authentication and encryption due to operating requirements and use of
Optimization in Quaternion Dynamic Systems: Gradient, Hessian, and Learning Algorithms.
Xu, Dongpo; Xia, Yili; Mandic, Danilo P
2016-02-01
The optimization of real scalar functions of quaternion variables, such as the mean square error or array output power, underpins many practical applications. Solutions typically require the calculation of the gradient and Hessian. However, real functions of quaternion variables are essentially nonanalytic, which are prohibitive to the development of quaternion-valued learning systems. To address this issue, we propose new definitions of quaternion gradient and Hessian, based on the novel generalized Hamilton-real (GHR) calculus, thus making a possible efficient derivation of general optimization algorithms directly in the quaternion field, rather than using the isomorphism with the real domain, as is current practice. In addition, unlike the existing quaternion gradients, the GHR calculus allows for the product and chain rule, and for a one-to-one correspondence of the novel quaternion gradient and Hessian with their real counterparts. Properties of the quaternion gradient and Hessian relevant to numerical applications are also introduced, opening a new avenue of research in quaternion optimization and greatly simplified the derivations of learning algorithms. The proposed GHR calculus is shown to yield the same generic algorithm forms as the corresponding real- and complex-valued algorithms. Advantages of the proposed framework are illuminated over illustrative simulations in quaternion signal processing and neural networks.
On-line learning algorithms for locally recurrent neural networks.
Campolucci, P; Uncini, A; Piazza, F; Rao, B D
1999-01-01
This paper focuses on on-line learning procedures for locally recurrent neural networks with emphasis on multilayer perceptron (MLP) with infinite impulse response (IIR) synapses and its variations which include generalized output and activation feedback multilayer networks (MLN's). We propose a new gradient-based procedure called recursive backpropagation (RBP) whose on-line version, causal recursive backpropagation (CRBP), presents some advantages with respect to the other on-line training methods. The new CRBP algorithm includes as particular cases backpropagation (BP), temporal backpropagation (TBP), backpropagation for sequences (BPS), Back-Tsoi algorithm among others, thereby providing a unifying view on gradient calculation techniques for recurrent networks with local feedback. The only learning method that has been proposed for locally recurrent networks with no architectural restriction is the one by Back and Tsoi. The proposed algorithm has better stability and higher speed of convergence with respect to the Back-Tsoi algorithm, which is supported by the theoretical development and confirmed by simulations. The computational complexity of the CRBP is comparable with that of the Back-Tsoi algorithm, e.g., less that a factor of 1.5 for usual architectures and parameter settings. The superior performance of the new algorithm, however, easily justifies this small increase in computational burden. In addition, the general paradigms of truncated BPTT and RTRL are applied to networks with local feedback and compared with the new CRBP method. The simulations show that CRBP exhibits similar performances and the detailed analysis of complexity reveals that CRBP is much simpler and easier to implement, e.g., CRBP is local in space and in time while RTRL is not local in space.
New Iterative Learning Control Algorithms Based on Vector Plots Analysis1）
Institute of Scientific and Technical Information of China (English)
XIESheng-Li; TIANSen-Ping; XIEZhen-Dong
2004-01-01
Based on vector plots analysis, this paper researches the geometric frame of iterativelearning control method. New structure of iterative learning algorithms is obtained by analyzingthe vector plots of some general algorithms. The structure of the new algorithm is different fromthose of the present algorithms. It is of faster convergence speed and higher accuracy. Simulationspresented here illustrate the effectiveness and advantage of the new algorithm.
Sparse kernel learning with LASSO and Bayesian inference algorithm.
Gao, Junbin; Kwan, Paul W; Shi, Daming
2010-03-01
Kernelized LASSO (Least Absolute Selection and Shrinkage Operator) has been investigated in two separate recent papers [Gao, J., Antolovich, M., & Kwan, P. H. (2008). L1 LASSO and its Bayesian inference. In W. Wobcke, & M. Zhang (Eds.), Lecture notes in computer science: Vol. 5360 (pp. 318-324); Wang, G., Yeung, D. Y., & Lochovsky, F. (2007). The kernel path in kernelized LASSO. In International conference on artificial intelligence and statistics (pp. 580-587). San Juan, Puerto Rico: MIT Press]. This paper is concerned with learning kernels under the LASSO formulation via adopting a generative Bayesian learning and inference approach. A new robust learning algorithm is proposed which produces a sparse kernel model with the capability of learning regularized parameters and kernel hyperparameters. A comparison with state-of-the-art methods for constructing sparse regression models such as the relevance vector machine (RVM) and the local regularization assisted orthogonal least squares regression (LROLS) is given. The new algorithm is also demonstrated to possess considerable computational advantages. Copyright 2009 Elsevier Ltd. All rights reserved.
Exploration Of Deep Learning Algorithms Using Openacc Parallel Programming Model
Hamam, Alwaleed A.
2017-03-13
Deep learning is based on a set of algorithms that attempt to model high level abstractions in data. Specifically, RBM is a deep learning algorithm that used in the project to increase it\\'s time performance using some efficient parallel implementation by OpenACC tool with best possible optimizations on RBM to harness the massively parallel power of NVIDIA GPUs. GPUs development in the last few years has contributed to growing the concept of deep learning. OpenACC is a directive based ap-proach for computing where directives provide compiler hints to accelerate code. The traditional Restricted Boltzmann Ma-chine is a stochastic neural network that essentially perform a binary version of factor analysis. RBM is a useful neural net-work basis for larger modern deep learning model, such as Deep Belief Network. RBM parameters are estimated using an efficient training method that called Contrastive Divergence. Parallel implementation of RBM is available using different models such as OpenMP, and CUDA. But this project has been the first attempt to apply OpenACC model on RBM.
An augmented Lagrangian multi-scale dictionary learning algorithm
Directory of Open Access Journals (Sweden)
Ye Meng
2011-01-01
Full Text Available Abstract Learning overcomplete dictionaries for sparse signal representation has become a hot topic fascinated by many researchers in the recent years, while most of the existing approaches have a serious problem that they always lead to local minima. In this article, we present a novel augmented Lagrangian multi-scale dictionary learning algorithm (ALM-DL, which is achieved by first recasting the constrained dictionary learning problem into an AL scheme, and then updating the dictionary after each inner iteration of the scheme during which majorization-minimization technique is employed for solving the inner subproblem. Refining the dictionary from low scale to high makes the proposed method less dependent on the initial dictionary hence avoiding local optima. Numerical tests for synthetic data and denoising applications on real images demonstrate the superior performance of the proposed approach.
Institute of Scientific and Technical Information of China (English)
张冉
2011-01-01
随着3G网络的全面普及，手机广告目前已逐渐成为商家抢占市场的一种营销手段，但手机广告投放的精准性是目前比较突出的一个问题。本文介绍了BP神经网络以及AdaBoost算法的基本原理，研究了应用AdaBoost结合BP神经网络算法的增量学习模型，该模型基于用户历史点击记录来预测手机用户感兴趣的广告类别，以提高手机广告投放的精准度。%With the overall popularity of 3G networks,mobile advertising business has become a marketing tool to seize the market,but the precise nature of mobile advertising is a more prominent issue.This article describes the BP neural network and the basic principles of AdaBoost algorithm to study the application of BP neural network algorithm AdaBoost with incremental learning model that records based on user click history to predict the mobile phone users are interested in advertising categories,in order to improve the mobile advertising the accuracy.
A pruning algorithm with L1/2 regularizer for extreme learning machine
Institute of Scientific and Technical Information of China (English)
Ye-tian FAN; Wei WU; Wen-yu YANG; Qin-wei FAN; Jian WANG
2014-01-01
Compared with traditional learning methods such as the back propagation (BP) method, extreme learning machine provides much faster learning speed and needs less human intervention, and thus has been widely used. In this paper we combine the L1/2 regularization method with extreme learning machine to prune extreme learning machine. A variable learning coefficient is employed to prevent too large a learning increment. A numerical experiment demonstrates that a network pruned by L1/2 regularization has fewer hidden nodes but provides better performance than both the original network and the network pruned by L2 regularization.
Minimal Change and Bounded Incremental Parsing
Wiren, M
1994-01-01
Ideally, the time that an incremental algorithm uses to process a change should be a function of the size of the change rather than, say, the size of the entire current input. Based on a formalization of ``the set of things changed'' by an incremental modification, this paper investigates how and to what extent it is possible to give such a guarantee for a chart-based parsing framework and discusses the general utility of a minimality notion in incremental processing.
A Comparison of the Effects of K-Anonymity on Machine Learning Algorithms
Directory of Open Access Journals (Sweden)
Hayden Wimmer
2014-11-01
Full Text Available While research has been conducted in machine learning algorithms and in privacy preserving in data mining (PPDM, a gap in the literature exists which combines the aforementioned areas to determine how PPDM affects common machine learning algorithms. The aim of this research is to narrow this literature gap by investigating how a common PPDM algorithm, K-Anonymity, affects common machine learning and data mining algorithms, namely neural networks, logistic regression, decision trees, and Bayesian classifiers. This applied research reveals practical implications for applying PPDM to data mining and machine learning and serves as a critical first step learning how to apply PPDM to machine learning algorithms and the effects of PPDM on machine learning. Results indicate that certain machine learning algorithms are more suited for use with PPDM techniques.
Compressive tracking with incremental multivariate Gaussian distribution
Li, Dongdong; Wen, Gongjian; Zhu, Gao; Zeng, Qiaoling
2016-09-01
Various approaches have been proposed for robust visual tracking, among which compressive tracking (CT) yields promising performance. In CT, Haar-like features are efficiently extracted with a very sparse measurement matrix and modeled as an online updated naïve Bayes classifier to account for target appearance change. The naïve Bayes classifier ignores overlap between Haar-like features and assumes that Haar-like features are independently distributed, which leads to drift in complex scenario. To address this problem, we present an extended CT algorithm, which assumes that all Haar-like features are correlated with each other and have multivariate Gaussian distribution. The mean vector and covariance matrix of multivariate normal distribution are incrementally updated with constant computational complexity to adapt to target appearance change. Each frame is associated with a temporal weight to expend less modeling power on old observation. Based on temporal weight, an update scheme with changing but convergent learning rate is derived with strict mathematic proof. Compared with CT, our extended algorithm achieves a richer representation of target appearance. The incremental multivariate Gaussian distribution is integrated into the particle filter framework to achieve better tracking performance. Extensive experiments on the CVPR2013 tracking benchmark demonstrate that our proposed tracker achieves superior performance both qualitatively and quantitatively over several state-of-the-art trackers.
The threshold EM algorithm for parameter learning in bayesian network with incomplete data
Lamine, Fradj Ben; Mahjoub, Mohamed Ali
2012-01-01
Bayesian networks (BN) are used in a big range of applications but they have one issue concerning parameter learning. In real application, training data are always incomplete or some nodes are hidden. To deal with this problem many learning parameter algorithms are suggested foreground EM, Gibbs sampling and RBE algorithms. In order to limit the search space and escape from local maxima produced by executing EM algorithm, this paper presents a learning parameter algorithm that is a fusion of EM and RBE algorithms. This algorithm incorporates the range of a parameter into the EM algorithm. This range is calculated by the first step of RBE algorithm allowing a regularization of each parameter in bayesian network after the maximization step of the EM algorithm. The threshold EM algorithm is applied in brain tumor diagnosis and show some advantages and disadvantages over the EM algorithm.
Rough Set Assisted Meta-Learning Method to Select Learning Algorithms
Institute of Scientific and Technical Information of China (English)
Lisa Fan; Min-xiao Lei
2006-01-01
In this paper,we propose a Rough Set assisted Meta-Learning method on how to select the most-suited machine-learning algorithms with minimal effort for a new given dataset. A k-Nearest Neighbor (k-NN) algorithm is used to recognize the most similar datasets that have been performed by all of the candidate algorithms. By matching the most similar datasets we found,the corresponding performance of the candidate algorithms is used to generate recommendation to the user. The performance derives from a multi-criteria evaluation measure-ARR, which contains both accuracy and time. Furthermore, after applying Rough Set theory, we can find the redundant properties of the dataset. Thus,we can speed up the ranking process and increase the accuracy by using the reduct of the meta attributes.
Q-Learning-Based Adjustable Fixed-Phase Quantum Grover Search Algorithm
Guo, Ying; Shi, Wensha; Wang, Yijun; Hu, Jiankun
2017-02-01
We demonstrate that the rotation phase can be suitably chosen to increase the efficiency of the phase-based quantum search algorithm, leading to a dynamic balance between iterations and success probabilities of the fixed-phase quantum Grover search algorithm with Q-learning for a given number of solutions. In this search algorithm, the proposed Q-learning algorithm, which is a model-free reinforcement learning strategy in essence, is used for performing a matching algorithm based on the fraction of marked items λ and the rotation phase α. After establishing the policy function α = π(λ), we complete the fixed-phase Grover algorithm, where the phase parameter is selected via the learned policy. Simulation results show that the Q-learning-based Grover search algorithm (QLGA) enables fewer iterations and gives birth to higher success probabilities. Compared with the conventional Grover algorithms, it avoids the optimal local situations, thereby enabling success probabilities to approach one.
Fall detection using supervised machine learning algorithms: A comparative study
Zerrouki, Nabil
2017-01-05
Fall incidents are considered as the leading cause of disability and even mortality among older adults. To address this problem, fall detection and prevention fields receive a lot of intention over the past years and attracted many researcher efforts. We present in the current study an overall performance comparison between fall detection systems using the most popular machine learning approaches which are: Naïve Bayes, K nearest neighbor, neural network, and support vector machine. The analysis of the classification power associated to these most widely utilized algorithms is conducted on two fall detection databases namely FDD and URFD. Since the performance of the classification algorithm is inherently dependent on the features, we extracted and used the same features for all classifiers. The classification evaluation is conducted using different state of the art statistical measures such as the overall accuracy, the F-measure coefficient, and the area under ROC curve (AUC) value.
Machine learning based global particle indentification algorithms at LHCb experiment
Derkach, Denis; Likhomanenko, Tatiana; Rogozhnikov, Aleksei; Ratnikov, Fedor
2017-01-01
One of the most important aspects of data processing at LHC experiments is the particle identification (PID) algorithm. In LHCb, several different sub-detector systems provide PID information: the Ring Imaging CHerenkov (RICH) detector, the hadronic and electromagnetic calorimeters, and the muon chambers. To improve charged particle identification, several neural networks including a deep architecture and gradient boosting have been applied to data. These new approaches provide higher identification efficiencies than existing implementations for all charged particle types. It is also necessary to achieve a flat dependency between efficiencies and spectator variables such as particle momentum, in order to reduce systematic uncertainties during later stages of data analysis. For this purpose, "flat” algorithms that guarantee the flatness property for efficiencies have also been developed. This talk presents this new approach based on machine learning and its performance.
Institute of Scientific and Technical Information of China (English)
王伟
2015-01-01
Classification is an important research content of data mining. In this paper, a new incremental classification algorithm of multiple center vector base on minimun-distance is presented after analysising the existing methods on incremental classifica⁃tion algorithm of minimun-distance. In the method, first, cluster the training data according to class attribute ,then eliminate the overlap of class space by adjusting the space between classes, finally, incremental classification algorithm of multiple center vector base on minimun-distance is presented to classify incremental training data, reduce the selected number of representative sample. The experiments indicate that compare with the Algorithm from literature[14],the classification accuracy is basically the same, but the demand of storage space and the time complex decreased in different degree, it is significant for big data classification.%分类是数据挖掘的一项重要研究内容。在分析了现有分类方法后，提出了基于最小距离的多中心向量的增量分类算法。该方法首先按照属性类聚类训练样本，通过类间调整，消除类域空间重叠。针对增量分类，提出了多中心向量的分类算法，通过空间区域划分的方法，减少增量分类选取的代表样本数量。实验结果表明，与文献[14]提出的增量分类算法相比，分类精度近似相同，但所需时间复杂度和存储空间则有不同程度的下降，这对大数据的处理是具有重要意义的。
Understanding Neural Networks for Machine Learning using Microsoft Neural Network Algorithm
National Research Council Canada - National Science Library
Nagesh Ramprasad
2016-01-01
.... In this research, focus is on the Microsoft Neural System Algorithm. The Microsoft Neural System Algorithm is a simple implementation of the adaptable and popular neural networks that are used in the machine learning...
A study on the performance comparison of metaheuristic algorithms on the learning of neural networks
Lai, Kee Huong; Zainuddin, Zarita; Ong, Pauline
2017-08-01
The learning or training process of neural networks entails the task of finding the most optimal set of parameters, which includes translation vectors, dilation parameter, synaptic weights, and bias terms. Apart from the traditional gradient descent-based methods, metaheuristic methods can also be used for this learning purpose. Since the inception of genetic algorithm half a century ago, the last decade witnessed the explosion of a variety of novel metaheuristic algorithms, such as harmony search algorithm, bat algorithm, and whale optimization algorithm. Despite the proof of the no free lunch theorem in the discipline of optimization, a survey in the literature of machine learning gives contrasting results. Some researchers report that certain metaheuristic algorithms are superior to the others, whereas some others argue that different metaheuristic algorithms give comparable performance. As such, this paper aims to investigate if a certain metaheuristic algorithm will outperform the other algorithms. In this work, three metaheuristic algorithms, namely genetic algorithms, particle swarm optimization, and harmony search algorithm are considered. The algorithms are incorporated in the learning of neural networks and their classification results on the benchmark UCI machine learning data sets are compared. It is found that all three metaheuristic algorithms give similar and comparable performance, as captured in the average overall classification accuracy. The results corroborate the findings reported in the works done by previous researchers. Several recommendations are given, which include the need of statistical analysis to verify the results and further theoretical works to support the obtained empirical results.
Protein sequence classification with improved extreme learning machine algorithms.
Cao, Jiuwen; Xiong, Lianglin
2014-01-01
Precisely classifying a protein sequence from a large biological protein sequences database plays an important role for developing competitive pharmacological products. Comparing the unseen sequence with all the identified protein sequences and returning the category index with the highest similarity scored protein, conventional methods are usually time-consuming. Therefore, it is urgent and necessary to build an efficient protein sequence classification system. In this paper, we study the performance of protein sequence classification using SLFNs. The recent efficient extreme learning machine (ELM) and its invariants are utilized as the training algorithms. The optimal pruned ELM is first employed for protein sequence classification in this paper. To further enhance the performance, the ensemble based SLFNs structure is constructed where multiple SLFNs with the same number of hidden nodes and the same activation function are used as ensembles. For each ensemble, the same training algorithm is adopted. The final category index is derived using the majority voting method. Two approaches, namely, the basic ELM and the OP-ELM, are adopted for the ensemble based SLFNs. The performance is analyzed and compared with several existing methods using datasets obtained from the Protein Information Resource center. The experimental results show the priority of the proposed algorithms.
A MULTI-AGENT LOCAL-LEARNING ALGORITHM UNDER GROUP ENVIROMENT
Institute of Scientific and Technical Information of China (English)
Jiang Daoping; Yin Yixin; Ban Xiaojuan; Meng Xiangsong
2009-01-01
In this paper, a local-learning algorithm for multi-agent is presented based on the fact that individual agent performs local perception and local interaction under group environment. As for individual-learning, agent adopts greedy strategy to maximize its reward when interacting with environment. In group-learning, local interaction takes place between each two agents. A local-learning algorithm to choose and modify agents' actions is proposed to improve the traditional learning algorithm, respectively in the situations of zero-sum games and general-sum games with unique equilibrium or multi-equilibrium. And this local-learning algorithm is proved to be convergent and the computation complexity is lower than the NashAdditionally, through grid-game test, it is indicated that by using this local-learning algorithm, the local behaviors of agents can spread to globe.
Energy Technology Data Exchange (ETDEWEB)
Machado, Marcelo Dornellas; Schirru, Roberto [Universidade Federal, Rio de Janeiro, RJ (Brazil). Coordenacao dos Programas de Pos-graduacao de Engenharia. Programa de Engenharia Nuclear
2000-07-01
Genetic algorithms are biologically motivated adaptive systems which have been used, with good results, for combinatorial problems optimization. In this work, a new learning mode, to be used by the population-based incremental learning algorithm, has the aim to build a new evolutionary algorithm to be used in optimization of numerical problems and combinatorial problems. This new learning mode uses a variable learning rate during the optimization process, constituting a process known as proportional reward. The development of this new algorithm aims its application in the optimization of reload problem of PWR nuclear reactors, in order to increase the useful life of the nuclear fuel. For the test, two classes of problems are used: numerical problems and combinatorial problems. Due to the fact that the reload problem is a combinatorial problem, the major interest relies on the last class. The results achieved with the tests indicate the applicability of the new learning mode, showing its potential as a developing tool in the solution of reload problem. (author)
Pullback incremental attraction
Directory of Open Access Journals (Sweden)
Kloeden Peter E.
2014-01-01
Full Text Available A pullback incremental attraction, a nonautonomous version of incremental stability, is introduced for nonautonomous systems that may have unbounded limiting solutions. Its characterisation by a Lyapunov function is indicated
Storkel, Holly L.; Bontempo, Daniel E.; Aschenbrenner, Andrew J.; Maekawa, Junko; Lee, Su-Yeon
2013-01-01
Purpose: Phonotactic probability or neighborhood density has predominately been defined through the use of gross distinctions (i.e., low vs. high). In the current studies, the authors examined the influence of finer changes in probability (Experiment 1) and density (Experiment 2) on word learning. Method: The authors examined the full range of…
Storkel, Holly L.; Bontempo, Daniel E.; Aschenbrenner, Andrew J.; Maekawa, Junko; Lee, Su-Yeon
2013-01-01
Purpose: Phonotactic probability or neighborhood density has predominately been defined through the use of gross distinctions (i.e., low vs. high). In the current studies, the authors examined the influence of finer changes in probability (Experiment 1) and density (Experiment 2) on word learning. Method: The authors examined the full range of…
Incremental Distance Transforms (IDT)
Schouten, Theo E.; van den Broek, Egon; Erçil, A.; Çetin, M.; Boyer, K.; Lee, S.-W.
2010-01-01
A new generic scheme for incremental implementations of distance transforms (DT) is presented: Incremental Distance Transforms (IDT). This scheme is applied on the cityblock, Chamfer, and three recent exact Euclidean DT (E2DT). A benchmark shows that for all five DT, the incremental implementation r
A Locality-Constrained and Label Embedding Dictionary Learning Algorithm for Image Classification.
Zhengming Li; Zhihui Lai; Yong Xu; Jian Yang; Zhang, David
2017-02-01
Locality and label information of training samples play an important role in image classification. However, previous dictionary learning algorithms do not take the locality and label information of atoms into account together in the learning process, and thus their performance is limited. In this paper, a discriminative dictionary learning algorithm, called the locality-constrained and label embedding dictionary learning (LCLE-DL) algorithm, was proposed for image classification. First, the locality information was preserved using the graph Laplacian matrix of the learned dictionary instead of the conventional one derived from the training samples. Then, the label embedding term was constructed using the label information of atoms instead of the classification error term, which contained discriminating information of the learned dictionary. The optimal coding coefficients derived by the locality-based and label-based reconstruction were effective for image classification. Experimental results demonstrated that the LCLE-DL algorithm can achieve better performance than some state-of-the-art algorithms.
Chi-square Tests Driven Method for Learning the Structure of Factored MDPs
2012-01-01
SDYNA is a general framework designed to address large stochastic reinforcement learning problems. Unlike previous model based methods in FMDPs, it incrementally learns the structure and the parameters of a RL problem using supervised learning techniques. Then, it integrates decision-theoric planning algorithms based on FMDPs to compute its policy. SPITI is an instanciation of SDYNA that exploits ITI, an incremental decision tree algorithm, to learn the reward function and the Dynamic Bayesia...
