WorldWideScience

Sample records for learning unsupervised learning

  1. Unsupervised learning algorithms

    CERN Document Server

    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,...

  2. Unsupervised Learning and Generalization

    DEFF Research Database (Denmark)

    Hansen, Lars Kai; Larsen, Jan

    1996-01-01

    The concept of generalization is defined for a general class of unsupervised learning machines. The generalization error is a straightforward extension of the corresponding concept for supervised learning, and may be estimated empirically using a test set or by statistical means-in close analogy ...... with supervised learning. The empirical and analytical estimates are compared for principal component analysis and for K-means clustering based density estimation......The concept of generalization is defined for a general class of unsupervised learning machines. The generalization error is a straightforward extension of the corresponding concept for supervised learning, and may be estimated empirically using a test set or by statistical means-in close analogy...

  3. Decomposition methods for unsupervised learning

    DEFF Research Database (Denmark)

    Mørup, Morten

    2008-01-01

    This thesis presents the application and development of decomposition methods for Unsupervised Learning. It covers topics from classical factor analysis based decomposition and its variants such as Independent Component Analysis, Non-negative Matrix Factorization and Sparse Coding...... methods and clustering problems is derived both in terms of classical point clustering but also in terms of community detection in complex networks. A guiding principle throughout this thesis is the principle of parsimony. Hence, the goal of Unsupervised Learning is here posed as striving for simplicity...... in the decompositions. Thus, it is demonstrated how a wide range of decomposition methods explicitly or implicitly strive to attain this goal. Applications of the derived decompositions are given ranging from multi-media analysis of image and sound data, analysis of biomedical data such as electroencephalography...

  4. Unsupervised Learning of Action Primitives

    DEFF Research Database (Denmark)

    Baby, Sanmohan; Krüger, Volker; Kragic, Danica

    2010-01-01

    and scale, the use of the object can provide a strong invariant for the detection of motion primitives. In this paper we propose an unsupervised learning approach for action primitives that makes use of the human movements as well as the object state changes. We group actions according to the changes......Action representation is a key issue in imitation learning for humanoids. With the recent finding of mirror neurons there has been a growing interest in expressing actions as a combination meaningful subparts called primitives. Primitives could be thought of as an alphabet for the human actions....... In this paper we observe that human actions and objects can be seen as being intertwined: we can interpret actions from the way the body parts are moving, but as well from how their effect on the involved object. While human movements can look vastly different even under minor changes in location, orientation...

  5. Concept formation knowledge and experience in unsupervised learning

    CERN Document Server

    Fisher, Douglas H; Langley, Pat

    1991-01-01

    Concept Formation: Knowledge and Experience in Unsupervised Learning presents the interdisciplinary interaction between machine learning and cognitive psychology on unsupervised incremental methods. This book focuses on measures of similarity, strategies for robust incremental learning, and the psychological consistency of various approaches.Organized into three parts encompassing 15 chapters, this book begins with an overview of inductive concept learning in machine learning and psychology, with emphasis on issues that distinguish concept formation from more prevalent supervised methods and f

  6. Unsupervised learning of facial emotion decoding skills

    Directory of Open Access Journals (Sweden)

    Jan Oliver Huelle

    2014-02-01

    Full Text Available Research on the mechanisms underlying human facial emotion recognition has long focussed on genetically determined neural algorithms and often neglected the question of how these algorithms might be tuned by social learning. Here we show that facial emotion decoding skills can be significantly and sustainably improved by practise without an external teaching signal. Participants saw video clips of dynamic facial expressions of five different women and were asked to decide which of four possible emotions (anger, disgust, fear and sadness was shown in each clip. Although no external information about the correctness of the participant’s response or the sender’s true affective state was provided, participants showed a significant increase of facial emotion recognition accuracy both within and across two training sessions two days to several weeks apart. We discuss several similarities and differences between the unsupervised improvement of facial decoding skills observed in the current study, unsupervised perceptual learning of simple stimuli described in previous studies and practise effects often observed in cognitive tasks.