IDEAL: Images Across Domains, Experiments, Algorithms and Learning
Ushizima, Daniela M.; Bale, Hrishikesh A.; Bethel, E. Wes; Ercius, Peter; Helms, Brett A.; Krishnan, Harinarayan; Grinberg, Lea T.; Haranczyk, Maciej; Macdowell, Alastair A.; Odziomek, Katarzyna; Parkinson, Dilworth Y.; Perciano, Talita; Ritchie, Robert O.; Yang, Chao
2016-09-01
Research across science domains is increasingly reliant on image-centric data. Software tools are in high demand to uncover relevant, but hidden, information in digital images, such as those coming from faster next generation high-throughput imaging platforms. The challenge is to analyze the data torrent generated by the advanced instruments efficiently, and provide insights such as measurements for decision-making. In this paper, we overview work performed by an interdisciplinary team of computational and materials scientists, aimed at designing software applications and coordinating research efforts connecting (1) emerging algorithms for dealing with large and complex datasets; (2) data analysis methods with emphasis in pattern recognition and machine learning; and (3) advances in evolving computer architectures. Engineering tools around these efforts accelerate the analyses of image-based recordings, improve reusability and reproducibility, scale scientific procedures by reducing time between experiments, increase efficiency, and open opportunities for more users of the imaging facilities. This paper describes our algorithms and software tools, showing results across image scales, demonstrating how our framework plays a role in improving image understanding for quality control of existent materials and discovery of new compounds.
IDEAL: Images Across Domains, Experiments, Algorithms and Learning
Ushizima, Daniela M.; Bale, Hrishikesh A.; Bethel, E. Wes; Ercius, Peter; Helms, Brett A.; Krishnan, Harinarayan; Grinberg, Lea T.; Haranczyk, Maciej; Macdowell, Alastair A.; Odziomek, Katarzyna; Parkinson, Dilworth Y.; Perciano, Talita; Ritchie, Robert O.; Yang, Chao
2016-11-01
Research across science domains is increasingly reliant on image-centric data. Software tools are in high demand to uncover relevant, but hidden, information in digital images, such as those coming from faster next generation high-throughput imaging platforms. The challenge is to analyze the data torrent generated by the advanced instruments efficiently, and provide insights such as measurements for decision-making. In this paper, we overview work performed by an interdisciplinary team of computational and materials scientists, aimed at designing software applications and coordinating research efforts connecting (1) emerging algorithms for dealing with large and complex datasets; (2) data analysis methods with emphasis in pattern recognition and machine learning; and (3) advances in evolving computer architectures. Engineering tools around these efforts accelerate the analyses of image-based recordings, improve reusability and reproducibility, scale scientific procedures by reducing time between experiments, increase efficiency, and open opportunities for more users of the imaging facilities. This paper describes our algorithms and software tools, showing results across image scales, demonstrating how our framework plays a role in improving image understanding for quality control of existent materials and discovery of new compounds.
Online Learning Algorithms for Stochastic Water-Filling
Gai, Yi
2011-01-01
Water-filling is the term for the classic solution to the problem of allocating constrained power to a set of parallel channels to maximize the total data-rate. It is used widely in practice, for example, for power allocation to sub-carriers in multi-user OFDM systems such as WiMax. The classic water-filling algorithm is deterministic and requires perfect knowledge of the channel gain to noise ratios. In this paper we consider how to do power allocation over stochastically time-varying (i.i.d.) channels with unknown gain to noise ratio distributions. We adopt an online learning framework based on stochastic multi-armed bandits. We consider two variations of the problem, one in which the goal is to find a power allocation to maximize $\\sum\\limits_i \\mathbb{E}[\\log(1 + SNR_i)]$, and another in which the goal is to find a power allocation to maximize $\\sum\\limits_i \\log(1 + \\mathbb{E}[SNR_i])$. For the first problem, we propose a \\emph{cognitive water-filling} algorithm that we call CWF1. We show that CWF1 obtai...
MODIS Aerosol Optical Depth Bias Adjustment Using Machine Learning Algorithms
Albayrak, A.; Wei, J. C.; Petrenko, M.; Lary, D. J.; Leptoukh, G. G.
2011-12-01
Over the past decade, global aerosol observations have been conducted by space-borne sensors, airborne instruments, and ground-base network measurements. Unfortunately, quite often we encounter the differences of aerosol measurements by different well-calibrated instruments, even with a careful collocation in time and space. The differences might be rather substantial, and need to be better understood and accounted for when merging data from many sensors. The possible causes for these differences come from instrumental bias, different satellite viewing geometries, calibration issues, dynamically changing atmospheric and the surface conditions, and other "regressors", resulting in random and systematic errors in the final aerosol products. In this study, we will concentrate on the subject of removing biases and the systematic errors from MODIS (both Terra and Aqua) aerosol product, using Machine Learning algorithms. While we are assessing our regressors in our system when comparing global aerosol products, the Aerosol Robotic Network of sun-photometers (AERONET) will be used as a baseline for evaluating the MODIS aerosol products (Dark Target for land and ocean, and Deep Blue retrieval algorithms). The results of bias adjustment for MODIS Terra and Aqua are planned to be incorporated into the AeroStat Giovanni as part of the NASA ACCESS funded AeroStat project.
Robust Background Subtraction with Incremental Eigen Models
Gritti, T.
2008-01-01
In this report we first describe a background subtraction algorithm based on the use of eigen space decomposition. We then present a method to achive incremental modelling, which allows for faster computation and saving in memory requirements. We discuss the performanceof the algorithm and the issu
An AdaBoost algorithm for multiclass semi-supervised learning
Tanha, J.; van Someren, M.; Afsarmanesh, H.; Zaki, M.J.; Siebes, A.; Yu, J.X.; Goethals, B.; Webb, G.; Wu, X.
2012-01-01
We present an algorithm for multiclass Semi-Supervised learning which is learning from a limited amount of labeled data and plenty of unlabeled data. Existing semi-supervised algorithms use approaches such as one-versus-all to convert the multiclass problem to several binary classification problems
Iterative learning control algorithm for spiking behavior of neuron model
Li, Shunan; Li, Donghui; Wang, Jiang; Yu, Haitao
2016-11-01
Controlling neurons to generate a desired or normal spiking behavior is the fundamental building block of the treatment of many neurologic diseases. The objective of this work is to develop a novel control method-closed-loop proportional integral (PI)-type iterative learning control (ILC) algorithm to control the spiking behavior in model neurons. In order to verify the feasibility and effectiveness of the proposed method, two single-compartment standard models of different neuronal excitability are specifically considered: Hodgkin-Huxley (HH) model for class 1 neural excitability and Morris-Lecar (ML) model for class 2 neural excitability. ILC has remarkable advantages for the repetitive processes in nature. To further highlight the superiority of the proposed method, the performances of the iterative learning controller are compared to those of classical PI controller. Either in the classical PI control or in the PI control combined with ILC, appropriate background noises are added in neuron models to approach the problem under more realistic biophysical conditions. Simulation results show that the controller performances are more favorable when ILC is considered, no matter which neuronal excitability the neuron belongs to and no matter what kind of firing pattern the desired trajectory belongs to. The error between real and desired output is much smaller under ILC control signal, which suggests ILC of neuron’s spiking behavior is more accurate.
Online State-Based Structured SVM Combined With Incremental PCA for Robust Visual Tracking.
Yin, Yingjie; Xu, De; Wang, Xingang; Bai, Mingran
2015-09-01
In this paper, we propose a robust state-based structured support vector machine (SVM) tracking algorithm combined with incremental principal component analysis (PCA). Different from the current structured SVM for tracking, our method directly learns and predicts the object's states and not the 2-D translation transformation during tracking. We define the object's virtual state to combine the state-based structured SVM and incremental PCA. The virtual state is considered as the most confident state of the object in every frame. The incremental PCA is used to update the virtual feature vector corresponding to the virtual state and the principal subspace of the object's feature vectors. In order to improve the accuracy of the prediction, all the feature vectors are projected onto the principal subspace in the learning and prediction process of the state-based structured SVM. Experimental results on several challenging video sequences validate the effectiveness and robustness of our approach.
An Improved Attention Parameter Setting Algorithm Based on Award Learning Mechanism
Institute of Scientific and Technical Information of China (English)
Fang Xiuduan; Liu Binhan; Wang Weizhi
2002-01-01
The setting of attention parameters plays a role in the performance of synergetic neural network based on PFAP model. This paper first analyzes the attention parameter setting algorithm based on award-penalty learning mechanism. Then, it presents an improved algorithm to overcome its drawbacks. The experimental results demonstrate that the novel algorithm is better than the original one under the same circumstances.
Directed Incremental Symbolic Execution
Person, Suzette; Yang, Guowei; Rungta, Neha; Khurshid, Sarfraz
2011-01-01
The last few years have seen a resurgence of interest in the use of symbolic execution -- a program analysis technique developed more than three decades ago to analyze program execution paths. Scaling symbolic execution and other path-sensitive analysis techniques to large systems remains challenging despite recent algorithmic and technological advances. An alternative to solving the problem of scalability is to reduce the scope of the analysis. One approach that is widely studied in the context of regression analysis is to analyze the differences between two related program versions. While such an approach is intuitive in theory, finding efficient and precise ways to identify program differences, and characterize their effects on how the program executes has proved challenging in practice. In this paper, we present Directed Incremental Symbolic Execution (DiSE), a novel technique for detecting and characterizing the effects of program changes. The novelty of DiSE is to combine the efficiencies of static analysis techniques to compute program difference information with the precision of symbolic execution to explore program execution paths and generate path conditions affected by the differences. DiSE is a complementary technique to other reduction or bounding techniques developed to improve symbolic execution. Furthermore, DiSE does not require analysis results to be carried forward as the software evolves -- only the source code for two related program versions is required. A case-study of our implementation of DiSE illustrates its effectiveness at detecting and characterizing the effects of program changes.
Institute of Scientific and Technical Information of China (English)
杨涛; 张生虎; 高洪明; 吴林; 许可望; 刘永贞
2013-01-01
Plasma-MIG复合电弧焊接对电源的外特性输出及焊接过程控制有着很高的要求,以VC++软件开发工具为平台,推导了适合于Plasma-MIG复合电弧焊接的增量型PID控制算法,实现了对复合电弧焊接过程控制及电源外特性的要求.结果表明,增量型PID恒流恒压控制能够满足Plasma-MIG对电源外特性的输出要求.Plasma电弧和MIG电弧并不是相互独立的,两者以共享的电磁空间、导电气氛和焊丝为媒介建立起耦合关系.Plasma-MIG复合电弧焊接过程中,增量型PID控制下的Plasma电弧能够自发的调节自身电参数,来稳定电弧空间的电流密度,使得焊接过程中无飞溅.采用控制后,Plasma-MIG复合电弧焊焊接过程焊缝铺展好,焊接过程稳定,焊缝成形好.%Output characteristics of the power supply and welding process control are important factors for plasma-MIG hybrid arc welding. PID increment control algorithm suitable for Plasma-MIG hybrid arc welding was developed based on VC + + language in this paper, which optimized the output characteristics of the power supply and welding process control. The results show that the plasma arc and MIG arc were coupled with each other by sharing the electro-magnetic space, gas and filler metal. Plasma are controlled by PID increment control algorithm was capable of stabilizing the current density through the arc due to its self-adjusting function, without sputtering in the welding process. High stability, molten metal with excellent liquidity and weld with smooth surface were realized by plasma-MIG hybrid arc welding with PID increment control algorithm.
Construction of a new adaptive wavelet network and its learning algorithm
Institute of Scientific and Technical Information of China (English)
无
2001-01-01
A new adaptive learning algorithm for constructing and training wavelet networks is proposed based on the time-frequency localization properties of wavelet frames and the adaptive projection algorithm. The exponential convergence of the adaptive projection algorithm in finite-dimensional Hilbert spaces is constructively proved, with exponential decay ratios given with high accuracy. The learning algorithm can sufficiently utilize the time-frequency information contained in the training data, iteratively determines the number of the hidden layer nodes and the weights of wavelet networks, and solves the problem of structure optimization of wavelet networks. The algorithm is simple and efficient, as illustrated by examples of signal representation and denoising.
Institute of Scientific and Technical Information of China (English)
柴宏祥; 曲凯; 赵芳
2011-01-01
Aiming at large difference in understanding the conception and elements of direct incremental cost in green building water-saving projects between the government and developers as well as lack of a unified calculation method in China, the definition, calculation principle, components and algorithm of incremental cost in green building water-saving project are proposed and verified through the water-saving demonstration project in a green building residential area in western China.%针对我国政府和开发商对绿色建筑节水项目直接增量成本的概念、构成要素等理解差异较大,缺乏统一的计算方法的现状,提出了绿色建筑节水项目直接增量成本定义、计算原则、构成内容及其计算方法,并以西部某绿色建筑小区节水示范项目为例进行验证.
Huang, Yin; Chen, Jianhua; Xiong, Shaojun
2009-07-01
Mobile-Learning (M-learning) makes many learners get the advantages of both traditional learning and E-learning. Currently, Web-based Mobile-Learning Systems have created many new ways and defined new relationships between educators and learners. Association rule mining is one of the most important fields in data mining and knowledge discovery in databases. Rules explosion is a serious problem which causes great concerns, as conventional mining algorithms often produce too many rules for decision makers to digest. Since Web-based Mobile-Learning System collects vast amounts of student profile data, data mining and knowledge discovery techniques can be applied to find interesting relationships between attributes of learners, assessments, the solution strategies adopted by learners and so on. Therefore ,this paper focus on a new data-mining algorithm, combined with the advantages of genetic algorithm and simulated annealing algorithm , called ARGSA(Association rules based on an improved Genetic Simulated Annealing Algorithm), to mine the association rules. This paper first takes advantage of the Parallel Genetic Algorithm and Simulated Algorithm designed specifically for discovering association rules. Moreover, the analysis and experiment are also made to show the proposed method is superior to the Apriori algorithm in this Mobile-Learning system.
Institute of Scientific and Technical Information of China (English)
吴强; 韩震宇; 李程
2013-01-01
In order to improve the control precision of brushless DC motor,using TI TMS320LF2407A as the control chip, a digital incremental PID algorithm and PWM control technology. This paper describes the principle of PID algorithm, PWM speed control principle and system hardware block diagram, software flow chart and draw the conclusion that PID algorithm has great superiority in the brushless DC motor speed control .% 为了提高无刷直流电机转速控制精度，系统选用了 TI 公司 TMS320LF2407A 为控制芯片，采用数字式增量 PID 算法和PWM控制技术。叙述了PID算法原理、PWM调速控制原理以及系统硬件原理框图、软件流程框图，并得出实验结论，证明PID算法在无刷直流电机调速过程中的优越性。
Singh, R.; Verma, H. K.
2013-12-01
This paper presents a teaching-learning-based optimization (TLBO) algorithm to solve parameter identification problems in the designing of digital infinite impulse response (IIR) filter. TLBO based filter modelling is applied to calculate the parameters of unknown plant in simulations. Unlike other heuristic search algorithms, TLBO algorithm is an algorithm-specific parameter-less algorithm. In this paper big bang-big crunch (BB-BC) optimization and PSO algorithms are also applied to filter design for comparison. Unknown filter parameters are considered as a vector to be optimized by these algorithms. MATLAB programming is used for implementation of proposed algorithms. Experimental results show that the TLBO is more accurate to estimate the filter parameters than the BB-BC optimization algorithm and has faster convergence rate when compared to PSO algorithm. TLBO is used where accuracy is more essential than the convergence speed.
Chen, S; Wu, Y; Luk, B L
1999-01-01
The paper presents a two-level learning method for radial basis function (RBF) networks. A regularized orthogonal least squares (ROLS) algorithm is employed at the lower level to construct RBF networks while the two key learning parameters, the regularization parameter and the RBF width, are optimized using a genetic algorithm (GA) at the upper level. Nonlinear time series modeling and prediction is used as an example to demonstrate the effectiveness of this hierarchical learning approach.
Institute of Scientific and Technical Information of China (English)
陆晓华; 左洪福; 蔡景
2013-01-01
The maintenance of an aero-engine usually includes three levels ,and the maintenance cost and period greatly differ depending on the different maintenance levels .To plan a reasonable maintenance budget program , airlines would like to predict the maintenance level of aero-engine before repairing in terms of performance parame-ters ,which can provide more economic benefits .The maintenance level decision rules are mined using the histori-cal maintenance data of a civil aero-engine based on the rough set theory ,and a variety of possible models of upda-ting rules produced by newly increased maintenance cases added to the historical maintenance case database are in-vestigated by the means of incremental machine learning .The continuously updated rules can provide reasonable guidance suggestions for engineers and decision support for planning a maintenance budget program before repai-ring .The results of an example show that the decision rules become more typical and robust ,and they are more accurate to predict the maintenance level of an aero-engine module as the maintenance data increase ,which illus-trates the feasibility of the represented method .
Efficient generation of image chips for training deep learning algorithms
Han, Sanghui; Fafard, Alex; Kerekes, John; Gartley, Michael; Ientilucci, Emmett; Savakis, Andreas; Law, Charles; Parhan, Jason; Turek, Matt; Fieldhouse, Keith; Rovito, Todd
2017-05-01
Training deep convolutional networks for satellite or aerial image analysis often requires a large amount of training data. For a more robust algorithm, training data need to have variations not only in the background and target, but also radiometric variations in the image such as shadowing, illumination changes, atmospheric conditions, and imaging platforms with different collection geometry. Data augmentation is a commonly used approach to generating additional training data. However, this approach is often insufficient in accounting for real world changes in lighting, location or viewpoint outside of the collection geometry. Alternatively, image simulation can be an efficient way to augment training data that incorporates all these variations, such as changing backgrounds, that may be encountered in real data. The Digital Imaging and Remote Sensing Image Image Generation (DIRSIG) model is a tool that produces synthetic imagery using a suite of physics-based radiation propagation modules. DIRSIG can simulate images taken from different sensors with variation in collection geometry, spectral response, solar elevation and angle, atmospheric models, target, and background. Simulation of Urban Mobility (SUMO) is a multi-modal traffic simulation tool that explicitly models vehicles that move through a given road network. The output of the SUMO model was incorporated into DIRSIG to generate scenes with moving vehicles. The same approach was used when using helicopters as targets, but with slight modifications. Using the combination of DIRSIG and SUMO, we quickly generated many small images, with the target at the center with different backgrounds. The simulations generated images with vehicles and helicopters as targets, and corresponding images without targets. Using parallel computing, 120,000 training images were generated in about an hour. Some preliminary results show an improvement in the deep learning algorithm when real image training data are augmented with
Modeling the Swift BAT Trigger Algorithm with Machine Learning
Graff, Philip B.; Lien, Amy Y.; Baker, John G.; Sakamoto, Takanori
2015-01-01
To draw inferences about gamma-ray burst (GRB) source populations based on Swift observations, it is essential to understand the detection efficiency of the Swift burst alert telescope (BAT). This study considers the problem of modeling the Swift BAT triggering algorithm for long GRBs, a computationally expensive procedure, and models it using machine learning algorithms. A large sample of simulated GRBs from Lien et al. (2014) is used to train various models: random forests, boosted decision trees (with AdaBoost), support vector machines, and artificial neural networks. The best models have accuracies of approximately greater than 97% (approximately less than 3% error), which is a significant improvement on a cut in GRB flux which has an accuracy of 89:6% (10:4% error). These models are then used to measure the detection efficiency of Swift as a function of redshift z, which is used to perform Bayesian parameter estimation on the GRB rate distribution. We find a local GRB rate density of eta(sub 0) approximately 0.48(+0.41/-0.23) Gpc(exp -3) yr(exp -1) with power-law indices of eta(sub 1) approximately 1.7(+0.6/-0.5) and eta(sub 2) approximately -5.9(+5.7/-0.1) for GRBs above and below a break point of z(sub 1) approximately 6.8(+2.8/-3.2). This methodology is able to improve upon earlier studies by more accurately modeling Swift detection and using this for fully Bayesian model fitting. The code used in this is analysis is publicly available online.
Modeling the Swift Bat Trigger Algorithm with Machine Learning
Graff, Philip B.; Lien, Amy Y.; Baker, John G.; Sakamoto, Takanori
2016-01-01
To draw inferences about gamma-ray burst (GRB) source populations based on Swift observations, it is essential to understand the detection efficiency of the Swift burst alert telescope (BAT). This study considers the problem of modeling the Swift / BAT triggering algorithm for long GRBs, a computationally expensive procedure, and models it using machine learning algorithms. A large sample of simulated GRBs from Lien et al. is used to train various models: random forests, boosted decision trees (with AdaBoost), support vector machines, and artificial neural networks. The best models have accuracies of greater than or equal to 97 percent (less than or equal to 3 percent error), which is a significant improvement on a cut in GRB flux, which has an accuracy of 89.6 percent (10.4 percent error). These models are then used to measure the detection efficiency of Swift as a function of redshift z, which is used to perform Bayesian parameter estimation on the GRB rate distribution. We find a local GRB rate density of n (sub 0) approaching 0.48 (sup plus 0.41) (sub minus 0.23) per cubic gigaparsecs per year with power-law indices of n (sub 1) approaching 1.7 (sup plus 0.6) (sub minus 0.5) and n (sub 2) approaching minus 5.9 (sup plus 5.7) (sub minus 0.1) for GRBs above and below a break point of z (redshift) (sub 1) approaching 6.8 (sup plus 2.8) (sub minus 3.2). This methodology is able to improve upon earlier studies by more accurately modeling Swift detection and using this for fully Bayesian model fitting.
2010-01-01
Back-propagation with gradient method is the most popular learning algorithm for feed-forward neural networks. However, it is critical to determine a proper fixed learning rate for the algorithm. In this paper, an optimized recursive algorithm is presented for online learning based on matrix operation and optimization methods analytically, which can avoid the trouble to select a proper learning rate for the gradient method. The proof of weak convergence of the proposed algorithm also is given...
Incremental Training for SVM-Based Classification with Keyword Adjusting
Institute of Scientific and Technical Information of China (English)
SUN Jin-wen; YANG Jian-wu; LU Bin; XIAO Jian-guo
2004-01-01
This paper analyzed the theory of incremental learning of SVM (support vector machine) and pointed out it is a shortage that the support vector optimization is only considered in present research of SVM incremental learning.According to the significance of keyword in training, a new incremental training method considering keyword adjusting was proposed, which eliminates the difference between incremental learning and batch learning through the keyword adjusting.The experimental results show that the improved method outperforms the method without the keyword adjusting and achieve the same precision as the batch method.
Efficient Grammar Induction Algorithm with Parse Forests from Real Corpora
Kurihara, Kenichi; Kameya, Yoshitaka; Sato, Taisuke
The task of inducing grammar structures has received a great deal of attention. The reasons why researchers have studied are different; to use grammar induction as the first stage in building large treebanks or to make up better language models. However, grammar induction has inherent computational complexity. To overcome it, some grammar induction algorithms add new production rules incrementally. They refine the grammar while keeping their computational complexity low. In this paper, we propose a new efficient grammar induction algorithm. Although our algorithm is similar to algorithms which learn a grammar incrementally, our algorithm uses the graphical EM algorithm instead of the Inside-Outside algorithm. We report results of learning experiments in terms of learning speeds. The results show that our algorithm learns a grammar in constant time regardless of the size of the grammar. Since our algorithm decreases syntactic ambiguities in each step, our algorithm reduces required time for learning. This constant-time learning considerably affects learning time for larger grammars. We also reports results of evaluation of criteria to choose nonterminals. Our algorithm refines a grammar based on a nonterminal in each step. Since there can be several criteria to decide which nonterminal is the best, we evaluate them by learning experiments.