  7. Unsupervised learning of facial emotion decoding skills.

    Science.gov (United States)

    Huelle, Jan O; Sack, Benjamin; Broer, Katja; Komlewa, Irina; Anders, Silke

    2014-01-01

    Research on the mechanisms underlying human facial emotion recognition has long focussed on genetically determined neural algorithms and often neglected the question of how these algorithms might be tuned by social learning. Here we show that facial emotion decoding skills can be significantly and sustainably improved by practice without an external teaching signal. Participants saw video clips of dynamic facial expressions of five different women and were asked to decide which of four possible emotions (anger, disgust, fear, and sadness) was shown in each clip. Although no external information about the correctness of the participant's response or the sender's true affective state was provided, participants showed a significant increase of facial emotion recognition accuracy both within and across two training sessions two days to several weeks apart. We discuss several similarities and differences between the unsupervised improvement of facial decoding skills observed in the current study, unsupervised perceptual learning of simple stimuli described in previous studies and practice effects often observed in cognitive tasks.

  8. Integrating the Supervised Information into Unsupervised Learning

    Directory of Open Access Journals (Sweden)

    Ping Ling

    2013-01-01

    Full Text Available This paper presents an assembling unsupervised learning framework that adopts the information coming from the supervised learning process and gives the corresponding implementation algorithm. The algorithm consists of two phases: extracting and clustering data representatives (DRs firstly to obtain labeled training data and then classifying non-DRs based on labeled DRs. The implementation algorithm is called SDSN since it employs the tuning-scaled Support vector domain description to collect DRs, uses spectrum-based method to cluster DRs, and adopts the nearest neighbor classifier to label non-DRs. The validation of the clustering procedure of the first-phase is analyzed theoretically. A new metric is defined data dependently in the second phase to allow the nearest neighbor classifier to work with the informed information. A fast training approach for DRs’ extraction is provided to bring more efficiency. Experimental results on synthetic and real datasets verify that the proposed idea is of correctness and performance and SDSN exhibits higher popularity in practice over the traditional pure clustering procedure.

  9. Teacher and learner: Supervised and unsupervised learning in communities.

    Science.gov (United States)

    Shafto, Michael G; Seifert, Colleen M

    2015-01-01

    How far can teaching methods go to enhance learning? Optimal methods of teaching have been considered in research on supervised and unsupervised learning. Locally optimal methods are usually hybrids of teaching and self-directed approaches. The costs and benefits of specific methods have been shown to depend on the structure of the learning task, the learners, the teachers, and the environment.

  10. Estimating extinction using unsupervised machine learning

    Science.gov (United States)

    Meingast, Stefan; Lombardi, Marco; Alves, João

    2017-05-01

    Dust extinction is the most robust tracer of the gas distribution in the interstellar medium, but measuring extinction is limited by the systematic uncertainties involved in estimating the intrinsic colors to background stars. In this paper we present a new technique, Pnicer, that estimates intrinsic colors and extinction for individual stars using unsupervised machine learning algorithms. This new method aims to be free from any priors with respect to the column density and intrinsic color distribution. It is applicable to any combination of parameters and works in arbitrary numbers of dimensions. Furthermore, it is not restricted to color space. Extinction toward single sources is determined by fitting Gaussian mixture models along the extinction vector to (extinction-free) control field observations. In this way it becomes possible to describe the extinction for observed sources with probability densities, rather than a single value. Pnicer effectively eliminates known biases found in similar methods and outperforms them in cases of deep observational data where the number of background galaxies is significant, or when a large number of parameters is used to break degeneracies in the intrinsic color distributions. This new method remains computationally competitive, making it possible to correctly de-redden millions of sources within a matter of seconds. With the ever-increasing number of large-scale high-sensitivity imaging surveys, Pnicer offers a fast and reliable way to efficiently calculate extinction for arbitrary parameter combinations without prior information on source characteristics. The Pnicer software package also offers access to the well-established Nicer technique in a simple unified interface and is capable of building extinction maps including the Nicest correction for cloud substructure. Pnicer is offered to the community as an open-source software solution and is entirely written in Python.

  11. Specialization processes in on-line unsupervised learning

    NARCIS (Netherlands)

    Biehl, M.; Freking, A.; Reents, G.; Schlösser, E.