Effective and efficient optics inspection approach using machine learning algorithms
Energy Technology Data Exchange (ETDEWEB)
Abdulla, G; Kegelmeyer, L; Liao, Z; Carr, W
2010-11-02
The Final Optics Damage Inspection (FODI) system automatically acquires and utilizes the Optics Inspection (OI) system to analyze images of the final optics at the National Ignition Facility (NIF). During each inspection cycle up to 1000 images acquired by FODI are examined by OI to identify and track damage sites on the optics. The process of tracking growing damage sites on the surface of an optic can be made more effective by identifying and removing signals associated with debris or reflections. The manual process to filter these false sites is daunting and time consuming. In this paper we discuss the use of machine learning tools and data mining techniques to help with this task. We describe the process to prepare a data set that can be used for training and identifying hardware reflections in the image data. In order to collect training data, the images are first automatically acquired and analyzed with existing software and then relevant features such as spatial, physical and luminosity measures are extracted for each site. A subset of these sites is 'truthed' or manually assigned a class to create training data. A supervised classification algorithm is used to test if the features can predict the class membership of new sites. A suite of self-configuring machine learning tools called 'Avatar Tools' is applied to classify all sites. To verify, we used 10-fold cross correlation and found the accuracy was above 99%. This substantially reduces the number of false alarms that would otherwise be sent for more extensive investigation.
Institute of Scientific and Technical Information of China (English)
袁向荣
2014-01-01
Precise encoder and grating ruler are often used to measure and position in CNC system. In indexable inserts peripher-al grinding CNC system,incremental grating encoder was applied to measure displacement for the blade feed axis because this axis re-turned to the reference point in a single direction. For the grinding wheel axis,an incremental grating encoder with distance-coded was used to determine absolute position after the system was powered. High-speed finding-zero algorithm based on distance-coding made au-to-finding-zero into reality. Besides,the algorithm itself was very simple. The experimental results indicate that the proposed method has its prominent superiorities in speed,accuracy over the ordinary incremental encoders and can meet the requirements of precise mo-tion contro1 in CNC system,which means it has high practical value.%数控系统常采用高精度的编码器和光栅尺进行位移测量和定位。在可转位刀片周边磨削数控系统中，刀片进给轴上电后需回参考点，但回参考点的方向是唯一的，因此采用增量式光栅编码器进行位置检测；对于上电需要确定绝对位置的砂轮摆动轴，采用一种带距离编码的增量式光栅编码器，利用距离编码的快速找零算法，在砂轮摆动轴实现了自动找零，而算法本身非常简单。实验结果表明：该找零方法在快速性、精确性等方面比一般增量式光栅编码器具有突出的优势，能够达到数控系统高精度运动控制的要求，具有较高的应用价值。
Design of Learning Model of Logic and Algorithms Based on APOS Theory
Hartati, Sulis Janu
2014-01-01
This research questions were "how do the characteristics of learning model of logic & algorithm according to APOS theory" and "whether or not these learning model can improve students learning outcomes". This research was conducted by exploration, and quantitative approach. Exploration used in constructing theory about the…
A Coupled User Clustering Algorithm Based on Mixed Data for Web-Based Learning Systems
Directory of Open Access Journals (Sweden)
Ke Niu
2015-01-01
Full Text Available In traditional Web-based learning systems, due to insufficient learning behaviors analysis and personalized study guides, a few user clustering algorithms are introduced. While analyzing the behaviors with these algorithms, researchers generally focus on continuous data but easily neglect discrete data, each of which is generated from online learning actions. Moreover, there are implicit coupled interactions among the data but are frequently ignored in the introduced algorithms. Therefore, a mass of significant information which can positively affect clustering accuracy is neglected. To solve the above issues, we proposed a coupled user clustering algorithm for Wed-based learning systems by taking into account both discrete and continuous data, as well as intracoupled and intercoupled interactions of the data. The experiment result in this paper demonstrates the outperformance of the proposed algorithm.
Self-adaptive learning based discrete differential evolution algorithm for solving CJWTA problem
Institute of Scientific and Technical Information of China (English)
Yu Xue; Yi Zhuang; Tianquan Ni; Siru Ni; Xuezhi Wen
2014-01-01
Cooperative jamming weapon-target assignment (CJWTA) problem is a key issue in electronic countermeasures (ECM). Some symbols which relevant to the CJWTA are defined firstly. Then, a formulation of jamming fitness is presented. Final y, a model of the CJWTA problem is constructed. In order to solve the CJWTA problem efficiently, a self-adaptive learning based discrete differential evolution (SLDDE) algorithm is proposed by introduc-ing a self-adaptive learning mechanism into the traditional discrete differential evolution algorithm. The SLDDE algorithm steers four candidate solution generation strategies simultaneously in the framework of the self-adaptive learning mechanism. Computa-tional simulations are conducted on ten test instances of CJWTA problem. The experimental results demonstrate that the proposed SLDDE algorithm not only can generate better results than only one strategy based discrete differential algorithms, but also outper-forms two algorithms which are proposed recently for the weapon-target assignment problems.
A New Method for Intrusion Detection using Manifold Learning Algorithm
Directory of Open Access Journals (Sweden)
Guoping Hou
2013-07-01
Full Text Available Computer and network security has received and will still receive much attention. Any unexpected intrusion will damage the network. It is therefore imperative to detect the network intrusion to ensure the normal operation of the internet. There are many studies in the intrusion detection and intrusion patter recognition. The artificial neural network (ANN has proven to be powerful for the intrusion detection. However, very little work has discussed the optimization of the input intrusion features for the ANN. Generally, the intrusion features contain a certain number of useless features, which is useless for the intrusion detection. Large dimensions of the feature data will also affect the intrusion detection performance of the ANN. In order to improve the ANN performance, a new approach for network intrusion detection based on nonlinear feature dimension reduction and ANN is proposed in this work. The manifold learning algorithm was used to reduce the intrusion feature vector. Then an ANN classifier was employed to identify the intrusion. The efficiency of the proposed method was evaluated with the real intrusion data. The test result shows that the proposed approach has good intrusion detection performance.
A rank-based Prediction Algorithm of Learning User's Intention
Shen, Jie; Gao, Ying; Chen, Cang; Gong, HaiPing
Internet search has become an important part in people's daily life. People can find many types of information to meet different needs through search engines on the Internet. There are two issues for the current search engines: first, the users should predetermine the types of information they want and then change to the appropriate types of search engine interfaces. Second, most search engines can support multiple kinds of search functions, each function has its own separate search interface. While users need different types of information, they must switch between different interfaces. In practice, most queries are corresponding to various types of information results. These queries can search the relevant results in various search engines, such as query "Palace" contains the websites about the introduction of the National Palace Museum, blog, Wikipedia, some pictures and video information. This paper presents a new aggregative algorithm for all kinds of search results. It can filter and sort the search results by learning three aspects about the query words, search results and search history logs to achieve the purpose of detecting user's intention. Experiments demonstrate that this rank-based method for multi-types of search results is effective. It can meet the user's search needs well, enhance user's satisfaction, provide an effective and rational model for optimizing search engines and improve user's search experience.
New Dandelion Algorithm Optimizes Extreme Learning Machine for Biomedical Classification Problems
Directory of Open Access Journals (Sweden)
Xiguang Li
2017-01-01
Full Text Available Inspired by the behavior of dandelion sowing, a new novel swarm intelligence algorithm, namely, dandelion algorithm (DA, is proposed for global optimization of complex functions in this paper. In DA, the dandelion population will be divided into two subpopulations, and different subpopulations will undergo different sowing behaviors. Moreover, another sowing method is designed to jump out of local optimum. In order to demonstrate the validation of DA, we compare the proposed algorithm with other existing algorithms, including bat algorithm, particle swarm optimization, and enhanced fireworks algorithm. Simulations show that the proposed algorithm seems much superior to other algorithms. At the same time, the proposed algorithm can be applied to optimize extreme learning machine (ELM for biomedical classification problems, and the effect is considerable. At last, we use different fusion methods to form different fusion classifiers, and the fusion classifiers can achieve higher accuracy and better stability to some extent.
A fast learning algorithm of neural network with tunable activation function
Institute of Scientific and Technical Information of China (English)
SHEN Yanjun; WANG Bingwen
2004-01-01
This paper presents a modified structure of a neural network with tunable activation function and provides a new learning algorithm for the neural network training. Simulation results of XOR problem, Feigenbaum function, and Henon map show that the new algorithm has better performance than BP (back propagation) algorithm in terms of shorter convergence time and higher convergence accuracy. Further modifications of the structure of the neural network with the faster learning algorithm demonstrate simpler structure with even faster convergence speed and better convergence accuracy.
Lile, Joshua A; Wesley, Michael J; Kelly, Thomas H; Hays, Lon R
2016-04-01
The aim of the present study was to examine a potential mechanism of action of gabapentin to manage cannabis-use disorders by determining the interoceptive effects of gabapentin in cannabis users discriminating [INCREMENT]-tetrahydrocannabinol ([INCREMENT]-THC) using a pharmacologically selective drug-discrimination procedure. Eight cannabis users learned to discriminate 30 mg oral [INCREMENT]-THC from placebo and then received gabapentin (600 and 1200 mg), [INCREMENT]-THC (5, 15, and 30 mg), and placebo alone and in combination. Self-report, task performance, and physiological measures were also collected. [INCREMENT]-THC served as a discriminative stimulus, produced positive subjective effects, elevated heart rate, and impaired psychomotor performance. Both doses of gabapentin substituted for the [INCREMENT]-THC discriminative stimulus and engendered subjective and performance-impairing effects that overlapped with those of [INCREMENT]-THC when administered alone. When administered concurrently, gabapentin shifted the discriminative-stimulus effects of [INCREMENT]-THC leftward/upward, and combinations of [INCREMENT]-THC and gabapentin generally produced larger effects on cannabinoid-sensitive outcomes relative to [INCREMENT]-THC alone. These results suggest that one mechanism by which gabapentin might facilitate cannabis abstinence is by producing effects that overlap with those of cannabinoids.
The efficiency of the RULES-4 classification learning algorithm in predicting the density of agents
Directory of Open Access Journals (Sweden)
Ziad Salem
2014-12-01
Full Text Available Learning is the act of obtaining new or modifying existing knowledge, behaviours, skills or preferences. The ability to learn is found in humans, other organisms and some machines. Learning is always based on some sort of observations or data such as examples, direct experience or instruction. This paper presents a classification algorithm to learn the density of agents in an arena based on the measurements of six proximity sensors of a combined actuator sensor units (CASUs. Rules are presented that were induced by the learning algorithm that was trained with data-sets based on the CASU’s sensor data streams collected during a number of experiments with “Bristlebots (agents in the arena (environment”. It was found that a set of rules generated by the learning algorithm is able to predict the number of bristlebots in the arena based on the CASU’s sensor readings with satisfying accuracy.
Advanced Credit-Assignment CMAC Algorithm for Robust Self-Learning and Self-Maintenance Machine
Institute of Scientific and Technical Information of China (English)
ZHANG Lei(张蕾); LEE Jay; CAO Qixin(曹其新); WANG Lei(王磊)
2004-01-01
Smart machine necessitates self-learning capabilities to assess its own performance and predict its behavior. To achieve self-maintenance intelligence, robust and fast learning algorithms need to be embedded in machine for real-time decision. This paper presents a credit-assignment cerebellar model articulation controller (CA-CMAC) algorithm to reduce learning interference in machine learning. The developed algorithms on credit matrix and the credit correlation matrix are presented. The error of the training sample distributed to the activated memory cell is proportional to the cell's credibility, which is determined by its activated times. The convergence processes of CA-CMAC in cyclic learning are further analyzed with two convergence theorems. In addition, simulation results on the inverse kinematics of 2-degree-of-freedom planar robot arm are used to prove the convergence theorems and show that CA-CMAC converges faster than conventional machine learning.
Institute of Scientific and Technical Information of China (English)
李楠; 谢娟英
2011-01-01
A feature subset selection algorithm is presented based on neighborhood rough set theory for die datasets which are updated by the increment in their samples. It is well known that the increment in samples can cause the changeable in the reduction of attributes of the dataset. Did a through-paced analysis to the variety on positive region brought by the new added sample to the dataset, and discussed the selective updating to the feature subset (attribute reduction) according to all the cases. The selective updating to the original reduction of attributes of the dataset can avoid the unwanted operations, and reduce the complexity of the feature subset selection algorithm. Finally, gave a real example and demonstrated the algorithm.%针对连续型属性的数据集,当有新样本加入时,可能引起最佳属性约简子集变化的问题,提出了基于邻域粗糙集的特征子集增量式更新方法.根据新增样本对正域的影响,分情况对原数据集的属性约简子集进行动态更新,以便得到增加样本后的新数据的最佳属性约简子集.这种对原约简集合进行的有选择的动态更新可以有效地避免重复操作,降低算法复杂度,只有在最坏的情况下才需要对整个数据集进行重新约简.并以一个实例进行分析说明.实例分析表明,先对新增样本进行分析,然后选择性对新数据集进行约简可以有效地避免重复操作,得到新数据集的最佳属性约简子集.
Institute of Scientific and Technical Information of China (English)
张钧波; 李天瑞; 潘毅; 罗川; 滕飞
2015-01-01
adapt to the dynamic real-time system, the MapReduce model and incremental method are combined to build two parallel incremental algorithms for updating rough set approximations in different incremental strategies. An extensive experimental evaluation on big data sets show that the proposed algorithms are very effective and have better performance with the increasing size of the data.
Efficiency versus Convergence of Boolean Kernels for On-Line Learning Algorithms
Khardon, R; Servedio, R A; 10.1613/jair.1655
2011-01-01
The paper studies machine learning problems where each example is described using a set of Boolean features and where hypotheses are represented by linear threshold elements. One method of increasing the expressiveness of learned hypotheses in this context is to expand the feature set to include conjunctions of basic features. This can be done explicitly or where possible by using a kernel function. Focusing on the well known Perceptron and Winnow algorithms, the paper demonstrates a tradeoff between the computational efficiency with which the algorithm can be run over the expanded feature space and the generalization ability of the corresponding learning algorithm. We first describe several kernel functions which capture either limited forms of conjunctions or all conjunctions. We show that these kernels can be used to efficiently run the Perceptron algorithm over a feature space of exponentially many conjunctions; however we also show that using such kernels, the Perceptron algorithm can provably make an ex...
Wang, Z O; Zhu, T
2000-01-01
This paper presents an efficient recursive learning algorithm for improving generalization performance of radial basis function (RBF) neural networks. The approach combines the rival penalized competitive learning (PRCL) [Xu, L., Kizyzak, A. & Oja, E. (1993). Rival penalized competitive learning for clustering analysis, RBF net and curve detection, IEEE Transactions on Neural Networks, 4, 636-649] and the regularized least squares (RLS) to provide an efficient and powerful procedure for constructing a minimal RBF network that generalizes very well. The RPCL selects the number of hidden units of network and adjusts centers, while the RLS constructs the parsimonious network and estimates the connection weights. In the RLS we derived a simple recursive algorithm, which needs no matrix calculation, and so largely reduces the computational cost. This combined algorithm significantly enhances the generalization performance and the real-time capability of the RBF networks. Simulation results of three different problems demonstrate much better generalization performance of the present algorithm over other existing similar algorithms.
Multidimensional dictionary learning algorithm for compressive sensing-based hyperspectral imaging
Zhao, Rongqiang; Wang, Qiang; Shen, Yi; Li, Jia
2016-11-01
The sparsifying representation plays a significant role in compressive sensing (CS)-based hyperspectral (HS) imaging. Training the dictionaries for each dimension from HS samples is very beneficial to accurate reconstruction. However, the tensor dictionary learning algorithms are limited by a great amount of computation and convergence difficulties. We propose a least squares (LS) type multidimensional dictionary learning algorithm for CS-based HS imaging. We develop a practical method for the dictionary updating stage, which avoids the use of the Kronecker product and thus has lower computation complexity. To guarantee the convergence, we add a pruning stage to the algorithm to ensure the similarity and relativity among data in the spectral dimension. Our experimental results demonstrated that the dictionaries trained using the proposed algorithm performed better at CS-based HS image reconstruction than those trained with traditional LS-type dictionary learning algorithms and the commonly used analytical dictionaries.
Karayiannis, Nicolaos B; Randolph-Gips, Mary M
2005-03-01
This paper presents the development of soft clustering and learning vector quantization (LVQ) algorithms that rely on a weighted norm to measure the distance between the feature vectors and their prototypes. The development of LVQ and clustering algorithms is based on the minimization of a reformulation function under the constraint that the generalized mean of the norm weights be constant. According to the proposed formulation, the norm weights can be computed from the data in an iterative fashion together with the prototypes. An error analysis provides some guidelines for selecting the parameter involved in the definition of the generalized mean in terms of the feature variances. The algorithms produced from this formulation are easy to implement and they are almost as fast as clustering algorithms relying on the Euclidean norm. An experimental evaluation on four data sets indicates that the proposed algorithms outperform consistently clustering algorithms relying on the Euclidean norm and they are strong competitors to non-Euclidean algorithms which are computationally more demanding.
Directory of Open Access Journals (Sweden)
Jing Zhao
2013-10-01
Full Text Available The evolutionary learning of fuzzy neural networks (FNN consists of structure learning to determine the proper number of fuzzy rules and parameters learning to adjust the network parameters. Many optimization algorithms can be applied to evolve FNN. However the search space of most algorithms has fixed dimension, which can not suit to dynamic structure learning of FNN. We propose a novel technique, which is named the variable-dimensional quantum-behaved particle swarm optimization algorithm (VDQPSO, to address the problem. In the proposed algorithm, the optimum dimension, which is unknown at the beginning, is updated together with the position of swarm. The optimum dimension converged at the end of the optimization process corresponds to a unique FNN structure where the optimum parameters can be achieved. The results of the prediction of chaotic time series experiment show that the proposed technique is effective. It can evolve to optimum or near-optimum FNN structure and optimum parameters.
Validating Machine Learning Algorithms for Twitter Data Against Established Measures of Suicidality.
Braithwaite, Scott R; Giraud-Carrier, Christophe; West, Josh; Barnes, Michael D; Hanson, Carl Lee
2016-05-16
One of the leading causes of death in the United States (US) is suicide and new methods of assessment are needed to track its risk in real time. Our objective is to validate the use of machine learning algorithms for Twitter data against empirically validated measures of suicidality in the US population. Using a machine learning algorithm, the Twitter feeds of 135 Mechanical Turk (MTurk) participants were compared with validated, self-report measures of suicide risk. Our findings show that people who are at high suicidal risk can be easily differentiated from those who are not by machine learning algorithms, which accurately identify the clinically significant suicidal rate in 92% of cases (sensitivity: 53%, specificity: 97%, positive predictive value: 75%, negative predictive value: 93%). Machine learning algorithms are efficient in differentiating people who are at a suicidal risk from those who are not. Evidence for suicidality can be measured in nonclinical populations using social media data.
Study on Q-learning algorithm based on ART 2%基于ART2的Q学习算法研究
Institute of Scientific and Technical Information of China (English)
姚明海; 瞿心昱; 李佳鹤; 顾勤龙; 汤丽平
2011-01-01
为了解决Q学习应用于连续状态空间的智能系统所面临的"维数灾难"问题,提出一种基于ART2的Q学习算法.通过引入ART2神经网络,让Q学习Agent针对任务学习一个适当的增量式的状态空间模式聚类,使Agent无需任何先验知识,即可在未知环境中进行行为决策和状态空间模式聚类两层在线学习,通过与环境交互来不断改进控制策略,从而提高学习精度.仿真实验表明,使用ARTQL算法的移动机器人能通过与环境交互学习来不断提高导航性能.%In order to solve the problem of dimension disaster which may be produced by applying Q-learing to intelligent system of continuous state-space, this paper proposes a Q-learning algorithm based on ART 2 and gives the specific steps. Through introducing the ART 2 neural network in the Q-learning algorithm, Q-learning Agent in view of the duty learns an appropriate incremental clustering of state-space model, so Agent can carry out decision-making and a two-tiers online learning of state-space model cluster in unknown environment without any priori knowledge. Through the interaction with the environment unceasingly alternately to improve the control strategies, the learning accuracy is increased. Finally, the mobile robot navigation simulation experiments show that, using the ARTQL algorithm, motion robot can improve its navigation performance continuously by interactive learning with the environment.
Robust algorithm for arrhythmia classification in ECG using extreme learning machine
Directory of Open Access Journals (Sweden)
Shin Kwangsoo
2009-10-01
Full Text Available Abstract Background Recently, extensive studies have been carried out on arrhythmia classification algorithms using artificial intelligence pattern recognition methods such as neural network. To improve practicality, many studies have focused on learning speed and the accuracy of neural networks. However, algorithms based on neural networks still have some problems concerning practical application, such as slow learning speeds and unstable performance caused by local minima. Methods In this paper we propose a novel arrhythmia classification algorithm which has a fast learning speed and high accuracy, and uses Morphology Filtering, Principal Component Analysis and Extreme Learning Machine (ELM. The proposed algorithm can classify six beat types: normal beat, left bundle branch block, right bundle branch block, premature ventricular contraction, atrial premature beat, and paced beat. Results The experimental results of the entire MIT-BIH arrhythmia database demonstrate that the performances of the proposed algorithm are 98.00% in terms of average sensitivity, 97.95% in terms of average specificity, and 98.72% in terms of average accuracy. These accuracy levels are higher than or comparable with those of existing methods. We make a comparative study of algorithm using an ELM, back propagation neural network (BPNN, radial basis function network (RBFN, or support vector machine (SVM. Concerning the aspect of learning time, the proposed algorithm using ELM is about 290, 70, and 3 times faster than an algorithm using a BPNN, RBFN, and SVM, respectively. Conclusion The proposed algorithm shows effective accuracy performance with a short learning time. In addition we ascertained the robustness of the proposed algorithm by evaluating the entire MIT-BIH arrhythmia database.
Cost-conscious comparison of supervised learning algorithms over multiple data sets
Ulaş, Aydın; Yıldız, Olcay Taner; Alpaydın, Ahmet İbrahim Ethem
2012-01-01
In the literature, there exist statistical tests to compare supervised learning algorithms on multiple data sets in terms of accuracy but they do not always generate an ordering. We propose Multi(2)Test, a generalization of our previous work, for ordering multiple learning algorithms on multiple data sets from "best" to "worst" where our goodness measure is composed of a prior cost term additional to generalization error. Our simulations show that Multi2Test generates orderings using pairwise...
Extracting quantum dynamics from genetic learning algorithms through principal component analysis
White, J L; Bucksbaum, P H
2004-01-01
Genetic learning algorithms are widely used to control ultrafast optical pulse shapes for photo-induced quantum control of atoms and molecules. An outstanding issue is how to use the solutions found by these algorithms to learn about the system's quantum dynamics. We propose a simple method based on principal component analysis of the control space, which can reveal the degrees of freedom responsible for control, and aid in the construction of an effective Hamiltonian for the dynamics.
Directory of Open Access Journals (Sweden)
REIS, M V. S. de A.