    1998-01-01

    From the recent analysis of supervised learning by on-line gradient descent in multilayered neural networks it is known that the necessary process of student specialization can be delayed significantly. We demonstrate that this phenomenon also occurs in various models of unsupervised learning. A

  12. Unsupervised process monitoring and fault diagnosis with machine learning methods

    CERN Document Server

    Aldrich, Chris

    2013-01-01

    This unique text/reference describes in detail the latest advances in unsupervised process monitoring and fault diagnosis with machine learning methods. Abundant case studies throughout the text demonstrate the efficacy of each method in real-world settings. The broad coverage examines such cutting-edge topics as the use of information theory to enhance unsupervised learning in tree-based methods, the extension of kernel methods to multiple kernel learning for feature extraction from data, and the incremental training of multilayer perceptrons to construct deep architectures for enhanced data

  13. Unsupervised Learning of Spatiotemporal Features by Video Completion

    OpenAIRE

    Nallabolu, Adithya Reddy

    2017-01-01

    In this work, we present an unsupervised representation learning approach for learning rich spatiotemporal features from videos without the supervision from semantic labels. We propose to learn the spatiotemporal features by training a 3D convolutional neural network (CNN) using video completion as a surrogate task. Using a large collection of unlabeled videos, we train the CNN to predict the missing pixels of a spatiotemporal hole given the remaining parts of the video through minimizing per...

  14. Towards unsupervised ontology learning from data

    CSIR Research Space (South Africa)

    Klarman, S

    2015-07-01

    Full Text Available from facts [Shapiro, 1981], finite automata descriptions from observations [Pitt, 1989], logic programs from interpretations [De Raedt and Lavracˇ, 1993; De Raedt, 1994]. In the area of DLs, a few learning scenarios have been formally addressed..., concerned largely with learning concept descriptions via different learn- ing operators [Straccia and Mucci, 2015; Lehmann and Hit- zler, 2008; Fanizzi et al., 2008; Cohen and Hirsh, 1994] and applications of formal concept analysis techniques to auto- mated...

  15. Unsupervised feature learning for autonomous rock image classification

    Science.gov (United States)

    Shu, Lei; McIsaac, Kenneth; Osinski, Gordon R.; Francis, Raymond

    2017-09-01

    Autonomous rock image classification can enhance the capability of robots for geological detection and enlarge the scientific returns, both in investigation on Earth and planetary surface exploration on Mars. Since rock textural images are usually inhomogeneous and manually hand-crafting features is not always reliable, we propose an unsupervised feature learning method to autonomously learn the feature representation for rock images. In our tests, rock image classification using the learned features shows that the learned features can outperform manually selected features. Self-taught learning is also proposed to learn the feature representation from a large database of unlabelled rock images of mixed class. The learned features can then be used repeatedly for classification of any subclass. This takes advantage of the large dataset of unlabelled rock images and learns a general feature representation for many kinds of rocks. We show experimental results supporting the feasibility of self-taught learning on rock images.

  16. Interactive Algorithms for Unsupervised Machine Learning

    Science.gov (United States)

    2015-06-01

    in Neural Information Processing Systems, 2013. 14 [3] Louigi Addario-Berry, Nicolas Broutin, Luc Devroye, and Gábor Lugosi. On combinato- rial...Myung Jin Choi, Vincent Y F Tan , Animashree Anandkumar, and Alan S Willsky. Learn- ing Latent Tree Graphical Models. Journal of Machine Learning

  17. Semi-supervised and unsupervised extreme learning machines.

    Science.gov (United States)

    Huang, Gao; Song, Shiji; Gupta, Jatinder N D; Wu, Cheng

    2014-12-01

    Extreme learning machines (ELMs) have proven to be efficient and effective learning mechanisms for pattern classification and regression. However, ELMs are primarily applied to supervised learning problems. Only a few existing research papers have used ELMs to explore unlabeled data. In this paper, we extend ELMs for both semi-supervised and unsupervised tasks based on the manifold regularization, thus greatly expanding the applicability of ELMs. The key advantages of the proposed algorithms are as follows: 1) both the semi-supervised ELM (SS-ELM) and the unsupervised ELM (US-ELM) exhibit learning capability and computational efficiency of ELMs; 2) both algorithms naturally handle multiclass classification or multicluster clustering; and 3) both algorithms are inductive and can handle unseen data at test time directly. Moreover, it is shown in this paper that all the supervised, semi-supervised, and unsupervised ELMs can actually be put into a unified framework. This provides new perspectives for understanding the mechanism of random feature mapping, which is the key concept in ELM theory. Empirical study on a wide range of data sets demonstrates that the proposed algorithms are competitive with the state-of-the-art semi-supervised or unsupervised learning algorithms in terms of accuracy and efficiency.

  18. Unsupervised learning of facial expression components

    OpenAIRE

    Egede, Joy Onyekachukwu

    2013-01-01

    The face is one of the most important means of non-verbal communication. A lot of information can be gotten about the emotional state of a person just by merely observing their facial expression. This is relatively easy in face to face communication but not so in human computer interaction. Supervised learning has been widely used by researchers to train machines to recognise facial expressions just like humans. However, supervised learning has significant limitations one of which is the fact...

  19. Slow feature analysis: unsupervised learning of invariances.

    Science.gov (United States)

    Wiskott, Laurenz; Sejnowski, Terrence J

    2002-04-01

    Invariant features of temporally varying signals are useful for analysis and classification. Slow feature analysis (SFA) is a new method for learning invariant or slowly varying features from a vectorial input signal. It is based on a nonlinear expansion of the input signal and application of principal component analysis to this expanded signal and its time derivative. It is guaranteed to find the optimal solution within a family of functions directly and can learn to extract a large number of decorrelated features, which are ordered by their degree of invariance. SFA can be applied hierarchically to process high-dimensional input signals and extract complex features. SFA is applied first to complex cell tuning properties based on simple cell output, including disparity and motion. Then more complicated input-output functions are learned by repeated application of SFA. Finally, a hierarchical network of SFA modules is presented as a simple model of the visual system. The same unstructured network can learn translation, size, rotation, contrast, or, to a lesser degree, illumination invariance for one-dimensional objects, depending on only the training stimulus. Surprisingly, only a few training objects suffice to achieve good generalization to new objects. The generated representation is suitable for object recognition. Performance degrades if the network is trained to learn multiple invariances simultaneously.

  20. Unsupervised Learning (Clustering) of Odontocete Echolocation Clicks

    Science.gov (United States)

    2015-09-30

    develop methods for clustering of marine mammal echolocation clicks to learn about species assemblages where little or no prior knowledge exists about... Mexico or the Atlanic. 2 APPROACH Acoustic encounters with odontocetes are detected automatically and noise-corrected cepstral features...Estmation of Marine Mammals Using Passive Acoustic Monitoring (DCLDE). KL divergence maps were created for all known species, but the sperm whale

  1. On parameterized deformations and unsupervised learning

    DEFF Research Database (Denmark)

    Hansen, Michael Sass

    matrix. Spline approximations of functions and in particular image registration warp fields are discussed. It is shown how spline bases may be learned from the optimization process, i.e. image registration optimization, and how this may contribute with a reasonable prior, or regularization in the method...... on an unrestricted linear parameter space, where all derivatives are defined, is introduced. Furthermore, it is shown that L2-norm the parameter space introduces a reasonable metric in the actual space of modelled diffeomorphisms. A new parametrization of 3D deformation fields, using potentials and Helmholtz...... of the multivariate B-splines, the warp field is automatically refined in areas where it results in the minimization of the registration cost function....

  2. Analog memristive synapse in spiking networks implementing unsupervised learning

    Directory of Open Access Journals (Sweden)

    Erika Covi

    2016-10-01

    Full Text Available Emerging brain-inspired architectures call for devices that can emulate the functionality of biological synapses in order to implement new efficient computational schemes able to solve ill-posed problems. Various devices and solutions are still under investigation and, in this respect, a challenge is opened to the researchers in the field. Indeed, the optimal candidate is a device able to reproduce the complete functionality of a synapse, i.e. the typical synaptic process underlying learning in biological systems (activity-dependent synaptic plasticity. This implies a device able to change its resistance (synaptic strength, or weight upon proper electrical stimuli (synaptic activity and showing several stable resistive states throughout its dynamic range (analog behavior. Moreover, it should be able to perform spike timing dependent plasticity (STDP, an associative homosynaptic plasticity learning rule based on the delay time between the two firing neurons the synapse is connected to. This rule is a fundamental learning protocol in state-of-art networks, because it allows unsupervised learning. Notwithstanding this fact, STDP-based unsupervised learning has been proposed several times mainly for binary synapses rather than multilevel synapses composed of many binary memristors. This paper proposes an HfO2-based analog memristor as a synaptic element which performs STDP within a small spiking neuromorphic network operating unsupervised learning for character recognition. The trained network is able to recognize five characters even in case incomplete or noisy characters are displayed and it is robust to a device-to-device variability of up to +/-30%.