2017-06-01
Full Text Available This paper aims to evaluate the use of machine learning techniques in a database of marine accidents. We analyzed and evaluated the main causes and types of marine accidents in the Northern Fluminense region. For this, machine learning techniques were used. The study showed that the modeling can be done in a satisfactory manner using different configurations of classification algorithms, varying the activation functions and training parameters. The SMO (Sequential Minimal Optimization algorithm showed the best performance result.
A study of experimental evaluations of neural network learning algorithms: current research practice
Prechelt, Lutz
2007-01-01
113 articles about neural network learning algorithms published in 1993 and 1994 are examined for the amount of experimental evaluation they contain. Every third of them does employ not even a single realistic or real learning problem. Only 6% of all articles present results for more than one problem using real world data.Furthermore, one third of all articles does not present any quantitative comparison with a previously known algorithm. These results indicate that the q...
An analysis dictionary learning algorithm under a noisy data model with orthogonality constraint.
Zhang, Ye; Yu, Tenglong; Wang, Wenwu
2014-01-01
Two common problems are often encountered in analysis dictionary learning (ADL) algorithms. The first one is that the original clean signals for learning the dictionary are assumed to be known, which otherwise need to be estimated from noisy measurements. This, however, renders a computationally slow optimization process and potentially unreliable estimation (if the noise level is high), as represented by the Analysis K-SVD (AK-SVD) algorithm. The other problem is the trivial solution to the dictionary, for example, the null dictionary matrix that may be given by a dictionary learning algorithm, as discussed in the learning overcomplete sparsifying transform (LOST) algorithm. Here we propose a novel optimization model and an iterative algorithm to learn the analysis dictionary, where we directly employ the observed data to compute the approximate analysis sparse representation of the original signals (leading to a fast optimization procedure) and enforce an orthogonality constraint on the optimization criterion to avoid the trivial solutions. Experiments demonstrate the competitive performance of the proposed algorithm as compared with three baselines, namely, the AK-SVD, LOST, and NAAOLA algorithms.
An Analysis Dictionary Learning Algorithm under a Noisy Data Model with Orthogonality Constraint
Directory of Open Access Journals (Sweden)
Ye Zhang
2014-01-01
Full Text Available Two common problems are often encountered in analysis dictionary learning (ADL algorithms. The first one is that the original clean signals for learning the dictionary are assumed to be known, which otherwise need to be estimated from noisy measurements. This, however, renders a computationally slow optimization process and potentially unreliable estimation (if the noise level is high, as represented by the Analysis K-SVD (AK-SVD algorithm. The other problem is the trivial solution to the dictionary, for example, the null dictionary matrix that may be given by a dictionary learning algorithm, as discussed in the learning overcomplete sparsifying transform (LOST algorithm. Here we propose a novel optimization model and an iterative algorithm to learn the analysis dictionary, where we directly employ the observed data to compute the approximate analysis sparse representation of the original signals (leading to a fast optimization procedure and enforce an orthogonality constraint on the optimization criterion to avoid the trivial solutions. Experiments demonstrate the competitive performance of the proposed algorithm as compared with three baselines, namely, the AK-SVD, LOST, and NAAOLA algorithms.
A method for classification of network traffic based on C5.0 Machine Learning Algorithm
DEFF Research Database (Denmark)
Bujlow, Tomasz; Riaz, M. Tahir; Pedersen, Jens Myrup
2012-01-01
current network traffic. To overcome the drawbacks of existing methods for traffic classification, usage of C5.0 Machine Learning Algorithm (MLA) was proposed. On the basis of statistical traffic information received from volunteers and C5.0 algorithm we constructed a boosted classifier, which was shown...
Two Projection Pursuit Algorithms for Machine Learning under Non-Stationarity
Blythe, Duncan A J
2011-01-01
This thesis derives, tests and applies two linear projection algorithms for machine learning under non-stationarity. The first finds a direction in a linear space upon which a data set is maximally non-stationary. The second aims to robustify two-way classification against non-stationarity. The algorithm is tested on a key application scenario, namely Brain Computer Interfacing.
Grahl, J.; Minner, S.; Bosman, P.A.N.; Michalewicz, Z.; Siarry, P.
2008-01-01
This chapter serves as an introduction to estimation of distribution algorithms (EDAs). Estimation of distribution algorithms are a new paradigm in evolutionary computation. They combine statistical learning with population-based search in order to automatically identify and exploit certain structur
J. Grahl; S. Minner; P.A.N. Bosman (Peter); Z. Michalewicz; P. Siarry
2008-01-01
htmlabstractThis chapter serves as an introduction to estimation of distribution algorithms (EDAs). Estimation of distribution algorithms are a new paradigm in evolutionary computation. They combine statistical learning with population-based search in order to automatically identify and exploit
A Generalization of the Chow-Liu Algorithm and its Application to Statistical Learning
Suzuki, Joe
2010-01-01
We extend the Chow-Liu algorithm for general random variables while the previous versions only considered finite cases. In particular, this paper applies the generalization to Suzuki's learning algorithm that generates from data forests rather than trees based on the minimum description length by balancing the fitness of the data to the forest and the simplicity of the forest. As a result, we successfully obtain an algorithm when both of the Gaussian and finite random variables are present.
An Interactive Learning Algorithm for Acquisition of Concepts Represented as CFL
Institute of Scientific and Technical Information of China (English)
董韫美
1998-01-01
In this paper,an interactive learning algorithm of context-frmm language is presented.This algorithm is designed especially for system SAQ,which is a system for formal secification acquisition and verification.As the kernel of concept acquisition subsystem(SAQ/CL)of SAQ,the algorithm has been implemented on SUN SPARC workstation.The grammar to be obtained can represent sentence structure naturally.
$\\ell_1$-K-SVD: A Robust Dictionary Learning Algorithm With Simultaneous Update
Mukherjee, Subhadip; Basu, Rupam; Seelamantula, Chandra Sekhar
2014-01-01
We develop a dictionary learning algorithm by minimizing the $\\ell_1$ distortion metric on the data term, which is known to be robust for non-Gaussian noise contamination. The proposed algorithm exploits the idea of iterative minimization of weighted $\\ell_2$ error. We refer to this algorithm as $\\ell_1$-K-SVD, where the dictionary atoms and the corresponding sparse coefficients are simultaneously updated to minimize the $\\ell_1$ objective, resulting in noise-robustness. We demonstrate throug...
A Genetic Algorithm Approach to Recognise Students' Learning Styles
Yannibelli, Virginia; Godoy, Daniela; Amandi, Analia
2006-01-01
Learning styles encapsulate the preferences of the students, regarding how they learn. By including information about the student learning style, computer-based educational systems are able to adapt a course according to the individual characteristics of the students. In accomplishing this goal, educational systems have been mostly based on the…
A Genetic Algorithm Approach to Recognise Students' Learning Styles
Yannibelli, Virginia; Godoy, Daniela; Amandi, Analia
2006-01-01
Learning styles encapsulate the preferences of the students, regarding how they learn. By including information about the student learning style, computer-based educational systems are able to adapt a course according to the individual characteristics of the students. In accomplishing this goal, educational systems have been mostly based on the…
The evaluation of functional heart condition with machine learning algorithms
Overchuk, K. V.; Lezhnina, I. A.; Uvarov, A. A.; Perchatkin, V. A.; Lvova, A. B.
2017-08-01
This paper is considering the most suitable algorithms to build a classifier for evaluating of the functional heart condition with the ability to estimate the direction and progress of the patient’s treatment. The cons and pros of algorithms was analyzed with respect to the problem posed. The most optimal solution has been given and justified.
A new supervised learning algorithm for spiking neurons.
Xu, Yan; Zeng, Xiaoqin; Zhong, Shuiming
2013-06-01
The purpose of supervised learning with temporal encoding for spiking neurons is to make the neurons emit a specific spike train encoded by the precise firing times of spikes. If only running time is considered, the supervised learning for a spiking neuron is equivalent to distinguishing the times of desired output spikes and the other time during the running process of the neuron through adjusting synaptic weights, which can be regarded as a classification problem. Based on this idea, this letter proposes a new supervised learning method for spiking neurons with temporal encoding; it first transforms the supervised learning into a classification problem and then solves the problem by using the perceptron learning rule. The experiment results show that the proposed method has higher learning accuracy and efficiency over the existing learning methods, so it is more powerful for solving complex and real-time problems.
Self-learning Fuzzy Controllers Based On a Real-time Reinforcement Genetic Algorithm
Institute of Scientific and Technical Information of China (English)
FANG Jian-an; MIAO Qing-ying; GUO Zhao-xia; SHAO Shi-huang
2002-01-01
This paper presents a novel method for constructing fuzzy controllers based on a real time reinforcement genetic algorithm. This methodology introduces the real-time learning capability of neural networks into globally searching process of genetic algorithm, aiming to enhance the convergence rate and real-time learning ability of genetic algorithm, which is then used to construct fuzzy controllers for complex dynamic systems without any knowledge about system dynamics and prior control experience. The cart-pole system is employed as a test bed to demonstrate the effectiveness of the proposed control scheme, and the robustness of the acquired fuzzy controller with comparable result.
Chinese handwriting recognition an algorithmic perspective
Su, Tonghua
2013-01-01
This book provides an algorithmic perspective on the recent development of Chinese handwriting recognition. Two technically sound strategies, the segmentation-free and integrated segmentation-recognition strategy, are investigated and algorithms that have worked well in practice are primarily focused on. Baseline systems are initially presented for these strategies and are subsequently expanded on and incrementally improved. The sophisticated algorithms covered include: 1) string sample expansion algorithms which synthesize string samples from isolated characters or distort realistic string samples; 2) enhanced feature representation algorithms, e.g. enhanced four-plane features and Delta features; 3) novel learning algorithms, such as Perceptron learning with dynamic margin, MPE training and distributed training; and lastly 4) ensemble algorithms, that is, combining the two strategies using both parallel structure and serial structure. All the while, the book moves from basic to advanced algorithms, helping ...
Interactive Learning Environment for Bio-Inspired Optimization Algorithms for UAV Path Planning
Duan, Haibin; Li, Pei; Shi, Yuhui; Zhang, Xiangyin; Sun, Changhao
2015-01-01
This paper describes the development of BOLE, a MATLAB-based interactive learning environment, that facilitates the process of learning bio-inspired optimization algorithms, and that is dedicated exclusively to unmanned aerial vehicle path planning. As a complement to conventional teaching methods, BOLE is designed to help students consolidate the…
Predicting incomplete gene microarray data with the use of supervised learning algorithms
CSIR Research Space (South Africa)
Twala, B
2010-10-01
Full Text Available of many well-established supervised learning (SL) algorithms in an attempt to provide more accurate and automatic diagnosis class (cancer/non cancer) prediction. Virtually all research on SL addresses the task of learning to classify complete domain...
GreedEx: A Visualization Tool for Experimentation and Discovery Learning of Greedy Algorithms
Velazquez-Iturbide, J. A.; Debdi, O.; Esteban-Sanchez, N.; Pizarro, C.
2013-01-01
Several years ago we presented an experimental, discovery-learning approach to the active learning of greedy algorithms. This paper presents GreedEx, a visualization tool developed to support this didactic method. The paper states the design goals of GreedEx, makes explicit the major design decisions adopted, and describes its main characteristics…
GreedEx: A Visualization Tool for Experimentation and Discovery Learning of Greedy Algorithms
Velazquez-Iturbide, J. A.; Debdi, O.; Esteban-Sanchez, N.; Pizarro, C.
2013-01-01
Several years ago we presented an experimental, discovery-learning approach to the active learning of greedy algorithms. This paper presents GreedEx, a visualization tool developed to support this didactic method. The paper states the design goals of GreedEx, makes explicit the major design decisions adopted, and describes its main characteristics…
Upper-Lower Bounds Candidate Sets Searching Algorithm for Bayesian Network Structure Learning
Directory of Open Access Journals (Sweden)
Guangyi Liu
2014-01-01
Full Text Available Bayesian network is an important theoretical model in artificial intelligence field and also a powerful tool for processing uncertainty issues. Considering the slow convergence speed of current Bayesian network structure learning algorithms, a fast hybrid learning method is proposed in this paper. We start with further analysis of information provided by low-order conditional independence testing, and then two methods are given for constructing graph model of network, which is theoretically proved to be upper and lower bounds of the structure space of target network, so that candidate sets are given as a result; after that a search and scoring algorithm is operated based on the candidate sets to find the final structure of the network. Simulation results show that the algorithm proposed in this paper is more efficient than similar algorithms with the same learning precision.
Machine Learning Algorithms for Automatic Classification of Marmoset Vocalizations
Ribeiro, Sidarta; Pereira, Danillo R.; Papa, João P.; de Albuquerque, Victor Hugo C.
2016-01-01
Automatic classification of vocalization type could potentially become a useful tool for acoustic the monitoring of captive colonies of highly vocal primates. However, for classification to be useful in practice, a reliable algorithm that can be successfully trained on small datasets is necessary. In this work, we consider seven different classification algorithms with the goal of finding a robust classifier that can be successfully trained on small datasets. We found good classification performance (accuracy > 0.83 and F1-score > 0.84) using the Optimum Path Forest classifier. Dataset and algorithms are made publicly available. PMID:27654941
A Collaborative Algorithm for Ontological Matching in E-Learning Courseware Domain Knowledge Network
Directory of Open Access Journals (Sweden)
Akanbi C. Olufisoye
2011-11-01
Full Text Available Domain Knowledge is the content repository of a courseware system consisting of a series of learning objects. However, the unstructured and inconsistent naming of domain knowledge components does not permit knowledge transfer across diverse collaborative systems due to differences in architecture, format and representations. To address this identified problem, we formulate an ontological matching algorithm that provides a sharable knowledge in collaborative learning environment in this paper. The Algorithm employs Hybrid Similarity Measure to compute both Concept and Relational similarity values of the various input graphs-learning objects .
Li, Xiang-Tao; Yin, Ming-Hao
2012-05-01
We study the parameter estimation of a nonlinear chaotic system, which can be essentially formulated as a multidimensional optimization problem. In this paper, an orthogonal learning cuckoo search algorithm is used to estimate the parameters of chaotic systems. This algorithm can combine the stochastic exploration of the cuckoo search and the exploitation capability of the orthogonal learning strategy. Experiments are conducted on the Lorenz system and the Chen system. The proposed algorithm is used to estimate the parameters for these two systems. Simulation results and comparisons demonstrate that the proposed algorithm is better or at least comparable to the particle swarm optimization and the genetic algorithm when considering the quality of the solutions obtained.
Margin based ontology sparse vector learning algorithm and applied in biology science.
Gao, Wei; Qudair Baig, Abdul; Ali, Haidar; Sajjad, Wasim; Reza Farahani, Mohammad
2017-01-01
In biology field, the ontology application relates to a large amount of genetic information and chemical information of molecular structure, which makes knowledge of ontology concepts convey much information. Therefore, in mathematical notation, the dimension of vector which corresponds to the ontology concept is often very large, and thus improves the higher requirements of ontology algorithm. Under this background, we consider the designing of ontology sparse vector algorithm and application in biology. In this paper, using knowledge of marginal likelihood and marginal distribution, the optimized strategy of marginal based ontology sparse vector learning algorithm is presented. Finally, the new algorithm is applied to gene ontology and plant ontology to verify its efficiency.
A RBF Network Learning Scheme Using Immune Algorithm Based on Information Entropy
Institute of Scientific and Technical Information of China (English)
GONG Xin-bao; ZANG Xiao-gang; ZHOU Xi-lang
2005-01-01
A hybrid learning method combining immune algorithm and least square method is proposed to design the radial basis function(RBF) networks. The immune algorithm based on information entropy is used to determine the structure and parameters of RBF nonlinear hidden layer, and weights of RBF linear output layer are computed with least square method. By introducing the diversity control and immune memory mechanism, the algorithm improves the efficiency and overcomes the immature problem in genetic algorithm. Computer simulations demonstrate that the RBF networks designed in this method have fast convergence speed with good performances.
Institute of Scientific and Technical Information of China (English)
高红民; 周惠; 徐立中; 石爱业
2014-01-01
A hybrid feature selection and classification strategy was proposed based on the simulated annealing genetic algorithm and multiple instance learning (MIL). The band selection method was proposed from subspace decomposition, which combines the simulated annealing algorithm with the genetic algorithm in choosing different cross-over and mutation probabilities, as well as mutation individuals. Then MIL was combined with image segmentation, clustering and support vector machine algorithms to classify hyperspectral image. The experimental results show that this proposed method can get high classification accuracy of 93.13%at small training samples and the weaknesses of the conventional methods are overcome.
Nishizuka, N; Kubo, Y; Den, M; Watari, S; Ishii, M
2016-01-01
We developed a flare prediction model using machine learning, which is optimized to predict the maximum class of flares occurring in the following 24 h. Machine learning is used to devise algorithms that can learn from and make decisions on a huge amount of data. We used solar observation data during the period 2010-2015, such as vector magnetogram, ultraviolet (UV) emission, and soft X-ray emission taken by the Solar Dynamics Observatory and the Geostationary Operational Environmental Satellite. We detected active regions from the full-disk magnetogram, from which 60 features were extracted with their time differentials, including magnetic neutral lines, the current helicity, the UV brightening, and the flare history. After standardizing the feature database, we fully shuffled and randomly separated it into two for training and testing. To investigate which algorithm is best for flare prediction, we compared three machine learning algorithms: the support vector machine (SVM), k-nearest neighbors (k-NN), and ...
An Improved Reinforcement Learning Algorithm for Cooperative Behaviors of Mobile Robots
Directory of Open Access Journals (Sweden)
Yong Song
2014-01-01
Full Text Available Reinforcement learning algorithm for multirobot will become very slow when the number of robots is increasing resulting in an exponential increase of state space. A sequential Q-learning based on knowledge sharing is presented. The rule repository of robots behaviors is firstly initialized in the process of reinforcement learning. Mobile robots obtain present environmental state by sensors. Then the state will be matched to determine if the relevant behavior rule has been stored in the database. If the rule is present, an action will be chosen in accordance with the knowledge and the rules, and the matching weight will be refined. Otherwise the new rule will be appended to the database. The robots learn according to a given sequence and share the behavior database. We examine the algorithm by multirobot following-surrounding behavior, and find that the improved algorithm can effectively accelerate the convergence speed.
ALGORITHM FOR PHONOGRAM COMPARISON IN E-LEARNING SYSTEMS
Directory of Open Access Journals (Sweden)
V. V. Kiselev
2013-01-01
Full Text Available An algorithm for determination of the degree of phonogram matching on the basis of linear spectral frequency and dynamic time warping is considered. The problem of phonogram comparison is handled as the problem of recognizing the analyzed speech signal, which contains a lot of distortion and noise with unknown beginning and duration, non-linear timescale, and unknown pronunciation sample. A functional diagram of the algorithm is presented.
Learning Words through Computer-Adaptive Tool
DEFF Research Database (Denmark)
Zhang, Chun
2005-01-01
the category of L2 lexical learning in computer-adaptive learning environment. The reason to adopt computer-adaptive tool in WPG is based on the following premises: 1. Lexical learning is incremental in nature. 2. Learning can be measured precisely with tests (objectivist epistemology). In the course of WPG...... construction, I stress the design of a test theory, namely, a learning algorithm. The learning algorithm is designed under such principles that users experience both 'elaborative rehearsal’ (aspects in receptive and productive learning) and 'expanding rehearsal, (memory-based learning and repetitive act...
Végh, Ladislav
2016-01-01
The first data structure that first-year undergraduate students learn during the programming and algorithms courses is the one-dimensional array. For novice programmers, it might be hard to understand different algorithms on arrays (e.g. searching, mirroring, sorting algorithms), because the algorithms dynamically change the values of elements. In…
Institute of Scientific and Technical Information of China (English)
Lean YU; Shouyang WANG; Kin Keung LAI
2009-01-01
The slow convergence of back-propagation neu-ral network (BPNN) has become a challenge in data-mining and knowledge discovery applications due to the drawbacks of the gradient descent (GD) optimization method, which is widely adopted in BPNN learning. To solve this problem,some standard Optimization techniques such as conjugate-gradient and Newton method have been proposed to improve the convergence rate of BP learning algorithm. This paper presents a heuristic method that adds an adaptive smooth-ing momentum term to original BP learning algorithm to speedup the convergence. In this improved BP learning al-gorithm, adaptive smoothing technique is used to adjust the momentums of weight updating formula automatically in terms of "3 σ limits theory." Using the adaptive smoothing momentum terms, the improved BP learning algorithm can make the network training and convergence process faster,and the network's generalization performance stronger than the standard BP learning algorithm can do. In order to ver-ify the effectiveness of the proposed BP learning algorithm,three typical foreign exchange rates, British pound (GBP),Euro (EUR), and Japanese yen (JPY), are chosen as the fore-casting targets for illustration purpose. Experimental results from homogeneous algorithm comparisons reveal that the proposed BP learning algorithm outperforms the other com-parable BP algorithms in performance and convergence rate.Furthermore, empirical results from heterogeneous model comparisons also show the effectiveness of the proposed BP learning algorithm.
Incremental Similarity and Turbulence
DEFF Research Database (Denmark)
Barndorff-Nielsen, Ole E.; Hedevang, Emil; Schmiegel, Jürgen
This paper discusses the mathematical representation of an empirically observed phenomenon, referred to as Incremental Similarity. We discuss this feature from the viewpoint of stochastic processes and present a variety of non-trivial examples, including those that are of relevance for turbulence...
Incremental Bisimulation Abstraction Refinement
DEFF Research Database (Denmark)
Godskesen, Jens Christian; Song, Lei; Zhang, Lijun
2013-01-01
an abstraction refinement approach for the probabilistic computation tree logic (PCTL), which is based on incrementally computing a sequence of may- and must-quotient automata. These are induced by depth-bounded bisimulation equivalences of increasing depth. The approach is both sound and complete, since...
Lightweight incremental application upgrade
T. van der Storm (Tijs)
2006-01-01
textabstractI present a lightweight approach to incremental application upgrade in the context of component-based software development. The approach can be used to efficiently implement an automated update feature in a platform and programming language agnostic way. A formal release model is present
Schwarz, Daniel; Štourač, Petr; Komenda, Martin; Harazim, Hana; Kosinová, Martina; Gregor, Jakub; Hůlek, Richard; Smékalová, Olga; Křikava, Ivo; Štoudek, Roman; Dušek, Ladislav
2013-07-08
Medical Faculties Network (MEFANET) has established itself as the authority for setting standards for medical educators in the Czech Republic and Slovakia, 2 independent countries with similar languages that once comprised a federation and that still retain the same curricular structure for medical education. One of the basic goals of the network is to advance medical teaching and learning with the use of modern information and communication technologies. We present the education portal AKUTNE.CZ as an important part of the MEFANET's content. Our focus is primarily on simulation-based tools for teaching and learning acute medicine issues. Three fundamental elements of the MEFANET e-publishing system are described: (1) medical disciplines linker, (2) authentication/authorization framework, and (3) multidimensional quality assessment. A new set of tools for technology-enhanced learning have been introduced recently: Sandbox (works in progress), WikiLectures (collaborative content authoring), Moodle-MEFANET (central learning management system), and Serious Games (virtual casuistics and interactive algorithms). The latest development in MEFANET is designed for indexing metadata about simulation-based learning objects, also known as electronic virtual patients or virtual clinical cases. The simulations assume the form of interactive algorithms for teaching and learning acute medicine. An anonymous questionnaire of 10 items was used to explore students' attitudes and interests in using the interactive algorithms as part of their medical or health care studies. Data collection was conducted over 10 days in February 2013. In total, 25 interactive algorithms in the Czech and English languages have been developed and published on the AKUTNE.CZ education portal to allow the users to test and improve their knowledge and skills in the field of acute medicine. In the feedback survey, 62 participants completed the online questionnaire (13.5%) from the total 460 addressed
Directory of Open Access Journals (Sweden)
H Asayesh
2015-12-01
Full Text Available Introduction: Improvement of students’ clinical decision making is one of the main challenges in medical education. There are numerous ways to improve these skills. The aim of this study was to examine the effect of algorithm-based learning on clinical decision making abilities of medical emergency students. Method: in this experimental study, twenty five medical emergency students were randomly assigned to algorithm based learning group (n=13 and control group (n=12. Student in algorithm-based learning group were educated the diagnosis and treatment of selected medical emergency situation with algorithmic approach. Education in the control group was conducted by a routine lecture, along with copies of educational content. Three-hour training period was held for both groups (two separate sessions with an interval day. After intervention, clinical decision making of the students in both group were measured by clinical scenarios and clinical decision making self-efficacy scale. Results: The mean of acquired scores from clinical scenarios among students in algorithm-based learning group was 17.50 (±1.67 and in the control group was 14.50 (±2.63. The differences was statistically significant (t=0.006, P=0.006. The students in algorithm-based learning group had better scores in the clinical decision making in terms of self-efficacy scale and it was 13.30 (1.57 and in the control group this mean was 10.32 (3.05. In this case, the differences was statistically significant (t=3.01, P=0.009. Conclusion: algorithm-based learning is effective in improvement of clinical decision making and applying of this method along with other educational methods could promote students’ clinical decision making especially in medical emergency situations.
A Corrective Training Algorithm for Adaptive Learning in Bag Generation
Chen, H H; Chen, Hsin-Hsi; Lee, Yue-Shi
1994-01-01
The sampling problem in training corpus is one of the major sources of errors in corpus-based applications. This paper proposes a corrective training algorithm to best-fit the run-time context domain in the application of bag generation. It shows which objects to be adjusted and how to adjust their probabilities. The resulting techniques are greatly simplified and the experimental results demonstrate the promising effects of the training algorithm from generic domain to specific domain. In general, these techniques can be easily extended to various language models and corpus-based applications.
The Cognitive Underpinnings of Incremental Rehearsal
Varma, Sashank; Schleisman, Katrina B.
2014-01-01
Incremental rehearsal (IR) is a flashcard technique that has been developed and evaluated by school psychologists. We discuss potential learning and memory effects from cognitive psychology that may explain the observed superiority of IR over other flashcard techniques. First, we propose that IR is a form of "spaced practice" that…
A Weighted Block Dictionary Learning Algorithm for Classification
Zhongrong Shi
2016-01-01
Discriminative dictionary learning, playing a critical role in sparse representation based classification, has led to state-of-the-art classification results. Among the existing discriminative dictionary learning methods, two different approaches, shared dictionary and class-specific dictionary, which associate each dictionary atom to all classes or a single class, have been studied. The shared dictionary is a compact method but with lack of discriminative information; the class-specific dict...
Spectral Regularization Algorithms for Learning Large Incomplete Matrices.
Mazumder, Rahul; Hastie, Trevor; Tibshirani, Robert
2010-03-01
We use convex relaxation techniques to provide a sequence of regularized low-rank solutions for large-scale matrix completion problems. Using the nuclear norm as a regularizer, we provide a simple and very efficient convex algorithm for minimizing the reconstruction error subject to a bound on the nuclear norm. Our algorithm Soft-Impute iteratively replaces the missing elements with those obtained from a soft-thresholded SVD. With warm starts this allows us to efficiently compute an entire regularization path of solutions on a grid of values of the regularization parameter. The computationally intensive part of our algorithm is in computing a low-rank SVD of a dense matrix. Exploiting the problem structure, we show that the task can be performed with a complexity linear in the matrix dimensions. Our semidefinite-programming algorithm is readily scalable to large matrices: for example it can obtain a rank-80 approximation of a 10(6) × 10(6) incomplete matrix with 10(5) observed entries in 2.5 hours, and can fit a rank 40 approximation to the full Netflix training set in 6.6 hours. Our methods show very good performance both in training and test error when compared to other competitive state-of-the art techniques.
Learning JavaScript data structures and algorithms
Groner, Loiane
2014-01-01
If you are a JavaScript developer or someone who has basic knowledge of JavaScript, and want to explore its optimum ability, this fast-paced book is definitely for you. Programming logic is the only thing you need to know to start having fun with algorithms.
A comparison algorithm to check LTSA Layer 1 and SCORM compliance in e-Learning sites
Sengupta, Souvik; Banerjee, Nilanjan
2012-01-01
The success of e-Learning is largely dependent on the impact of its multimedia aided learning content on the learner over the hyper media. The e-Learning portals with different proportion of multimedia elements have different impact on the learner, as there is lack of standardization. The Learning Technology System Architecture (LTSA) Layer 1 deals with the effect of environment on the learner. From an information technology perspective it specifies learner interaction from the environment to the learner via multimedia content. Sharable Content Object Reference Model (SCROM) is a collection of standards and specifications for content of web-based e-learning and specifies how JavaScript API can be used to integrate content development. In this paper an examination is made on the design features of interactive multimedia components of the learning packages by creating an algorithm which will give a comparative study of multimedia component used by different learning packages. The resultant graph as output helps...
An efficient approximation algorithm for finding a maximum clique using Hopfield network learning.
Wang, Rong Long; Tang, Zheng; Cao, Qi Ping
2003-07-01
In this article, we present a solution to the maximum clique problem using a gradient-ascent learning algorithm of the Hopfield neural network. This method provides a near-optimum parallel algorithm for finding a maximum clique. To do this, we use the Hopfield neural network to generate a near-maximum clique and then modify weights in a gradient-ascent direction to allow the network to escape from the state of near-maximum clique to maximum clique or better. The proposed parallel algorithm is tested on two types of random graphs and some benchmark graphs from the Center for Discrete Mathematics and Theoretical Computer Science (DIMACS). The simulation results show that the proposed learning algorithm can find good solutions in reasonable computation time.
Incremental Web Usage Mining Based on Active Ant Colony Clustering
Institute of Scientific and Technical Information of China (English)
SHEN Jie; LIN Ying; CHEN Zhimin
2006-01-01
To alleviate the scalability problem caused by the increasing Web using and changing users' interests, this paper presents a novel Web Usage Mining algorithm-Incremental Web Usage Mining algorithm based on Active Ant Colony Clustering. Firstly, an active movement strategy about direction selection and speed, different with the positive strategy employed by other Ant Colony Clustering algorithms, is proposed to construct an Active Ant Colony Clustering algorithm, which avoid the idle and "flying over the plane" moving phenomenon, effectively improve the quality and speed of clustering on large dataset. Then a mechanism of decomposing clusters based on above methods is introduced to form new clusters when users' interests change. Empirical studies on a real Web dataset show the active ant colony clustering algorithm has better performance than the previous algorithms, and the incremental approach based on the proposed mechanism can efficiently implement incremental Web usage mining.
Quantum independent increment processes
Franz, Uwe
2005-01-01
This volume is the first of two volumes containing the revised and completed notes lectures given at the school "Quantum Independent Increment Processes: Structure and Applications to Physics". This school was held at the Alfried-Krupp-Wissenschaftskolleg in Greifswald during the period March 9 – 22, 2003, and supported by the Volkswagen Foundation. The school gave an introduction to current research on quantum independent increment processes aimed at graduate students and non-specialists working in classical and quantum probability, operator algebras, and mathematical physics. The present first volume contains the following lectures: "Lévy Processes in Euclidean Spaces and Groups" by David Applebaum, "Locally Compact Quantum Groups" by Johan Kustermans, "Quantum Stochastic Analysis" by J. Martin Lindsay, and "Dilations, Cocycles and Product Systems" by B.V. Rajarama Bhat.
Precursors of extreme increments
Hallerberg, S; Holstein, D; Kantz, H; Hallerberg, Sarah; Altmann, Eduardo G.; Holstein, Detlef; Kantz, Holger
2006-01-01
We investigate precursors and predictability of extreme events in time series, which consist in large increments within successive time steps. In order to understand the predictability of this class of extreme events, we study analytically the prediction of extreme increments in AR(1)-processes. The resulting strategies are then applied to predict sudden increases in wind speed recordings. In both cases we evaluate the success of predictions via creating receiver operator characteristics (ROC-plots). Surprisingly, we obtain better ROC-plots for completely uncorrelated Gaussian random numbers than for AR(1)-correlated data. Furthermore, we observe an increase of predictability with increasing event size. Both effects can be understood by using the likelihood ratio as a summary index for smooth ROC-curves.
Efficient incremental relaying
Fareed, Muhammad Mehboob
2013-07-01
We propose a novel relaying scheme which improves the spectral efficiency of cooperative diversity systems by utilizing limited feedback from destination. Our scheme capitalizes on the fact that relaying is only required when direct transmission suffers deep fading. We calculate the packet error rate for the proposed efficient incremental relaying scheme with both amplify and forward and decode and forward relaying. Numerical results are also presented to verify their analytical counterparts. © 2013 IEEE.
Shellsort with three increments
Janson, Svante
2008-01-01
A perturbation technique can be used to simplify and sharpen A. C. Yao's theorems about the behavior of shellsort with increments $(h,g,1)$. In particular, when $h=\\Theta(n^{7/15})$ and $g=\\Theta(h^{1/5})$, the average running time is $O(n^{23/15})$. The proof involves interesting properties of the inversions in random permutations that have been $h$-sorted and $g$-sorted.
Explicit Learning: an Effort towards Human Scheduling Algorithms
Li, Jingpeng
2008-01-01
Scheduling problems are generally NP-hard combinatorial problems, and a lot of research has been done to solve these problems heuristically. However, most of the previous approaches are problem-specific and research into the development of a general scheduling algorithm is still in its infancy. Mimicking the natural evolutionary process of the survival of the fittest, Genetic Algorithms (GAs) have attracted much attention in solving difficult scheduling problems in recent years. Some obstacles exist when using GAs: there is no canonical mechanism to deal with constraints, which are commonly met in most real-world scheduling problems, and small changes to a solution are difficult. To overcome both difficulties, indirect approaches have been presented (in [1] and [2]) for nurse scheduling and driver scheduling, where GAs are used by mapping the solution space, and separate decoding routines then build solutions to the original problem.
3D Visualization of Machine Learning Algorithms with Astronomical Data
Kent, Brian R.
2016-01-01
We present innovative machine learning (ML) methods using unsupervised clustering with minimum spanning trees (MSTs) to study 3D astronomical catalogs. Utilizing Python code to build trees based on galaxy catalogs, we can render the results with the visualization suite Blender to produce interactive 360 degree panoramic videos. The catalogs and their ML results can be explored in a 3D space using mobile devices, tablets or desktop browsers. We compare the statistics of the MST results to a number of machine learning methods relating to optimization and efficiency.
Intelligent open learning systems concepts, models and algorithms
Rózewski, Przemyslaw; Tadeusiewicz, Ryszard; Zaikin, Oleg
2011-01-01
In presented book the Intelligent Open Learning Systems (IOLS) are proposed, described, discussed, and evaluated. The IOLS is a system in which traditional methods of online teaching are enhanced through the use of artificial intelligence and cognitive science. This is the main topic of the book. It consists of ten chapters and is divided into three parts. The first part concentrates on the Open Learning System (OLS) analysis, in particular: the social and educational meanings of the OLS, the new role of the teacher and the new requirements regarding the structure of didactic material. Moreove
An Active Learning Algorithm for Control of Epidural Electrostimulation.
Desautels, Thomas A; Choe, Jaehoon; Gad, Parag; Nandra, Mandheerej S; Roy, Roland R; Zhong, Hui; Tai, Yu-Chong; Edgerton, V Reggie; Burdick, Joel W
2015-10-01
Epidural electrostimulation has shown promise for spinal cord injury therapy. However, finding effective stimuli on the multi-electrode stimulating arrays employed requires a laborious manual search of a vast space for each patient. Widespread clinical application of these techniques would be greatly facilitated by an autonomous, algorithmic system which choses stimuli to simultaneously deliver effective therapy and explore this space. We propose a method based on GP-BUCB, a Gaussian process bandit algorithm. In n = 4 spinally transected rats, we implant epidural electrode arrays and examine the algorithm's performance in selecting bipolar stimuli to elicit specified muscle responses. These responses are compared with temporally interleaved intra-animal stimulus selections by a human expert. GP-BUCB successfully controlled the spinal electrostimulation preparation in 37 testing sessions, selecting 670 stimuli. These sessions included sustained autonomous operations (ten-session duration). Delivered performance with respect to the specified metric was as good as or better than that of the human expert. Despite receiving no information as to anatomically likely locations of effective stimuli, GP-BUCB also consistently discovered such a pattern. Further, GP-BUCB was able to extrapolate from previous sessions' results to make predictions about performance in new testing sessions, while remaining sufficiently flexible to capture temporal variability. These results provide validation for applying automated stimulus selection methods to the problem of spinal cord injury therapy.
Directory of Open Access Journals (Sweden)
Cheng-Ming Lee
2016-11-01
Full Text Available A reinforcement learning algorithm is proposed to improve the accuracy of short-term load forecasting (STLF in this article. The proposed model integrates radial basis function neural network (RBFNN, support vector regression (SVR, and adaptive annealing learning algorithm (AALA. In the proposed methodology, firstly, the initial structure of RBFNN is determined by using an SVR. Then, an AALA with time-varying learning rates is used to optimize the initial parameters of SVR-RBFNN (AALA-SVR-RBFNN. In order to overcome the stagnation for searching optimal RBFNN, a particle swarm optimization (PSO is applied to simultaneously find promising learning rates in AALA. Finally, the short-term load demands are predicted by using the optimal RBFNN. The performance of the proposed methodology is verified on the actual load dataset from the Taiwan Power Company (TPC. Simulation results reveal that the proposed AALA-SVR-RBFNN can achieve a better load forecasting precision compared to various RBFNNs.
The Design and Analysis of Efficient Learning Algorithms
1991-01-01
Boucheron and Jean Sallantin. Some remarks about space-complexity of learning, and circuit complexity of recognizing. In Proceedings of the 1988 Workshop on...editors, Annual Review of Computer Science, volume 4, pages 255-306. Annual Reviews, 1990. [21] Gary L. Drescher. Genetic Al - translating Piaget into
Algorithms and Complexity Results for Exact Bayesian Structure Learning
Ordyniak, Sebastian
2012-01-01
Bayesian structure learning is the NP-hard problem of discovering a Bayesian network that optimally represents a given set of training data. In this paper we study the computational worst-case complexity of exact Bayesian structure learning under graph theoretic restrictions on the super-structure. The super-structure (a concept introduced by Perrier, Imoto, and Miyano, JMLR 2008) is an undirected graph that contains as subgraphs the skeletons of solution networks. Our results apply to several variants of score-based Bayesian structure learning where the score of a network decomposes into local scores of its nodes. Results: We show that exact Bayesian structure learning can be carried out in non-uniform polynomial time if the super-structure has bounded treewidth and in linear time if in addition the super-structure has bounded maximum degree. We complement this with a number of hardness results. We show that both restrictions (treewidth and degree) are essential and cannot be dropped without loosing uniform ...
Discovery Learning in Autonomous Agents Using Genetic Algorithms
1993-12-01
by the fil’.ers during the proceso of hypothesis boosting. I argue that this is a risk that must be taken by the autonomous aircraft agent control...can be checked in the effector int’rface and the learning system scolded ( penalized ) whenever it tries to drop an ordnance on the wrong place. Other
Cheng, Hong
2015-01-01
This unique text/reference presents a comprehensive review of the state of the art in sparse representations, modeling and learning. The book examines both the theoretical foundations and details of algorithm implementation, highlighting the practical application of compressed sensing research in visual recognition and computer vision. Topics and features: provides a thorough introduction to the fundamentals of sparse representation, modeling and learning, and the application of these techniques in visual recognition; describes sparse recovery approaches, robust and efficient sparse represen
Generalized cost-criterion-based learning algorithm for diagonal recurrent neural networks
Wang, Yongji; Wang, Hong
2000-05-01
A new generalized cost criterion based learning algorithm for diagonal recurrent neural networks is presented, which is with form of recursive prediction error (RPE) and has second convergent order. A guideline for the choice of the optimal learning rate is derived from convergence analysis. The application of this method to dynamic modeling of typical chemical processes shows that the generalized cost criterion RPE (QRPE) has higher modeling precision than BP trained MLP and quadratic cost criterion trained RPE (QRPE).
Algebraic learning for language acquisition
Farrell, Kevin R.; Mammone, Richard J.; Gorin, Allen
1994-02-01
This paper explores the application of new algorithms to the adaptive language acquisition model formulated by Gorin. The new methods consists of incremental approaches for the algebraic learning of statistical associations proposed by Tishby. The incremental methods are evaluated on a text-based natural language experiment, namely the inward call manager task. Performance is evaluated with respect to the alternative methods, namely the smooth mutual information method and the pseudo-inverse solution.
Directory of Open Access Journals (Sweden)
R. Venkata Rao
2016-03-01
Full Text Available The performance of rapid prototyping (RP processes is often measured in terms of build time, product quality, dimensional accuracy, cost of production, mechanical and tribological properties of the models and energy consumed in the process. The success of any RP process in terms of these performance measures entails selection of the optimum combination of the influential process parameters. Thus, in this work the single-objective and multi-objective optimization problems of a widely used RP process, namely, fused deposition modeling (FDM, are formulated, and the same are solved using the teaching-learning-based optimization (TLBO algorithm and non-dominated Sorting TLBO (NSTLBO algorithm, respectively. The results of the TLBO algorithm are compared with those obtained using genetic algorithm (GA, and quantum behaved particle swarm optimization (QPSO algorithm. The TLBO algorithm showed better performance as compared to GA and QPSO algorithms. The NSTLBO algorithm proposed to solve the multi-objective optimization problems of the FDM process in this work is a posteriori version of the TLBO algorithm. The NSTLBO algorithm is incorporated with non-dominated sorting concept and crowding distance assignment mechanism to obtain a dense set of Pareto optimal solutions in a single simulation run. The results of the NSTLBO algorithm are compared with those obtained using non-dominated sorting genetic algorithm (NSGA-II and the desirability function approach. The Pareto-optimal set of solutions for each problem is obtained and reported. These Pareto-optimal set of solutions will help the decision maker in volatile scenarios and are useful for the FDM process.
Breast Cancer Diagnosis Using Machine Learning Algorithms - A Survey
Directory of Open Access Journals (Sweden)
B.M.Gayathri
2013-06-01
Full Text Available Breast cancer has become a common factor now-a-days. Despite the fact, not all general hospitalshave the facilities to diagnose breast cancer through mammograms. Waiting for diagnosing a breastcancer for a long time may increase the possibility of the cancer spreading. Therefore a computerizedbreast cancer diagnosis has been developed to reduce the time taken to diagnose the breast cancer andreduce the death rate. This paper summarizes the survey on breast cancer diagnosis using various machinelearning algorithms and methods, which are used to improve the accuracy of predicting cancer. This surveycan also help us to know about number of papers that are implemented to diagnose the breast cancer.
A two-level on-line learning algorithm of Artificial Neural Network with forward connections
Directory of Open Access Journals (Sweden)
Stanislaw Placzek
2014-12-01
Full Text Available An Artificial Neural Network with cross-connection is one of the most popular network structures. The structure contains: an input layer, at least one hidden layer and an output layer. Analysing and describing an ANN structure, one usually finds that the first parameter is the number of ANN’s layers. A hierarchical structure is a default and accepted way of describing the network. Using this assumption, the network structure can be described from a different point of view. A set of concepts and models can be used to describe the complexity of ANN’s structure in addition to using a two-level learning algorithm. Implementing the hierarchical structure to the learning algorithm, an ANN structure is divided into sub-networks. Every sub-network is responsible for finding the optimal value of its weight coefficients using a local target function to minimise the learning error. The second coordination level of the learning algorithm is responsible for coordinating the local solutions and finding the minimum of the global target function. In the article a special emphasis is placed on the coordinator’s role in the learning algorithm and its target function. In each iteration the coordinator has to send coordination parameters into the first level of subnetworks. Using the input X and the teaching Z vectors, the local procedures are working and finding their weight coefficients. At the same step the feedback information is calculated and sent to the coordinator. The process is being repeated until the minimum of local target functions is achieved. As an example, a two-level learning algorithm is used to implement an ANN in the underwriting process for classifying the category of health in a life insurance company.
Directory of Open Access Journals (Sweden)
Hua Xu
2013-01-01
Full Text Available Estimation of distribution algorithms (EDAs, as an extension of genetic algorithms, samples new solutions from the probabilistic model, which characterizes the distribution of promising solutions in the search space at each generation. This paper introduces and evaluates a novel estimation of a distribution algorithm, called L1-regularized Bayesian optimization algorithm, L1BOA. In L1BOA, Bayesian networks as probabilistic models are learned in two steps. First, candidate parents of each variable in Bayesian networks are detected by means of L1-regularized logistic regression, with the aim of leading a sparse but nearly optimized network structure. Second, the greedy search, which is restricted to the candidate parent-child pairs, is deployed to identify the final structure. Compared with the Bayesian optimization algorithm (BOA, L1BOA improves the efficiency of structure learning due to the reduction and automated control of network complexity introduced with L1-regularized learning. Experimental studies on different types of benchmark problems show that L1BOA not only outperforms BOA when no prior knowledge about problem structure is available, but also achieves and even exceeds the best performance of BOA that applies explicit controls on network complexity. Furthermore, Bayesian networks built by L1BOA and BOA during evolution are analysed and compared, which demonstrates that L1BOA is able to build simpler, yet more accurate probabilistic models.
Moreno, Julian; Ovalle, Demetrio A.; Vicari, Rosa M.
2012-01-01
Considering that group formation is one of the key processes in collaborative learning, the aim of this paper is to propose a method based on a genetic algorithm approach for achieving inter-homogeneous and intra-heterogeneous groups. The main feature of such a method is that it allows for the consideration of as many student characteristics as…
Tillage management practices have direct impact on water holding capacity, evaporation, carbon sequestration, and water quality. This study examines the feasibility of two statistical learning algorithms, such as Least Square Support Vector Machine (LSSVM) and Relevance Vector Machine (RVM), for cla...
Moreno, Julian; Ovalle, Demetrio A.; Vicari, Rosa M.
2012-01-01
Considering that group formation is one of the key processes in collaborative learning, the aim of this paper is to propose a method based on a genetic algorithm approach for achieving inter-homogeneous and intra-heterogeneous groups. The main feature of such a method is that it allows for the consideration of as many student characteristics as…
DEFF Research Database (Denmark)
Endelt, Benny Ørtoft; Volk, Wolfram
2013-01-01
, the reaction speed may be insufficient compared to the production rate in an industrial application. We propose to design an iterative learning control (ILC) algorithm which can control and update the blank-holder force as well as the distribution of the blank-holder force based on limited geometric data from...
Performance Evaluation of an Option-Based Learning Algorithm in Multi-Car Elevator Systems
Valdivielso Chian, Alex; Miyamoto, Toshiyuki
In this letter, we present the evaluation of an option-based learning algorithm, developed to perform a conflict-free allocation of calls among cars in a multi-car elevator system. We evaluate its performance in terms of the service time, its flexibility in the task-allocation, and the load balancing.