  3. Analog Memristive Synapse in Spiking Networks Implementing Unsupervised Learning.

    Science.gov (United States)

    Covi, Erika; Brivio, Stefano; Serb, Alexander; Prodromakis, Themis; Fanciulli, Marco; Spiga, Sabina

    2016-01-01

    Emerging brain-inspired architectures call for devices that can emulate the functionality of biological synapses in order to implement new efficient computational schemes able to solve ill-posed problems. Various devices and solutions are still under investigation and, in this respect, a challenge is opened to the researchers in the field. Indeed, the optimal candidate is a device able to reproduce the complete functionality of a synapse, i.e., the typical synaptic process underlying learning in biological systems (activity-dependent synaptic plasticity). This implies a device able to change its resistance (synaptic strength, or weight) upon proper electrical stimuli (synaptic activity) and showing several stable resistive states throughout its dynamic range (analog behavior). Moreover, it should be able to perform spike timing dependent plasticity (STDP), an associative homosynaptic plasticity learning rule based on the delay time between the two firing neurons the synapse is connected to. This rule is a fundamental learning protocol in state-of-art networks, because it allows unsupervised learning. Notwithstanding this fact, STDP-based unsupervised learning has been proposed several times mainly for binary synapses rather than multilevel synapses composed of many binary memristors. This paper proposes an HfO 2 -based analog memristor as a synaptic element which performs STDP within a small spiking neuromorphic network operating unsupervised learning for character recognition. The trained network is able to recognize five characters even in case incomplete or noisy images are displayed and it is robust to a device-to-device variability of up to ±30%.

  4. Unsupervised spike sorting based on discriminative subspace learning.

    Science.gov (United States)

    Keshtkaran, Mohammad Reza; Yang, Zhi

    2014-01-01

    Spike sorting is a fundamental preprocessing step for many neuroscience studies which rely on the analysis of spike trains. In this paper, we present two unsupervised spike sorting algorithms based on discriminative subspace learning. The first algorithm simultaneously learns the discriminative feature subspace and performs clustering. It uses histogram of features in the most discriminative projection to detect the number of neurons. The second algorithm performs hierarchical divisive clustering that learns a discriminative 1-dimensional subspace for clustering in each level of the hierarchy until achieving almost unimodal distribution in the subspace. The algorithms are tested on synthetic and in-vivo data, and are compared against two widely used spike sorting methods. The comparative results demonstrate that our spike sorting methods can achieve substantially higher accuracy in lower dimensional feature space, and they are highly robust to noise. Moreover, they provide significantly better cluster separability in the learned subspace than in the subspace obtained by principal component analysis or wavelet transform.

  5. Function approximation using combined unsupervised and supervised learning.

    Science.gov (United States)

    Andras, Peter

    2014-03-01

    Function approximation is one of the core tasks that are solved using neural networks in the context of many engineering problems. However, good approximation results need good sampling of the data space, which usually requires exponentially increasing volume of data as the dimensionality of the data increases. At the same time, often the high-dimensional data is arranged around a much lower dimensional manifold. Here we propose the breaking of the function approximation task for high-dimensional data into two steps: (1) the mapping of the high-dimensional data onto a lower dimensional space corresponding to the manifold on which the data resides and (2) the approximation of the function using the mapped lower dimensional data. We use over-complete self-organizing maps (SOMs) for the mapping through unsupervised learning, and single hidden layer neural networks for the function approximation through supervised learning. We also extend the two-step procedure by considering support vector machines and Bayesian SOMs for the determination of the best parameters for the nonlinear neurons in the hidden layer of the neural networks used for the function approximation. We compare the approximation performance of the proposed neural networks using a set of functions and show that indeed the neural networks using combined unsupervised and supervised learning outperform in most cases the neural networks that learn the function approximation using the original high-dimensional data.