Directory of Open Access Journals (Sweden)
A. A. Salama
2015-03-01
Full Text Available In this paper, we present a review of different recommender system algorithms that are utilized in social networks based e-Learning systems. Future research will include our proposed our e-Learning system that utilizes Recommender System and Social Network. Since the world is full of indeterminacy, the neutrosophics found their place into contemporary research. The fundamental concepts of neutrosophic set, introduced by Smarandache in [21, 22, 23] and Salama et al. in [24-66].The purpose of this paper is to utilize a neutrosophic set to analyze social networks data conducted through learning activities.
A new machine learning algorithm for removal of salt and pepper noise
Wang, Yi; Adhami, Reza; Fu, Jian
2015-07-01
Supervised machine learning algorithm has been extensively studied and applied to different fields of image processing in past decades. This paper proposes a new machine learning algorithm, called margin setting (MS), for restoring images that are corrupted by salt and pepper impulse noise. Margin setting generates decision surface to classify the noise pixels and non-noise pixels. After the noise pixels are detected, a modified ranked order mean (ROM) filter is used to replace the corrupted pixels for images reconstruction. Margin setting algorithm is tested with grayscale and color images for different noise densities. The experimental results are compared with those of the support vector machine (SVM) and standard median filter (SMF). The results show that margin setting outperforms these methods with higher Peak Signal-to-Noise Ratio (PSNR), lower mean square error (MSE), higher image enhancement factor (IEF) and higher Structural Similarity Index (SSIM).
Autoclassification of the Variable 3XMM Sources Using the Random Forest Machine Learning Algorithm
Farrell, Sean A; Lo, Kitty K
2015-01-01
In the current era of large surveys and massive data sets, autoclassification of astrophysical sources using intelligent algorithms is becoming increasingly important. In this paper we present the catalog of variable sources in the Third XMM-Newton Serendipitous Source catalog (3XMM) autoclassified using the Random Forest machine learning algorithm. We used a sample of manually classified variable sources from the second data release of the XMM-Newton catalogs (2XMMi-DR2) to train the classifier, obtaining an accuracy of ~92%. We also evaluated the effectiveness of identifying spurious detections using a sample of spurious sources, achieving an accuracy of ~95%. Manual investigation of a random sample of classified sources confirmed these accuracy levels and showed that the Random Forest machine learning algorithm is highly effective at automatically classifying 3XMM sources. Here we present the catalog of classified 3XMM variable sources. We also present three previously unidentified unusual sources that wer...
A Learning Automata Based Algorithm For Solving Capacitated Vehicle Routing Problem
Directory of Open Access Journals (Sweden)
Mir Mohammad Alipour
2012-03-01
Full Text Available This paper presents an approximate algorithm based on distributed learning automata for solving capacitated vehicle routing problem. The vehicle routing problem (VRP is an NP-hard problem and capacitated vehicle routing problem variant (CVRP is considered here. This problem is one of the NP-hard problems and for this reason many approximate algorithms have been designed for solving it. Distributed learning automata that is a general searching tool and is a solving tool for variety of NP-complete problems, is used to solve this problem and tested on fourteen benchmark problems. Our results were compared to the best known results. The results of comparison have shown the efficiency of the proposed algorithm.
Salvador, Pablo; Sanz, Julia; Garcia, Miguel; Casanova, Jose Luis
2016-08-01
Fires in general and forest fires specific are a major concern in terms of economical and biological loses. Remote sensing technologies have been focusing on developing several algorithms, adapted to a large kind of sensors, platforms and regions in order to obtain hotspots as faster as possible. The aim of this study is to establish an automatic methodology to develop hotspots detection algorithms with Spinning Enhanced Visible and Infrared Imager (SEVIRI) sensor on board Meteosat Second Generation platform (MSG) based on machine learning techniques that can be exportable to others geostationary platforms and sensors and to any area of the Earth. The sensitivity (SE), specificity (SP) and accuracy (AC) parameters have been analyzed in order to develop the final machine learning algorithm taking into account the preferences and final use of the predicted data.
Yang, Miin-Shen; Lin, Karen Chia-Ren; Liu, Hsiu-Chih; Lirng, Jiing-Feng
2007-02-01
In this article, we propose batch-type learning vector quantization (LVQ) segmentation techniques for the magnetic resonance (MR) images. Magnetic resonance imaging (MRI) segmentation is an important technique to differentiate abnormal and normal tissues in MR image data. The proposed LVQ segmentation techniques are compared with the generalized Kohonen's competitive learning (GKCL) methods, which were proposed by Lin et al. [Magn Reson Imaging 21 (2003) 863-870]. Three MRI data sets of real cases are used in this article. The first case is from a 2-year-old girl who was diagnosed with retinoblastoma in her left eye. The second case is from a 55-year-old woman who developed complete left side oculomotor palsy immediately after a motor vehicle accident. The third case is from an 84-year-old man who was diagnosed with Alzheimer disease (AD). Our comparisons are based on sensitivity of algorithm parameters, the quality of MRI segmentation with the contrast-to-noise ratio and the accuracy of the region of interest tissue. Overall, the segmentation results from batch-type LVQ algorithms present good accuracy and quality of the segmentation images, and also flexibility of algorithm parameters in all the comparison consequences. The results support that the proposed batch-type LVQ algorithms are better than the previous GKCL algorithms. Specifically, the proposed fuzzy-soft LVQ algorithm works well in segmenting AD MRI data set to accurately measure the hippocampus volume in AD MR images.
A semi-learning algorithm for noise rejection: an fNIRS study on ADHD children
Sutoko, Stephanie; Funane, Tsukasa; Katura, Takusige; Sato, Hiroki; Kiguchi, Masashi; Maki, Atsushi; Monden, Yukifumi; Nagashima, Masako; Yamagata, Takanori; Dan, Ippeita
2017-02-01
In pediatrics studies, the quality of functional near infrared spectroscopy (fNIRS) signals is often reduced by motion artifacts. These artifacts likely mislead brain functionality analysis, causing false discoveries. While noise correction methods and their performance have been investigated, these methods require several parameter assumptions that apparently result in noise overfitting. In contrast, the rejection of noisy signals serves as a preferable method because it maintains the originality of the signal waveform. Here, we describe a semi-learning algorithm to detect and eliminate noisy signals. The algorithm dynamically adjusts noise detection according to the predetermined noise criteria, which are spikes, unusual activation values (averaged amplitude signals within the brain activation period), and high activation variances (among trials). Criteria were sequentially organized in the algorithm and orderly assessed signals based on each criterion. By initially setting an acceptable rejection rate, particular criteria causing excessive data rejections are neglected, whereas others with tolerable rejections practically eliminate noises. fNIRS data measured during the attention response paradigm (oddball task) in children with attention deficit/hyperactivity disorder (ADHD) were utilized to evaluate and optimize the algorithm's performance. This algorithm successfully substituted the visual noise identification done in the previous studies and consistently found significantly lower activation of the right prefrontal and parietal cortices in ADHD patients than in typical developing children. Thus, we conclude that the semi-learning algorithm confers more objective and standardized judgment for noise rejection and presents a promising alternative to visual noise rejection
LMS learning algorithms: misconceptions and new results on converence.
Wang, Z Q; Manry, M T; Schiano, J L
2000-01-01
The Widrow-Hoff delta rule is one of the most popular rules used in training neural networks. It was originally proposed for the ADALINE, but has been successfully applied to a few nonlinear neural networks as well. Despite its popularity, there exist a few misconceptions on its convergence properties. In this paper we consider repetitive learning (i.e., a fixed set of samples are used for training) and provide an in-depth analysis in the least mean square (LMS) framework. Our main result is that contrary to common belief, the nonbatch Widrow-Hoff rule does not converge in general. It converges only to a limit cycle.
Algorithms for Learning Preferences for Sets of Objects
Wagstaff, Kiri L.; desJardins, Marie; Eaton, Eric
2010-01-01
A method is being developed that provides for an artificial-intelligence system to learn a user's preferences for sets of objects and to thereafter automatically select subsets of objects according to those preferences. The method was originally intended to enable automated selection, from among large sets of images acquired by instruments aboard spacecraft, of image subsets considered to be scientifically valuable enough to justify use of limited communication resources for transmission to Earth. The method is also applicable to other sets of objects: examples of sets of objects considered in the development of the method include food menus, radio-station music playlists, and assortments of colored blocks for creating mosaics. The method does not require the user to perform the often-difficult task of quantitatively specifying preferences; instead, the user provides examples of preferred sets of objects. This method goes beyond related prior artificial-intelligence methods for learning which individual items are preferred by the user: this method supports a concept of setbased preferences, which include not only preferences for individual items but also preferences regarding types and degrees of diversity of items in a set. Consideration of diversity in this method involves recognition that members of a set may interact with each other in the sense that when considered together, they may be regarded as being complementary, redundant, or incompatible to various degrees. The effects of such interactions are loosely summarized in the term portfolio effect. The learning method relies on a preference representation language, denoted DD-PREF, to express set-based preferences. In DD-PREF, a preference is represented by a tuple that includes quality (depth) functions to estimate how desired a specific value is, weights for each feature preference, the desired diversity of feature values, and the relative importance of diversity versus depth. The system applies statistical
Computational Modeling of Teaching and Learning through Application of Evolutionary Algorithms
Directory of Open Access Journals (Sweden)
Richard Lamb
2015-09-01
Full Text Available Within the mind, there are a myriad of ideas that make sense within the bounds of everyday experience, but are not reflective of how the world actually exists; this is particularly true in the domain of science. Classroom learning with teacher explanation are a bridge through which these naive understandings can be brought in line with scientific reality. The purpose of this paper is to examine how the application of a Multiobjective Evolutionary Algorithm (MOEA can work in concert with an existing computational-model to effectively model critical-thinking in the science classroom. An evolutionary algorithm is an algorithm that iteratively optimizes machine learning based computational models. The research question is, does the application of an evolutionary algorithm provide a means to optimize the Student Task and Cognition Model (STAC-M and does the optimized model sufficiently represent and predict teaching and learning outcomes in the science classroom? Within this computational study, the authors outline and simulate the effect of teaching on the ability of a “virtual” student to solve a Piagetian task. Using the Student Task and Cognition Model (STAC-M a computational model of student cognitive processing in science class developed in 2013, the authors complete a computational experiment which examines the role of cognitive retraining on student learning. Comparison of the STAC-M and the STAC-M with inclusion of the Multiobjective Evolutionary Algorithm shows greater success in solving the Piagetian science-tasks post cognitive retraining with the Multiobjective Evolutionary Algorithm. This illustrates the potential uses of cognitive and neuropsychological computational modeling in educational research. The authors also outline the limitations and assumptions of computational modeling.
Freezing increment in keratophakia.
Swinger, C A; Wisnicki, H J
In homoplastic keratomileusis, keratophakia, and epikeratophakia, the corneal tissue that provides the final refractive lenticule undergoes a conformational change when frozen. Because corneal tissue is composed primarily of water, an assumed value of 9.08% (approximate volumic percentage expansion of water when frozen) is frequently used for the increase in thickness, or freezing increment, rather than measuring it directly. We evaluated 32 cases of clinical keratophakia and found the increase in thickness to average 37 +/- 21%. In this series of 32 cases, the percentage of patients with a greater than 4 D residual refractive error was 16%. If an assumed freezing increment of 9.08% had been used, the percentage would have been 28%, with two-thirds of these 28% manifesting a marked undercorrection. Because of a lack of studies documenting the behavior of corneal tissue following cryoprotection and freezing, it is suggested that measurements be taken during homoplastic surgery to minimize the potential for significant inaccuracy in obtaining the desired optic result.
Efficient Actor-Critic Algorithm with Hierarchical Model Learning and Planning
Fu, QiMing
2016-01-01
To improve the convergence rate and the sample efficiency, two efficient learning methods AC-HMLP and RAC-HMLP (AC-HMLP with ℓ2-regularization) are proposed by combining actor-critic algorithm with hierarchical model learning and planning. The hierarchical models consisting of the local and the global models, which are learned at the same time during learning of the value function and the policy, are approximated by local linear regression (LLR) and linear function approximation (LFA), respectively. Both the local model and the global model are applied to generate samples for planning; the former is used only if the state-prediction error does not surpass the threshold at each time step, while the latter is utilized at the end of each episode. The purpose of taking both models is to improve the sample efficiency and accelerate the convergence rate of the whole algorithm through fully utilizing the local and global information. Experimentally, AC-HMLP and RAC-HMLP are compared with three representative algorithms on two Reinforcement Learning (RL) benchmark problems. The results demonstrate that they perform best in terms of convergence rate and sample efficiency. PMID:27795704
Exploiting Bivariate Dependencies to Speedup Structure Learning in Bayesian Optimization Algorithm
Institute of Scientific and Technical Information of China (English)
Amin Nikanjam; Adel Rahmani
2012-01-01
Bayesian optimization algorithm (BOA) is one of the successful and widely used estimation of distribution algorithms (EDAs) which have been employed to solve different optimization problems.In EDAs,a model is learned from the selected population that encodes interactions among problem variables.New individuals are generated by sampling the model and incorporated into the population.Different probabilistic models have been used in EDAs to learn interactions.Bayesian network (BN) is a well-known graphical model which is used in BOA.Learning a proper model in EDAs and particularly in BOA is distinguished as a computationally expensive task.Different methods have been proposed in the literature to improve the complexity of model building in EDAs.This paper employs bivariate dependencies to learn accurate BNs in BOA efficiently.The proposed approach extracts the bivariate dependencies using an appropriate pairwise interaction-detection metric.Due to the static structure of the underlying problems,these dependencies are used in each generation of BOA to learn an accurate network.By using this approach,the computational cost of model building is reduced dramatically.Various optimization problems are selected to be solved by the algorithm.The experimental results show that the proposed approach successfully finds the optimum in problems with different types of interactions efficiently.Significant speedups are observed in the model building procedure as well.
Gaur, Pallavi; Chaturvedi, Anoop
2017-07-22
The clustering pattern and motifs give immense information about any biological data. An application of machine learning algorithms for clustering and candidate motif detection in miRNAs derived from exosomes is depicted in this paper. Recent progress in the field of exosome research and more particularly regarding exosomal miRNAs has led much bioinformatic-based research to come into existence. The information on clustering pattern and candidate motifs in miRNAs of exosomal origin would help in analyzing existing, as well as newly discovered miRNAs within exosomes. Along with obtaining clustering pattern and candidate motifs in exosomal miRNAs, this work also elaborates the usefulness of the machine learning algorithms that can be efficiently used and executed on various programming languages/platforms. Data were clustered and sequence candidate motifs were detected successfully. The results were compared and validated with some available web tools such as 'BLASTN' and 'MEME suite'. The machine learning algorithms for aforementioned objectives were applied successfully. This work elaborated utility of machine learning algorithms and language platforms to achieve the tasks of clustering and candidate motif detection in exosomal miRNAs. With the information on mentioned objectives, deeper insight would be gained for analyses of newly discovered miRNAs in exosomes which are considered to be circulating biomarkers. In addition, the execution of machine learning algorithms on various language platforms gives more flexibility to users to try multiple iterations according to their requirements. This approach can be applied to other biological data-mining tasks as well.
Think big: learning contexts, algorithms and data science
Directory of Open Access Journals (Sweden)
Baldassarre Michele
2016-12-01
Full Text Available Due to the increasing growth in available data in recent years, all areas of research and the managements of institutions and organisations, specifically schools and universities, feel the need to give meaning to this availability of data. This article, after a brief reference to the definition of big data, intends to focus attention and reflection on their type to proceed to an extension of their characterisation. One of the hubs to make feasible the use of Big Data in operational contexts is to give a theoretical basis to which to refer. The Data, Information, Knowledge and Wisdom (DIKW model correlates these four aspects, concluding in Data Science, which in many ways could revolutionise the established pattern of scientific investigation. The Learning Analytics applications on online learning platforms can be tools for evaluating the quality of teaching. And that is where some problems arise. It becomes necessary to handle with care the available data. Finally, a criterion for deciding whether it makes sense to think of an analysis based on Big Data can be to think about the interpretability and relevance in relation to both institutional and personal processes.
Wang, Donghao; Wan, Jiangwen; Chen, Junying; Zhang, Qiang
2016-09-22
To adapt to sense signals of enormous diversities and dynamics, and to decrease the reconstruction errors caused by ambient noise, a novel online dictionary learning method-based compressive data gathering (ODL-CDG) algorithm is proposed. The proposed dictionary is learned from a two-stage iterative procedure, alternately changing between a sparse coding step and a dictionary update step. The self-coherence of the learned dictionary is introduced as a penalty term during the dictionary update procedure. The dictionary is also constrained with sparse structure. It's theoretically demonstrated that the sensing matrix satisfies the restricted isometry property (RIP) with high probability. In addition, the lower bound of necessary number of measurements for compressive sensing (CS) reconstruction is given. Simulation results show that the proposed ODL-CDG algorithm can enhance the recovery accuracy in the presence of noise, and reduce the energy consumption in comparison with other dictionary based data gathering methods.
Institute of Scientific and Technical Information of China (English)
Gui-xia Liu; Wei Feng; Han Wang; Lei Liu; Chun-guang Zhou
2009-01-01
In the post-genomic biology era, the reconstruction of gene regulatory networks from microarray gene expression data is very important to understand the underlying biological system, and it has been a challenging task in bioinformatics. The Bayesian network model has been used in reconstructing the gene regulatory network for its advantages, but how to determine the network structure and parameters is still important to be explored. This paper proposes a two-stage structure learning algorithm which integrates immune evolution algorithm to build a Bayesian network .The new algorithm is evaluated with the use of both simulated and yeast cell cycle data. The experimental results indicate that the proposed algorithm can find many of the known real regulatory relationships from literature and predict the others unknown with high validity and accuracy.
Night-Time Vehicle Detection Algorithm Based on Visual Saliency and Deep Learning
Directory of Open Access Journals (Sweden)
Yingfeng Cai
2016-01-01
Full Text Available Night vision systems get more and more attention in the field of automotive active safety field. In this area, a number of researchers have proposed far-infrared sensor based night-time vehicle detection algorithm. However, existing algorithms have low performance in some indicators such as the detection rate and processing time. To solve this problem, we propose a far-infrared image vehicle detection algorithm based on visual saliency and deep learning. Firstly, most of the nonvehicle pixels will be removed with visual saliency computation. Then, vehicle candidate will be generated by using prior information such as camera parameters and vehicle size. Finally, classifier trained with deep belief networks will be applied to verify the candidates generated in last step. The proposed algorithm is tested in around 6000 images and achieves detection rate of 92.3% and processing time of 25 Hz which is better than existing methods.
An Orthogonal Learning Differential Evolution Algorithm for Remote Sensing Image Registration
Directory of Open Access Journals (Sweden)
Wenping Ma
2014-01-01
Full Text Available We introduce an area-based method for remote sensing image registration. We use orthogonal learning differential evolution algorithm to optimize the similarity metric between the reference image and the target image. Many local and global methods have been used to achieve the optimal similarity metric in the last few years. Because remote sensing images are usually influenced by large distortions and high noise, local methods will fail in some cases. For this reason, global methods are often required. The orthogonal learning (OL strategy is efficient when searching in complex problem spaces. In addition, it can discover more useful information via orthogonal experimental design (OED. Differential evolution (DE is a heuristic algorithm. It has shown to be efficient in solving the remote sensing image registration problem. So orthogonal learning differential evolution algorithm (OLDE is efficient for many optimization problems. The OLDE method uses the OL strategy to guide the DE algorithm to discover more useful information. Experiments show that the OLDE method is more robust and efficient for registering remote sensing images.
Narula, Sukrit; Shameer, Khader; Salem Omar, Alaa Mabrouk; Dudley, Joel T; Sengupta, Partho P
2016-11-29
Machine-learning models may aid cardiac phenotypic recognition by using features of cardiac tissue deformation. This study investigated the diagnostic value of a machine-learning framework that incorporates speckle-tracking echocardiographic data for automated discrimination of hypertrophic cardiomyopathy (HCM) from physiological hypertrophy seen in athletes (ATH). Expert-annotated speckle-tracking echocardiographic datasets obtained from 77 ATH and 62 HCM patients were used for developing an automated system. An ensemble machine-learning model with 3 different machine-learning algorithms (support vector machines, random forests, and artificial neural networks) was developed and a majority voting method was used for conclusive predictions with further K-fold cross-validation. Feature selection using an information gain (IG) algorithm revealed that volume was the best predictor for differentiating between HCM ands. ATH (IG = 0.24) followed by mid-left ventricular segmental (IG = 0.134) and average longitudinal strain (IG = 0.131). The ensemble machine-learning model showed increased sensitivity and specificity compared with early-to-late diastolic transmitral velocity ratio (p 13 mm. In this subgroup analysis, the automated model continued to show equal sensitivity, but increased specificity relative to early-to-late diastolic transmitral velocity ratio, e', and strain. Our results suggested that machine-learning algorithms can assist in the discrimination of physiological versus pathological patterns of hypertrophic remodeling. This effort represents a step toward the development of a real-time, machine-learning-based system for automated interpretation of echocardiographic images, which may help novice readers with limited experience. Copyright © 2016 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.
Zhou, Guoxu; Yang, Zuyuan; Xie, Shengli; Yang, Jun-Mei
2011-04-01
Online blind source separation (BSS) is proposed to overcome the high computational cost problem, which limits the practical applications of traditional batch BSS algorithms. However, the existing online BSS methods are mainly used to separate independent or uncorrelated sources. Recently, nonnegative matrix factorization (NMF) shows great potential to separate the correlative sources, where some constraints are often imposed to overcome the non-uniqueness of the factorization. In this paper, an incremental NMF with volume constraint is derived and utilized for solving online BSS. The volume constraint to the mixing matrix enhances the identifiability of the sources, while the incremental learning mode reduces the computational cost. The proposed method takes advantage of the natural gradient based multiplication updating rule, and it performs especially well in the recovery of dependent sources. Simulations in BSS for dual-energy X-ray images, online encrypted speech signals, and high correlative face images show the validity of the proposed method.
[Incremental peritoneal dialysis - yes].
Neri, Loris
2012-01-01
The incremental modality at the start of peritoneal dialysis (Incr-DP) is implicit in the definition of adequacy, which is expressed as the sum of dialysis clearance and renal clearance.Theoretically, it is possible to demonstrate that with a glomerular filtration rate at the start of dialysis of 6 mL/min, the minimum Kt/V target of 1.70 indicated by the current guidelines is easily exceeded with both 2-exchange of CAPD (incremental CAPD) and APD of 3 or 4 weekly sessions (Incr-APD), with a daytime icodextrin dwell. The GSDP (Peritoneal Dialysis Study Group) census data suggest that Incr-DP favors the choice of peritoneal dialysis. Although limited to a few studies with a relatively small number of patients, data show that Incr- CAPD is associated with a better quality of life, the achievement of Kt/V targets, and satisfactory ultrafiltration. The clearance of medium molecules is equivalent in Incr-DP and full-dose PD as it depends on the duration of the dwell and not on the number of exchanges. The maintenance of body weight, protein intake and peritoneal permeability may be explained by the lower glucose load with Incr-DP. The preservation of residual renal function is similar to that recorded with full-dose PD, while the peritonitis rate seems to be lower. The favorable results reported in the literature and the indications of the most recent guidelines about the importance of reducing the exposure to glucose to a minimum and safeguarding the patient's quality of life in our opinion further justify the use of Incr-DP.
Incremental activity modeling in multiple disjoint cameras.
Loy, Chen Change; Xiang, Tao; Gong, Shaogang
2012-09-01
Activity modeling and unusual event detection in a network of cameras is challenging, particularly when the camera views are not overlapped. We show that it is possible to detect unusual events in multiple disjoint cameras as context-incoherent patterns through incremental learning of time delayed dependencies between distributed local activities observed within and across camera views. Specifically, we model multicamera activities using a Time Delayed Probabilistic Graphical Model (TD-PGM) with different nodes representing activities in different decomposed regions from different views and the directed links between nodes encoding their time delayed dependencies. To deal with visual context changes, we formulate a novel incremental learning method for modeling time delayed dependencies that change over time. We validate the effectiveness of the proposed approach using a synthetic data set and videos captured from a camera network installed at a busy underground station.
A Heuristic Algorithm for Planning Personalized Learning Paths for Context-Aware Ubiquitous Learning
Hwang, Gwo-Jen; Kuo, Fan-Ray; Yin, Peng-Yeng; Chuang, Kuo-Hsien
2010-01-01
In a context-aware ubiquitous learning environment, learning systems can detect students' learning behaviors in the real-world with the help of context-aware (sensor) technology; that is, students can be guided to observe or operate real-world objects with personalized support from the digital world. In this study, an optimization problem that…
A Distributed Algorithm for Parallel Multi-task Allocation Based on Profit Sharing Learning
Institute of Scientific and Technical Information of China (English)
SU Zhao-Pin; JIANG Jian-Guo; LIANG Chang-Yong; ZHANG Guo-Fu
2011-01-01
Task allocation via coalition formation is a fundanental research challenge in several application domains of multi-agent systems (MAS),such as resource allocation,disaster response management,and so on.It mainly deals with how to allocate many unresolved tasks to groups of agents in a distributed manner.In this paper,we propose a distributed parallel multi-task allocation algorithm among self-organizing and self-learning agents.To tackle the situation,we disperse agents and tanks geographically in two-dimensional cells,and then introduce profit sharing learning (PSL) for a single agent to search its tasks by continual self-learuing.We also present strategies for communication and negotiation among agents to allocate real workload to every tasked agent.Finally,to evaluate the effectiveness of the proposed algorithm,we compare it with Shehory and Kraus' distributed task allocation algorithm which were discussed by many researchers in recent years.Experimental results show that the proposed algorithm can quickly form a solving coalition for every task.Moreover,the proposed algorithm can specifically tell us the real workload of every tasked agent,and thus can provide a specific and significant reference for practical control tasks.
Prediction of Employee Turnover in Organizations using Machine Learning Algorithms
Directory of Open Access Journals (Sweden)
Rohit Punnoose
2016-10-01
Full Text Available Employee turnover has been identified as a key issue for organizations because of its adverse impact on work place productivity and long term growth strategies. To solve this problem, organizations use machine learning techniques to predict employee turnover. Accurate predictions enable organizations to take action for retention or succession planning of employees. However, the data for this modeling problem comes from HR Information Systems (HRIS; these are typically under-funded compared to the Information Systems of other domains in the organization which are directly related to its priorities. This leads to the prevalence of noise in the data that renders predictive models prone to over-fitting and hence inaccurate. This is the key challenge that is the focus of this paper, and one that has not been addressed historically. The novel contribution of this paper is to explore the application of Extreme Gradient Boosting (XGBoost technique which is more robust because of its regularization formulation. Data from the HRIS of a global retailer is used to compare XGBoost against six historically used supervised classifiers and demonstrate its significantly higher accuracy for predicting employee turnover.
Network Intrusion Detection System Based On Machine Learning Algorithms
Directory of Open Access Journals (Sweden)
Vipin Das
2010-12-01
Full Text Available Network and system security is of paramount importance in the present data communication environment. Hackers and intruders can create many successful attempts to cause the crash of the networks and web services by unauthorized intrusion. New threats and associated solutions to prevent these threats are emerging together with the secured system evolution. Intrusion Detection Systems (IDS are one of these solutions. The main function of Intrusion Detection System is to protect the resources from threats. It analyzes and predicts the behaviours of users, and then these behaviours will be considered an attack or a normal behaviour. We use Rough Set Theory (RST and Support Vector Machine (SVM to detect network intrusions. First, packets are captured from the network, RST is used to pre-process the data and reduce the dimensions. The features selected by RST will be sent to SVM model to learn and test respectively. The method is effective to decrease the space density of data. The experiments compare the results with Principal Component Analysis (PCA and show RST and SVM schema could reduce the false positive rate and increase the accuracy.
Institute of Scientific and Technical Information of China (English)
WU Jian-sheng; JIN Long
2009-01-01
Because of the difficulty in deciding on the structure of BP neural network in operational meteorological application and the tendency tbr the network to transform to an issue of local solution,a hybrid Particle Swarm Optimization Algorithm based on Artificial Neural Network (PSO-BP) model is proposed for monthly mean rainfall of the whole area of Guangxi. It combines Particle Swarm Optimization (PSO) with BP,that is,the number of hidden nodes and connection weights are optimized by the implementation of PSO operation. The method produces a better network architecture and initial connection weights,trains the traditional backward propagation again by training samples. The ensemble strategy is carried out for the linear programming to calculate the best weights based on the "east sum of the error absolute value" as the optimal rule. The weighted coefficient of each ensemble individual is obtained. The results show that the method can effectively improve learning and generalization ability of the neural network.
Directory of Open Access Journals (Sweden)
Marc Wieland
2014-03-01
Full Text Available In this study, a classification and performance evaluation framework for the recognition of urban patterns in medium (Landsat ETM, TM and MSS and very high resolution (WorldView-2, Quickbird, Ikonos multi-spectral satellite images is presented. The study aims at exploring the potential of machine learning algorithms in the context of an object-based image analysis and to thoroughly test the algorithm’s performance under varying conditions to optimize their usage for urban pattern recognition tasks. Four classification algorithms, Normal Bayes, K Nearest Neighbors, Random Trees and Support Vector Machines, which represent different concepts in machine learning (probabilistic, nearest neighbor, tree-based, function-based, have been selected and implemented on a free and open-source basis. Particular focus is given to assess the generalization ability of machine learning algorithms and the transferability of trained learning machines between different image types and image scenes. Moreover, the influence of the number and choice of training data, the influence of the size and composition of the feature vector and the effect of image segmentation on the classification accuracy is evaluated.
Directory of Open Access Journals (Sweden)
Zhibo Zhai
2015-01-01
Full Text Available Cutting parameter optimization dramatically affects the production time, cost, profit rate, and the quality of the final products, in milling operations. Aiming to select the optimum machining parameters in multitool milling operations such as corner milling, face milling, pocket milling, and slot milling, this paper presents a novel version of TLBO, TLBO with dynamic assignment learning strategy (DATLBO, in which all the learners are divided into three categories based on their results in “Learner Phase”: good learners, moderate learners, and poor ones. Good learners are self-motivated and try to learn by themselves; each moderate learner uses a probabilistic approach to select one of good learners to learn; each poor learner also uses a probabilistic approach to select several moderate learners to learn. The CEC2005 contest benchmark problems are first used to illustrate the effectiveness of the proposed algorithm. Finally, the DATLBO algorithm is applied to a multitool milling process based on maximum profit rate criterion with five practical technological constraints. The unit time, unit cost, and profit rate from the Handbook (HB, Feasible Direction (FD method, Genetic Algorithm (GA method, five other TLBO variants, and DATLBO are compared, illustrating that the proposed approach is more effective than HB, FD, GA, and five other TLBO variants.
A Comparison Study of Machine Learning Based Algorithms for Fatigue Crack Growth Calculation.
Wang, Hongxun; Zhang, Weifang; Sun, Fuqiang; Zhang, Wei
2017-05-18
The relationships between the fatigue crack growth rate ( d a / d N ) and stress intensity factor range ( Δ K ) are not always linear even in the Paris region. The stress ratio effects on fatigue crack growth rate are diverse in different materials. However, most existing fatigue crack growth models cannot handle these nonlinearities appropriately. The machine learning method provides a flexible approach to the modeling of fatigue crack growth because of its excellent nonlinear approximation and multivariable learning ability. In this paper, a fatigue crack growth calculation method is proposed based on three different machine learning algorithms (MLAs): extreme learning machine (ELM), radial basis function network (RBFN) and genetic algorithms optimized back propagation network (GABP). The MLA based method is validated using testing data of different materials. The three MLAs are compared with each other as well as the classical two-parameter model ( K * approach). The results show that the predictions of MLAs are superior to those of K * approach in accuracy and effectiveness, and the ELM based algorithms show overall the best agreement with the experimental data out of the three MLAs, for its global optimization and extrapolation ability.
Sha, Daohang
2010-01-01
Back-propagation with gradient method is the most popular learning algorithm for feed-forward neural networks. However, it is critical to determine a proper fixed learning rate for the algorithm. In this paper, an optimized recursive algorithm is presented for online learning based on matrix operation and optimization methods analytically, which can avoid the trouble to select a proper learning rate for the gradient method. The proof of weak convergence of the proposed algorithm also is given. Although this approach is proposed for three-layer, feed-forward neural networks, it could be extended to multiple layer feed-forward neural networks. The effectiveness of the proposed algorithms applied to the identification of behavior of a two-input and two-output non-linear dynamic system is demonstrated by simulation experiments.
Toledo, A; Pinzolas, M; Ibarrola, J J; Lera, G
2005-07-01
In this letter, an improvement of the recently developed neighborhood-based Levenberg-Marquardt (NBLM) algorithm is proposed and tested for neural network (NN) training. The algorithm is modified by allowing local adaptation of a different learning coefficient for each neighborhood. This simple add-in to the NBLM training method significantly increases the efficiency of the training episodes carried out with small neighborhood sizes, thus, allowing important savings in memory occupation and computational time while obtaining better performance than the original Levenberg-Marquardt (LM) and NBLM methods.
Dynamic learning rates algorithm for BPNN to forecast time series of dam security
Institute of Scientific and Technical Information of China (English)
无
2007-01-01
Time series data of dam security have a large number of observed values and should be forecasted accurately in time.Neural networks have the powerful approach ablilities of arbitrary functions and have been broadly utilized in many domains.In this paper,a dynamic learning rate training algorithm of hack-propagation neural networks for time series forecasting is proposed and the networks with this algorithm are built to forecast time series of dam security.The application results demonostrate the efficiency of modelling and the effictiveness of forecasting.
基于支持向量机的分段线性学习方法%A Subsection Learning Algorithm Based on Support Vector Machines
Institute of Scientific and Technical Information of China (English)
杨强; 吴中福; 王茜
2003-01-01
In this paper, we discuss drawback of traditional subsection learning algorithm in pattern recognition and exiting support vector machines (including kernel functions), the necessity of using subsection learning algorithm based on support vector machines as well as. In turn, a subsection learning algorithm based on support vector machines, is proposed in this paper.
Cue-based and algorithmic learning in common carp: A possible link to stress coping style.
Mesquita, Flavia Oliveira; Borcato, Fabio Luiz; Huntingford, Felicity Ann
2015-06-01
Common carp that had been screened for stress coping style using a standard behavioural test (response to a novel environment) were given a learning task in which food was concealed in one of two compartments, its location randomised between trials and its presence in a given compartment signalled by either a red or a yellow light. All the fish learned to find food quickly, but did so in different ways. Fifty five percent learned to use the light cue to locate food; the remainder achieved the same result by developing a fixed movement routine. To explore this variation, we related learning strategy to stress coping style. Time to find food fell identically with successive trials in carp classified as reactive or proactive, but reactive fish tended to follow the light cue and proactive fish to adopt a fixed routine. Among fish that learned to follow the light, reactive individuals took fewer trials to reach the learning criterion than did proactive fish. These results add to the growing body of information on within-species variation in learning strategies and suggest a possible influence of stress coping style on the use of associative learning as opposed to algorithmic searching during foraging. Copyright © 2015 Elsevier B.V. All rights reserved.
A novel neural-inspired learning algorithm with application to clinical risk prediction.
Tay, Darwin; Poh, Chueh Loo; Kitney, Richard I
2015-04-01
Clinical risk prediction - the estimation of the likelihood an individual is at risk of a disease - is a coveted and exigent clinical task, and a cornerstone to the recommendation of life saving management strategies. This is especially important for individuals at risk of cardiovascular disease (CVD) given the fact that it is the leading causes of death in many developed counties. To this end, we introduce a novel learning algorithm - a key factor that influences the performance of machine learning-based prediction models - and utilities it to develop CVD risk prediction tool. This novel neural-inspired algorithm, called the Artificial Neural Cell System for classification (ANCSc), is inspired by mechanisms that develop the brain and empowering it with capabilities such as information processing/storage and recall, decision making and initiating actions on external environment. Specifically, we exploit on 3 natural neural mechanisms responsible for developing and enriching the brain - namely neurogenesis, neuroplasticity via nurturing and apoptosis - when implementing ANCSc algorithm. Benchmark testing was conducted using the Honolulu Heart Program (HHP) dataset and results are juxtaposed with 2 other algorithms - i.e. Support Vector Machine (SVM) and Evolutionary Data-Conscious Artificial Immune Recognition System (EDC-AIRS). Empirical experiments indicate that ANCSc algorithm (statistically) outperforms both SVM and EDC-AIRS algorithms. Key clinical markers identified by ANCSc algorithm include risk factors related to diet/lifestyle, pulmonary function, personal/family/medical history, blood data, blood pressure, and electrocardiography. These clinical markers, in general, are also found to be clinically significant - providing a promising avenue for identifying potential cardiovascular risk factors to be evaluated in clinical trials.
An e-Learning environment for algorithmic: toward an active construction of skills
Directory of Open Access Journals (Sweden)
Abdelghani Babori
2016-07-01
Full Text Available Assimilating an algorithmic course is a persistent problem for many undergraduate students. The major problem faced by students is the lack of problem solving ability and flexibility. Therefore, students are generally passive, unmotivated and unable to mobilize all the acquired knowledge (loops, test, variables, etc. to deal with new encountered problems. Our study is structured around building, step by step, problem solving skills among novice learners. Our approach is based on the use of problem based learning in an e-Learning environment. We begin by establishing a cognitive model which represents knowledge elements, grouped into categories of skills, judged necessary to be appropriated. We then propose a problem built on a concrete situation which aims to actively construct a skill category. We conclude by presenting around the proposed problem a pedagogical scenario for the set of learning activities designed to be incorporated in an E-learning platform.
Monthly prediction of air temperature in Australia and New Zealand with machine learning algorithms
Salcedo-Sanz, S.; Deo, R. C.; Carro-Calvo, L.; Saavedra-Moreno, B.
2016-07-01
Long-term air temperature prediction is of major importance in a large number of applications, including climate-related studies, energy, agricultural, or medical. This paper examines the performance of two Machine Learning algorithms (Support Vector Regression (SVR) and Multi-layer Perceptron (MLP)) in a problem of monthly mean air temperature prediction, from the previous measured values in observational stations of Australia and New Zealand, and climate indices of importance in the region. The performance of the two considered algorithms is discussed in the paper and compared to alternative approaches. The results indicate that the SVR algorithm is able to obtain the best prediction performance among all the algorithms compared in the paper. Moreover, the results obtained have shown that the mean absolute error made by the two algorithms considered is significantly larger for the last 20 years than in the previous decades, in what can be interpreted as a change in the relationship among the prediction variables involved in the training of the algorithms.
A novel compensation-based recurrent fuzzy neural network and its learning algorithm
Institute of Scientific and Technical Information of China (English)
WU Bo; WU Ke; LU JianHong
2009-01-01
Based on detailed atudy on aeveral kinds of fuzzy neural networks, we propose a novel compensation. based recurrent fuzzy neural network (CRFNN) by adding recurrent element and compensatory element to the conventional fuzzy neural network. Then, we propose a sequential learning method for the structure Identification of the CRFNN In order to confirm the fuzzy rules and their correlaUve parameters effectively. Furthermore, we Improve the BP algorithm based on the characteristics of the proposed CRFNN to train the network. By modeling the typical nonlinear systems, we draw the conclusion that the proposed CRFNN has excellent dynamic response and strong learning ability.
Machine Learning Algorithms for $b$-Jet Tagging at the ATLAS Experiment
Paganini, Michela; The ATLAS collaboration
2017-01-01
The separation of b-quark initiated jets from those coming from lighter quark flavours (b-tagging) is a fundamental tool for the ATLAS physics program at the CERN Large Hadron Collider. The most powerful b-tagging algorithms combine information from low-level taggers exploiting reconstructed track and vertex information using a multivariate classifier. The potential of modern Machine Learning techniques such as Recurrent Neural Networks and Deep Learning is explored using simulated events, and compared to that achievable from more traditional classifiers such as boosted decision trees.
Incremental Visualizer for Visible Objects
DEFF Research Database (Denmark)
Bukauskas, Linas; Bøhlen, Michael Hanspeter
This paper discusses the integration of database back-end and visualizer front-end into a one tightly coupled system. The main aim which we achieve is to reduce the data pipeline from database to visualization by using incremental data extraction of visible objects in a fly-through scenarios. We...... also argue that passing only relevant data from the database will substantially reduce the overall load of the visualization system. We propose the system Incremental Visualizer for Visible Objects (IVVO) which considers visible objects and enables incremental visualization along the observer movement...... visibility ranges and show that considering visibility ranges is crucial when considering incremental visible object extraction....
A ciosed-loop algorithm to detect human face using color and reinforcement learning
Institute of Scientific and Technical Information of China (English)
吴东晖; 叶秀清; 顾伟康
2002-01-01
A closed-loop algorithm to detect human face using color information and reinforcement learning is presented in this paper. By using a skin-color selector, the regions with color "like" that of human skin are selected as candidates for human face. In the next stage, the candidates are matched with a face model and given an evaluation of the match degree by the matching module. And if the evaluation of the match result is too low, a reinforcement learning stage will start to search the best parameters of the skin-color selector. It has been tested using many photos of various ethnic groups under various lighting conditions, such as different light source, high light and shadow. And the experiment result proved that this algorithm is robust to the vary-ing lighting conditions and personal conditions.
A closed-loop algorithm to detect human face using color and reinforcement learning
Institute of Scientific and Technical Information of China (English)
无
2002-01-01
A closed-loop algorithm to detect human face using color information and reinforcement learning is presented in this paper. By using a skin-color selector, the regions with color “like" that of human skin are selected as candidates for human face. In the next stage, the candidates are matched with a face model and given an evaluation of the match degree by the matching module. And if the evaluation of the match result is too low, a reinforcement learning stage will start to search the best parameters of the skin-color selector. It has been tested using many photos of various ethnic groups under various lighting conditions, such as different light source, high light and shadow. And the experiment result proved that this algorithm is robust to the varying lighting conditions and personal conditions.
A hybrid manifold learning algorithm for the diagnosis and prognostication of Alzheimer's disease.
Dai, Peng; Gwadry-Sridhar, Femida; Bauer, Michael; Borrie, Michael
The diagnosis of Alzheimer's disease (AD) requires a variety of medical tests, which leads to huge amounts of multivariate heterogeneous data. Such data are difficult to compare, visualize, and analyze due to the heterogeneous nature of medical tests. We present a hybrid manifold learning framework, which embeds the feature vectors in a subspace preserving the underlying pairwise similarity structure, i.e. similar/dissimilar pairs. Evaluation tests are carried out using the neuroimaging and biological data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) in a three-class (normal, mild cognitive impairment, and AD) classification task using support vector machine (SVM). Furthermore, we make extensive comparison with standard manifold learning algorithms, such as Principal Component Analysis (PCA), Principal Component Analysis (PCA), Multidimensional Scaling (MDS), and isometric feature mapping (Isomap). Experimental results show that our proposed algorithm yields an overall accuracy of 85.33% in the three-class task.
A new optical disk driver fine-seek algorithm based on runout learning
Chen, Cheng-Hung; Yen, Jia-Yush
2005-01-01
The eccentricity in the Optical Disk Drive (ODD) is the inevitable deviation of the geometric center of circular tracks from the rotating center of the disk. The resulted "runout" in the drive is thus periodic with disk rotation. To overcome the runout, conventional approach is for the pick-up head to go forward to the target track while shaking with the period runout during track accessing. This paper proposes an integration of the learning algorithm to learn the runout motion with an on-line observer to estimate the track runout during track accessing. The purpose is to allow for online computation of the target track kinematics so that the controller can adjust the accessing strategy to accommodate for the target track behavior. The proposed algorithm is demonstrated to be feasible through experiments applied to the fine jump control for a general optical storage opto-mechenical-electrical-control plant from OES in ITRI.
Incremental Code Clone Detection and Elimination for Erlang Programs
Li, Huiqing; Thompson, Simon
2011-01-01
A well-known bad code smell in refactoring and software maintenance is the existence of code clones, which are code fragments that are identical or similar to one another. This paper describes an approach to incrementally detecting 'similar' code based on the notion of least-general common abstraction, or anti-unification, as well as a framework for user-controlled incremental elimination of code clones within the context of Erlang programs. The clone detection algorithm proposed in this pape...
Towards an incremental maintenance of cyclic association rules
Ahmed, Eya ben
2010-01-01
Recently, the cyclic association rules have been introduced in order to discover rules from items characterized by their regular variation over time. In real life situations, temporal databases are often appended or updated. Rescanning the whole database every time is highly expensive while existing incremental mining techniques can efficiently solve such a problem. In this paper, we propose an incremental algorithm for cyclic association rules maintenance. The carried out experiments of our proposal stress on its efficiency and performance.
Incremental Contingency Planning
Dearden, Richard; Meuleau, Nicolas; Ramakrishnan, Sailesh; Smith, David E.; Washington, Rich
2003-01-01
There has been considerable work in AI on planning under uncertainty. However, this work generally assumes an extremely simple model of action that does not consider continuous time and resources. These assumptions are not reasonable for a Mars rover, which must cope with uncertainty about the duration of tasks, the energy required, the data storage necessary, and its current position and orientation. In this paper, we outline an approach to generating contingency plans when the sources of uncertainty involve continuous quantities such as time and resources. The approach involves first constructing a "seed" plan, and then incrementally adding contingent branches to this plan in order to improve utility. The challenge is to figure out the best places to insert contingency branches. This requires an estimate of how much utility could be gained by building a contingent branch at any given place in the seed plan. Computing this utility exactly is intractable, but we outline an approximation method that back propagates utility distributions through a graph structure similar to that of a plan graph.
Incrementally Exploiting Sentential Association for Email Classification
Institute of Scientific and Technical Information of China (English)
Li Qu; He Yu; Feng Jianlin; Feng Yucai
2006-01-01
A novel association-based algorithm EmailInClass is proposed for incremental Email classification. In view of the fact that the basic semantic unit in an Email is actually a sentence, and the words within the same sentence are typically more semantically related than the words that just appear in the same Email, EmailInClass views a sentence rather than an Email as a transaction. Extensive experiments conducted on benchmark corpora Enron reveal that the effectiveness of EmailInClass is superior to the non-incremental alternatives such as NaiveBayes and SAT-MOD. In addition, the classification rules generated by EmailInClass are human readable and revisable.
DEFF Research Database (Denmark)
Endelt, Benny Ørtoft; Volk, Wolfram
2013-01-01
Feedback control of sheet metal forming operations has been an active research field the last two decades and highly advanced control algorithms have been proposed - controlling both the total blank-holder force and in some cases also the distribution of the blank-holder force. However, there is ......Feedback control of sheet metal forming operations has been an active research field the last two decades and highly advanced control algorithms have been proposed - controlling both the total blank-holder force and in some cases also the distribution of the blank-holder force. However......, the reaction speed may be insufficient compared to the production rate in an industrial application. We propose to design an iterative learning control (ILC) algorithm which can control and update the blank-holder force as well as the distribution of the blank-holder force based on limited geometric data from...