  6. Unsupervised deep learning reveals prognostically relevant subtypes of glioblastoma.

    Science.gov (United States)

    Young, Jonathan D; Cai, Chunhui; Lu, Xinghua

    2017-10-03

    One approach to improving the personalized treatment of cancer is to understand the cellular signaling transduction pathways that cause cancer at the level of the individual patient. In this study, we used unsupervised deep learning to learn the hierarchical structure within cancer gene expression data. Deep learning is a group of machine learning algorithms that use multiple layers of hidden units to capture hierarchically related, alternative representations of the input data. We hypothesize that this hierarchical structure learned by deep learning will be related to the cellular signaling system. Robust deep learning model selection identified a network architecture that is biologically plausible. Our model selection results indicated that the 1st hidden layer of our deep learning model should contain about 1300 hidden units to most effectively capture the covariance structure of the input data. This agrees with the estimated number of human transcription factors, which is approximately 1400. This result lends support to our hypothesis that the 1st hidden layer of a deep learning model trained on gene expression data may represent signals related to transcription factor activation. Using the 3rd hidden layer representation of each tumor as learned by our unsupervised deep learning model, we performed consensus clustering on all tumor samples-leading to the discovery of clusters of glioblastoma multiforme with differential survival. One of these clusters contained all of the glioblastoma samples with G-CIMP, a known methylation phenotype driven by the IDH1 mutation and associated with favorable prognosis, suggesting that the hidden units in the 3rd hidden layer representations captured a methylation signal without explicitly using methylation data as input. We also found differentially expressed genes and well-known mutations (NF1, IDH1, EGFR) that were uniquely correlated with each of these clusters. Exploring these unique genes and mutations will allow us to

  7. Unsupervised Feature Learning for Heart Sounds Classification Using Autoencoder

    Science.gov (United States)

    Hu, Wei; Lv, Jiancheng; Liu, Dongbo; Chen, Yao

    2018-04-01

    Cardiovascular disease seriously threatens the health of many people. It is usually diagnosed during cardiac auscultation, which is a fast and efficient method of cardiovascular disease diagnosis. In recent years, deep learning approach using unsupervised learning has made significant breakthroughs in many fields. However, to our knowledge, deep learning has not yet been used for heart sound classification. In this paper, we first use the average Shannon energy to extract the envelope of the heart sounds, then find the highest point of S1 to extract the cardiac cycle. We convert the time-domain signals of the cardiac cycle into spectrograms and apply principal component analysis whitening to reduce the dimensionality of the spectrogram. Finally, we apply a two-layer autoencoder to extract the features of the spectrogram. The experimental results demonstrate that the features from the autoencoder are suitable for heart sound classification.

  8. Continuous Online Sequence Learning with an Unsupervised Neural Network Model.

    Science.gov (United States)

    Cui, Yuwei; Ahmad, Subutar; Hawkins, Jeff

    2016-09-14

    The ability to recognize and predict temporal sequences of sensory inputs is vital for survival in natural environments. Based on many known properties of cortical neurons, hierarchical temporal memory (HTM) sequence memory recently has been proposed as a theoretical framework for sequence learning in the cortex. In this letter, we analyze properties of HTM sequence memory and apply it to sequence learning and prediction problems with streaming data. We show the model is able to continuously learn a large number of variableorder temporal sequences using an unsupervised Hebbian-like learning rule. The sparse temporal codes formed by the model can robustly handle branching temporal sequences by maintaining multiple predictions until there is sufficient disambiguating evidence. We compare the HTM sequence memory with other sequence learning algorithms, including statistical methods: autoregressive integrated moving average; feedforward neural networks-time delay neural network and online sequential extreme learning machine; and recurrent neural networks-long short-term memory and echo-state networks on sequence prediction problems with both artificial and real-world data. The HTM model achieves comparable accuracy to other state-of-the-art algorithms. The model also exhibits properties that are critical for sequence learning, including continuous online learning, the ability to handle multiple predictions and branching sequences with high-order statistics, robustness to sensor noise and fault tolerance, and good performance without task-specific hyperparameter tuning. Therefore, the HTM sequence memory not only advances our understanding of how the brain may solve the sequence learning problem but is also applicable to real-world sequence learning problems from continuous data streams.

  9. A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning

    DEFF Research Database (Denmark)

    Fraccaro, Marco; Kamronn, Simon Due; Paquet, Ulrich

    2017-01-01

    This paper takes a step towards temporal reasoning in a dynamically changing video, not in the pixel space that constitutes its frames, but in a latent space that describes the non-linear dynamics of the objects in its world. We introduce the Kalman variational auto-encoder, a framework...... for unsupervised learning of sequential data that disentangles two latent representations: an object’s representation, coming from a recognition model, and a latent state describing its dynamics. As a result, the evolution of the world can be imagined and missing data imputed, both without the need to generate...