Directory of Open Access Journals (Sweden)
Foulkes Andrea S
2008-11-01
Full Text Available Abstract Background Population-based investigations aimed at uncovering genotype-trait associations often involve high-dimensional genetic polymorphism data as well as information on multiple environmental and clinical parameters. Machine learning (ML algorithms offer a straightforward analytic approach for selecting subsets of these inputs that are most predictive of a pre-defined trait. The performance of these algorithms, however, in the presence of covariates is not well characterized. Methods and Results In this manuscript, we investigate two approaches: Random Forests (RFs and Multivariate Adaptive Regression Splines (MARS. Through multiple simulation studies, the performance under several underlying models is evaluated. An application to a cohort of HIV-1 infected individuals receiving anti-retroviral therapies is also provided. Conclusion Consistent with more traditional regression modeling theory, our findings highlight the importance of considering the nature of underlying gene-covariate-trait relationships before applying ML algorithms, particularly when there is potential confounding or effect mediation.
Nonyane, Bareng A S; Foulkes, Andrea S
2008-11-14
Population-based investigations aimed at uncovering genotype-trait associations often involve high-dimensional genetic polymorphism data as well as information on multiple environmental and clinical parameters. Machine learning (ML) algorithms offer a straightforward analytic approach for selecting subsets of these inputs that are most predictive of a pre-defined trait. The performance of these algorithms, however, in the presence of covariates is not well characterized. In this manuscript, we investigate two approaches: Random Forests (RFs) and Multivariate Adaptive Regression Splines (MARS). Through multiple simulation studies, the performance under several underlying models is evaluated. An application to a cohort of HIV-1 infected individuals receiving anti-retroviral therapies is also provided. Consistent with more traditional regression modeling theory, our findings highlight the importance of considering the nature of underlying gene-covariate-trait relationships before applying ML algorithms, particularly when there is potential confounding or effect mediation.
Simulating Visual Learning and Optical Illusions via a Network-Based Genetic Algorithm
Siu, Theodore; Vivar, Miguel; Shinbrot, Troy
We present a neural network model that uses a genetic algorithm to identify spatial patterns. We show that the model both learns and reproduces common visual patterns and optical illusions. Surprisingly, we find that the illusions generated are a direct consequence of the network architecture used. We discuss the implications of our results and the insights that we gain on how humans fall for optical illusions
Nishizuka, N.; Sugiura, K.; Kubo, Y.; Den, M.; Watari, S.; Ishii, M.
2017-02-01
We developed a flare prediction model using machine learning, which is optimized to predict the maximum class of flares occurring in the following 24 hr. Machine learning is used to devise algorithms that can learn from and make decisions on a huge amount of data. We used solar observation data during the period 2010–2015, such as vector magnetograms, ultraviolet (UV) emission, and soft X-ray emission taken by the Solar Dynamics Observatory and the Geostationary Operational Environmental Satellite. We detected active regions (ARs) from the full-disk magnetogram, from which ∼60 features were extracted with their time differentials, including magnetic neutral lines, the current helicity, the UV brightening, and the flare history. After standardizing the feature database, we fully shuffled and randomly separated it into two for training and testing. To investigate which algorithm is best for flare prediction, we compared three machine-learning algorithms: the support vector machine, k-nearest neighbors (k-NN), and extremely randomized trees. The prediction score, the true skill statistic, was higher than 0.9 with a fully shuffled data set, which is higher than that for human forecasts. It was found that k-NN has the highest performance among the three algorithms. The ranking of the feature importance showed that previous flare activity is most effective, followed by the length of magnetic neutral lines, the unsigned magnetic flux, the area of UV brightening, and the time differentials of features over 24 hr, all of which are strongly correlated with the flux emergence dynamics in an AR.
Marc Wieland; Massimiliano Pittore
2014-01-01
In this study, a classification and performance evaluation framework for the recognition of urban patterns in medium (Landsat ETM, TM and MSS) and very high resolution (WorldView-2, Quickbird, Ikonos) multi-spectral satellite images is presented. The study aims at exploring the potential of machine learning algorithms in the context of an object-based image analysis and to thoroughly test the algorithm’s performance under varying conditions to optimize their usage for urban pattern recognitio...
Piretzidis, Dimitrios; Sra, Gurveer; Karantaidis, George; Sideris, Michael G.
2017-04-01
A new method for identifying correlated errors in Gravity Recovery and Climate Experiment (GRACE) monthly harmonic coefficients has been developed and tested. Correlated errors are present in the differences between monthly GRACE solutions, and can be suppressed using a de-correlation filter. In principle, the de-correlation filter should be implemented only on coefficient series with correlated errors to avoid losing useful geophysical information. In previous studies, two main methods of implementing the de-correlation filter have been utilized. In the first one, the de-correlation filter is implemented starting from a specific minimum order until the maximum order of the monthly solution examined. In the second one, the de-correlation filter is implemented only on specific coefficient series, the selection of which is based on statistical testing. The method proposed in the present study exploits the capabilities of supervised machine learning algorithms such as neural networks and support vector machines (SVMs). The pattern of correlated errors can be described by several numerical and geometric features of the harmonic coefficient series. The features of extreme cases of both correlated and uncorrelated coefficients are extracted and used for the training of the machine learning algorithms. The trained machine learning algorithms are later used to identify correlated errors and provide the probability of a coefficient series to be correlated. Regarding SVMs algorithms, an extensive study is performed with various kernel functions in order to find the optimal training model for prediction. The selection of the optimal training model is based on the classification accuracy of the trained SVM algorithm on the same samples used for training. Results show excellent performance of all algorithms with a classification accuracy of 97% - 100% on a pre-selected set of training samples, both in the validation stage of the training procedure and in the subsequent use of
Learning algorithm and application of quantum BP neural networks based on universal quantum gates
Institute of Scientific and Technical Information of China (English)
无
2008-01-01
A quantum BP neural networks model with learning algorithm is proposed.First,based on the universality of single qubit rotation gate and two-qubit controlled-NOT gate,a quantum neuron model is constructed,which is composed of input,phase rotation,aggregation,reversal rotation and output.In this model,the input is described by qubits,and the output is given by the probability of the state in which |1＞ is observed.The phase rotation and the reversal rotation are performed by the universal quantum gates.Secondly,the quantum BP neural networks model is constructed,in which the output layer and the hide layer are quantum neurons.With the application of the gradient descent algorithm,a learning algorithm of the model is proposed,and the continuity of the model is proved.It is shown that this model and algorithm are superior to the conventional BP networks in three aspects: convergence speed,convergence rate and robustness,by two application examples of pattern recognition and function approximation.
Premaladha, J; Ravichandran, K S
2016-04-01
Dermoscopy is a technique used to capture the images of skin, and these images are useful to analyze the different types of skin diseases. Malignant melanoma is a kind of skin cancer whose severity even leads to death. Earlier detection of melanoma prevents death and the clinicians can treat the patients to increase the chances of survival. Only few machine learning algorithms are developed to detect the melanoma using its features. This paper proposes a Computer Aided Diagnosis (CAD) system which equips efficient algorithms to classify and predict the melanoma. Enhancement of the images are done using Contrast Limited Adaptive Histogram Equalization technique (CLAHE) and median filter. A new segmentation algorithm called Normalized Otsu's Segmentation (NOS) is implemented to segment the affected skin lesion from the normal skin, which overcomes the problem of variable illumination. Fifteen features are derived and extracted from the segmented images are fed into the proposed classification techniques like Deep Learning based Neural Networks and Hybrid Adaboost-Support Vector Machine (SVM) algorithms. The proposed system is tested and validated with nearly 992 images (malignant & benign lesions) and it provides a high classification accuracy of 93 %. The proposed CAD system can assist the dermatologists to confirm the decision of the diagnosis and to avoid excisional biopsies.
How the machine ‘thinks’: Understanding opacity in machine learning algorithms
Directory of Open Access Journals (Sweden)
Jenna Burrell
2016-01-01
Full Text Available This article considers the issue of opacity as a problem for socially consequential mechanisms of classification and ranking, such as spam filters, credit card fraud detection, search engines, news trends, market segmentation and advertising, insurance or loan qualification, and credit scoring. These mechanisms of classification all frequently rely on computational algorithms, and in many cases on machine learning algorithms to do this work. In this article, I draw a distinction between three forms of opacity: (1 opacity as intentional corporate or state secrecy, (2 opacity as technical illiteracy, and (3 an opacity that arises from the characteristics of machine learning algorithms and the scale required to apply them usefully. The analysis in this article gets inside the algorithms themselves. I cite existing literatures in computer science, known industry practices (as they are publicly presented, and do some testing and manipulation of code as a form of lightweight code audit. I argue that recognizing the distinct forms of opacity that may be coming into play in a given application is a key to determining which of a variety of technical and non-technical solutions could help to prevent harm.
Pardo, Juan; Zamora-Martínez, Francisco; Botella-Rocamora, Paloma
2015-04-21
Time series forecasting is an important predictive methodology which can be applied to a wide range of problems. Particularly, forecasting the indoor temperature permits an improved utilization of the HVAC (Heating, Ventilating and Air Conditioning) systems in a home and thus a better energy efficiency. With such purpose the paper describes how to implement an Artificial Neural Network (ANN) algorithm in a low cost system-on-chip to develop an autonomous intelligent wireless sensor network. The present paper uses a Wireless Sensor Networks (WSN) to monitor and forecast the indoor temperature in a smart home, based on low resources and cost microcontroller technology as the 8051MCU. An on-line learning approach, based on Back-Propagation (BP) algorithm for ANNs, has been developed for real-time time series learning. It performs the model training with every new data that arrive to the system, without saving enormous quantities of data to create a historical database as usual, i.e., without previous knowledge. Consequently to validate the approach a simulation study through a Bayesian baseline model have been tested in order to compare with a database of a real application aiming to see the performance and accuracy. The core of the paper is a new algorithm, based on the BP one, which has been described in detail, and the challenge was how to implement a computational demanding algorithm in a simple architecture with very few hardware resources.
Directory of Open Access Journals (Sweden)
Juan Pardo
2015-04-01
Full Text Available Time series forecasting is an important predictive methodology which can be applied to a wide range of problems. Particularly, forecasting the indoor temperature permits an improved utilization of the HVAC (Heating, Ventilating and Air Conditioning systems in a home and thus a better energy efficiency. With such purpose the paper describes how to implement an Artificial Neural Network (ANN algorithm in a low cost system-on-chip to develop an autonomous intelligent wireless sensor network. The present paper uses a Wireless Sensor Networks (WSN to monitor and forecast the indoor temperature in a smart home, based on low resources and cost microcontroller technology as the 8051MCU. An on-line learning approach, based on Back-Propagation (BP algorithm for ANNs, has been developed for real-time time series learning. It performs the model training with every new data that arrive to the system, without saving enormous quantities of data to create a historical database as usual, i.e., without previous knowledge. Consequently to validate the approach a simulation study through a Bayesian baseline model have been tested in order to compare with a database of a real application aiming to see the performance and accuracy. The core of the paper is a new algorithm, based on the BP one, which has been described in detail, and the challenge was how to implement a computational demanding algorithm in a simple architecture with very few hardware resources.
How the machine ‘thinks’: Understanding opacity in machine learning algorithms
Directory of Open Access Journals (Sweden)
Jenna Burrell
2016-01-01
Full Text Available This article considers the issue of opacity as a problem for socially consequential mechanisms of classification and ranking, such as spam filters, credit card fraud detection, search engines, news trends, market segmentation and advertising, insurance or loan qualification, and credit scoring. These mechanisms of classification all frequently rely on computational algorithms, and in many cases on machine learning algorithms to do this work. In this article, I draw a distinction between three forms of opacity: (1 opacity as intentional corporate or state secrecy, (2 opacity as technical illiteracy, and (3 an opacity that arises from the characteristics of machine learning algorithms and the scale required to apply them usefully. The analysis in this article gets inside the algorithms themselves. I cite existing literatures in computer science, known industry practices (as they are publicly presented, and do some testing and manipulation of code as a form of lightweight code audit. I argue that recognizing the distinct forms of opacity that may be coming into play in a given application is a key to determining which of a variety of technical and non-technical solutions could help to prevent harm.
Analysis of image content recognition algorithm based on sparse coding and machine learning
Xiao, Yu
2017-03-01
This paper presents an image classification algorithm based on spatial sparse coding model and random forest. Firstly, SIFT feature extraction of the image; and then use the sparse encoding theory to generate visual vocabulary based on SIFT features, and using the visual vocabulary of SIFT features into a sparse vector; through the combination of regional integration and spatial sparse vector, the sparse vector gets a fixed dimension is used to represent the image; at last random forest classifier for image sparse vectors for training and testing, using the experimental data set for standard test Caltech-101 and Scene-15. The experimental results show that the proposed algorithm can effectively represent the features of the image and improve the classification accuracy. In this paper, we propose an innovative image recognition algorithm based on image segmentation, sparse coding and multi instance learning. This algorithm introduces the concept of multi instance learning, the image as a multi instance bag, sparse feature transformation by SIFT images as instances, sparse encoding model generation visual vocabulary as the feature space is mapped to the feature space through the statistics on the number of instances in bags, and then use the 1-norm SVM to classify images and generate sample weights to select important image features.
Development of a general learning algorithm with applications in nuclear reactor systems
Energy Technology Data Exchange (ETDEWEB)
Brittain, C.R.; Otaduy, P.J.; Perez, R.B.
1989-12-01
The objective of this study was development of a generalized learning algorithm that can learn to predict a particular feature of a process by observation of a set of representative input examples. The algorithm uses pattern matching and statistical analysis techniques to find a functional relationship between descriptive attributes of the input examples and the feature to be predicted. The algorithm was tested by applying it to a set of examples consisting of performance descriptions for 277 fuel cycles of Oak Ridge National Laboratory's High Flux Isotope Reactor (HFIR). The program learned to predict the critical rod position for the HFIR from core configuration data prior to reactor startup. The functional relationship bases its predictions on initial core reactivity, the number of certain targets placed in the center of the reactor, and the total exposure of the control plates. Twelve characteristic fuel cycle clusters were identified. Nine fuel cycles were diagnosed as having noisy data, and one could not be predicted by the functional relationship. 13 refs., 6 figs.
Zou, Han; Lu, Xiaoxuan; Jiang, Hao; Xie, Lihua
2015-01-15
Nowadays, developing indoor positioning systems (IPSs) has become an attractive research topic due to the increasing demands on location-based service (LBS) in indoor environments. WiFi technology has been studied and explored to provide indoor positioning service for years in view of the wide deployment and availability of existing WiFi infrastructures in indoor environments. A large body of WiFi-based IPSs adopt fingerprinting approaches for localization. However, these IPSs suffer from two major problems: the intensive costs of manpower and time for offline site survey and the inflexibility to environmental dynamics. In this paper, we propose an indoor localization algorithm based on an online sequential extreme learning machine (OS-ELM) to address the above problems accordingly. The fast learning speed of OS-ELM can reduce the time and manpower costs for the offline site survey. Meanwhile, its online sequential learning ability enables the proposed localization algorithm to adapt in a timely manner to environmental dynamics. Experiments under specific environmental changes, such as variations of occupancy distribution and events of opening or closing of doors, are conducted to evaluate the performance of OS-ELM. The simulation and experimental results show that the proposed localization algorithm can provide higher localization accuracy than traditional approaches, due to its fast adaptation to various environmental dynamics.
Directory of Open Access Journals (Sweden)
Han Zou
2015-01-01
Full Text Available Nowadays, developing indoor positioning systems (IPSs has become an attractive research topic due to the increasing demands on location-based service (LBS in indoor environments. WiFi technology has been studied and explored to provide indoor positioning service for years in view of the wide deployment and availability of existing WiFi infrastructures in indoor environments. A large body of WiFi-based IPSs adopt fingerprinting approaches for localization. However, these IPSs suffer from two major problems: the intensive costs of manpower and time for offline site survey and the inflexibility to environmental dynamics. In this paper, we propose an indoor localization algorithm based on an online sequential extreme learning machine (OS-ELM to address the above problems accordingly. The fast learning speed of OS-ELM can reduce the time and manpower costs for the offline site survey. Meanwhile, its online sequential learning ability enables the proposed localization algorithm to adapt in a timely manner to environmental dynamics. Experiments under specific environmental changes, such as variations of occupancy distribution and events of opening or closing of doors, are conducted to evaluate the performance of OS-ELM. The simulation and experimental results show that the proposed localization algorithm can provide higher localization accuracy than traditional approaches, due to its fast adaptation to various environmental dynamics.
Sequence-based prediction of protein protein interaction using a deep-learning algorithm.
Sun, Tanlin; Zhou, Bo; Lai, Luhua; Pei, Jianfeng
2017-05-25
Protein-protein interactions (PPIs) are critical for many biological processes. It is therefore important to develop accurate high-throughput methods for identifying PPI to better understand protein function, disease occurrence, and therapy design. Though various computational methods for predicting PPI have been developed, their robustness for prediction with external datasets is unknown. Deep-learning algorithms have achieved successful results in diverse areas, but their effectiveness for PPI prediction has not been tested. We used a stacked autoencoder, a type of deep-learning algorithm, to study the sequence-based PPI prediction. The best model achieved an average accuracy of 97.19% with 10-fold cross-validation. The prediction accuracies for various external datasets ranged from 87.99% to 99.21%, which are superior to those achieved with previous methods. To our knowledge, this research is the first to apply a deep-learning algorithm to sequence-based PPI prediction, and the results demonstrate its potential in this field.
Arroyo, Andrew T.; Kidd, Angel R.; Burns, Susan M.; Cruz, Ivan J.; Lawrence-Lamb, Judy E.
2015-01-01
Drawing from the qualitative tradition of narrative inquiry, and situated in an online learning environment at a historically Black college or university, this study explores the potential transformative impact of an original teaching philosophy from the perspectives of a tenure-track assistant professor and four former, nontraditional…
Dang, Thanh-Dung; Chen, Gwo-Dong; Dang, Giao; Li, Liang-Yi; Nurkhamid
2013-01-01
Dictionary use can improve reading comprehension and incidental vocabulary learning. Nevertheless, great extraneous cognitive load imposed by the search process may reduce or even prevent the improvement. With the help of technology, dictionary users can now instantly access the meaning list of a searched word using a mouse click. However, they…
Directory of Open Access Journals (Sweden)
R. Venkata Rao
2014-01-01
Full Text Available The present work proposes a multi-objective improved teaching-learning based optimization (MO-ITLBO algorithm for unconstrained and constrained multi-objective function optimization. The MO-ITLBO algorithm is the improved version of basic teaching-learning based optimization (TLBO algorithm adapted for multi-objective problems. The basic TLBO algorithm is improved to enhance its exploration and exploitation capacities by introducing the concept of number of teachers, adaptive teaching factor, tutorial training and self-motivated learning. The MO-ITLBO algorithm uses a grid-based approach to adaptively assess the non-dominated solutions (i.e. Pareto front maintained in an external archive. The performance of the MO-ITLBO algorithm is assessed by implementing it on unconstrained and constrained test problems proposed for the Congress on Evolutionary Computation 2009 (CEC 2009 competition. The performance assessment is done by using the inverted generational distance (IGD measure. The IGD measures obtained by using the MO-ITLBO algorithm are compared with the IGD measures of the other state-of-the-art algorithms available in the literature. Finally, Lexicographic ordering is used to assess the overall performance of competitive algorithms. Results have shown that the proposed MO-ITLBO algorithm has obtained the 1st rank in the optimization of unconstrained test functions and the 3rd rank in the optimization of constrained test functions.
Directory of Open Access Journals (Sweden)
Aimee Theresa Avancena
2015-06-01
Full Text Available An algorithm learning tool was developed for an introductory computer science class in a specialized science and technology high school in Japan. The tool presents lessons and simple visualizations that aim to facilitate teaching and learning of fundamental algorithms. Written tests and an evaluation questionnaire were designed and implemented along with the learning tool among the participants. The tool’s effect on the learning performance of the students was examined. The differences of the two types of visualizations offered by the tool, one with more input and control options and the other with fewer options, were analyzed. Based on the evaluation questionnaire, the scales with which the tool can be assessed according to its usability and pedagogical effectiveness were identified. After using the algorithm learning tool there was an increase in the posttest scores of the students, and those who used the visualization with more input and control options had higher scores compared to those who used the one with limited options. The learning objectives used to evaluate the tool correlated with the test performance of the students. Properties comprised of learning objectives, algorithm visualization characteristics, and interface assessment are proposed to be incorporated in evaluating an algorithm learning tool for novice learners.
Wang, Jie-sheng; Li, Shu-xia; Song, Jiang-di
2015-01-01
In order to improve convergence velocity and optimization accuracy of the cuckoo search (CS) algorithm for solving the function optimization problems, a new improved cuckoo search algorithm based on the repeat-cycle asymptotic self-learning and self-evolving disturbance (RC-SSCS) is proposed. A disturbance operation is added into the algorithm by constructing a disturbance factor to make a more careful and thorough search near the bird's nests location. In order to select a reasonable repeat-cycled disturbance number, a further study on the choice of disturbance times is made. Finally, six typical test functions are adopted to carry out simulation experiments, meanwhile, compare algorithms of this paper with two typical swarm intelligence algorithms particle swarm optimization (PSO) algorithm and artificial bee colony (ABC) algorithm. The results show that the improved cuckoo search algorithm has better convergence velocity and optimization accuracy.
Directory of Open Access Journals (Sweden)
Jie-sheng Wang
2015-01-01
Full Text Available In order to improve convergence velocity and optimization accuracy of the cuckoo search (CS algorithm for solving the function optimization problems, a new improved cuckoo search algorithm based on the repeat-cycle asymptotic self-learning and self-evolving disturbance (RC-SSCS is proposed. A disturbance operation is added into the algorithm by constructing a disturbance factor to make a more careful and thorough search near the bird’s nests location. In order to select a reasonable repeat-cycled disturbance number, a further study on the choice of disturbance times is made. Finally, six typical test functions are adopted to carry out simulation experiments, meanwhile, compare algorithms of this paper with two typical swarm intelligence algorithms particle swarm optimization (PSO algorithm and artificial bee colony (ABC algorithm. The results show that the improved cuckoo search algorithm has better convergence velocity and optimization accuracy.
National Research Council Canada - National Science Library
Caroline A. Rickards; Nisarg Vyas; Kathy L. Ryan; Kevin R. Ward; David Andre; Gennifer M. Hurst; Chelsea R. Barrera; Victor A. Convertino
2014-01-01
.... The purpose of this study was to test the hypothesis that low-level physiological signals can be used to develop a machine-learning algorithm for tracking changes in central blood volume that will...
Nelson, Kevin; Corbin, George; Blowers, Misty
2014-05-01
Machine learning is continuing to gain popularity due to its ability to solve problems that are difficult to model using conventional computer programming logic. Much of the current and past work has focused on algorithm development, data processing, and optimization. Lately, a subset of research has emerged which explores issues related to security. This research is gaining traction as systems employing these methods are being applied to both secure and adversarial environments. One of machine learning's biggest benefits, its data-driven versus logic-driven approach, is also a weakness if the data on which the models rely are corrupted. Adversaries could maliciously influence systems which address drift and data distribution changes using re-training and online learning. Our work is focused on exploring the resilience of various machine learning algorithms to these data-driven attacks. In this paper, we present our initial findings using Monte Carlo simulations, and statistical analysis, to explore the maximal achievable shift to a classification model, as well as the required amount of control over the data.