  10. Unsupervised behaviour-specific dictionary learning for abnormal event detection

    DEFF Research Database (Denmark)

    Ren, Huamin; Liu, Weifeng; Olsen, Søren Ingvor

    2015-01-01

    the training data is only a small proportion of the surveillance data. Therefore, we propose behavior-specific dictionaries (BSD) through unsupervised learning, pursuing atoms from the same type of behavior to represent one behavior dictionary. To further improve the dictionary by introducing information from...... potential infrequent normal patterns, we refine the dictionary by searching ‘missed atoms’ that have compact coefficients. Experimental results show that our BSD algorithm outperforms state-of-the-art dictionaries in abnormal event detection on the public UCSD dataset. Moreover, BSD has less false alarms...

  11. CHISSL: A Human-Machine Collaboration Space for Unsupervised Learning

    Energy Technology Data Exchange (ETDEWEB)

    Arendt, Dustin L.; Komurlu, Caner; Blaha, Leslie M.

    2017-07-14

    We developed CHISSL, a human-machine interface that utilizes supervised machine learning in an unsupervised context to help the user group unlabeled instances by her own mental model. The user primarily interacts via correction (moving a misplaced instance into its correct group) or confirmation (accepting that an instance is placed in its correct group). Concurrent with the user's interactions, CHISSL trains a classification model guided by the user's grouping of the data. It then predicts the group of unlabeled instances and arranges some of these alongside the instances manually organized by the user. We hypothesize that this mode of human and machine collaboration is more effective than Active Learning, wherein the machine decides for itself which instances should be labeled by the user. We found supporting evidence for this hypothesis in a pilot study where we applied CHISSL to organize a collection of handwritten digits.

  12. Unsupervised active learning based on hierarchical graph-theoretic clustering.

    Science.gov (United States)

    Hu, Weiming; Hu, Wei; Xie, Nianhua; Maybank, Steve

    2009-10-01

    Most existing active learning approaches are supervised. Supervised active learning has the following problems: inefficiency in dealing with the semantic gap between the distribution of samples in the feature space and their labels, lack of ability in selecting new samples that belong to new categories that have not yet appeared in the training samples, and lack of adaptability to changes in the semantic interpretation of sample categories. To tackle these problems, we propose an unsupervised active learning framework based on hierarchical graph-theoretic clustering. In the framework, two promising graph-theoretic clustering algorithms, namely, dominant-set clustering and spectral clustering, are combined in a hierarchical fashion. Our framework has some advantages, such as ease of implementation, flexibility in architecture, and adaptability to changes in the labeling. Evaluations on data sets for network intrusion detection, image classification, and video classification have demonstrated that our active learning framework can effectively reduce the workload of manual classification while maintaining a high accuracy of automatic classification. It is shown that, overall, our framework outperforms the support-vector-machine-based supervised active learning, particularly in terms of dealing much more efficiently with new samples whose categories have not yet appeared in the training samples.

  13. Modelling unsupervised online-learning of artificial grammars: linking implicit and statistical learning.

    Science.gov (United States)

    Rohrmeier, Martin A; Cross, Ian

    2014-07-01

    Humans rapidly learn complex structures in various domains. Findings of above-chance performance of some untrained control groups in artificial grammar learning studies raise questions about the extent to which learning can occur in an untrained, unsupervised testing situation with both correct and incorrect structures. The plausibility of unsupervised online-learning effects was modelled with n-gram, chunking and simple recurrent network models. A novel evaluation framework was applied, which alternates forced binary grammaticality judgments and subsequent learning of the same stimulus. Our results indicate a strong online learning effect for n-gram and chunking models and a weaker effect for simple recurrent network models. Such findings suggest that online learning is a plausible effect of statistical chunk learning that is possible when ungrammatical sequences contain a large proportion of grammatical chunks. Such common effects of continuous statistical learning may underlie statistical and implicit learning paradigms and raise implications for study design and testing methodologies. Copyright © 2014 Elsevier Inc. All rights reserved.

  14. An automatic taxonomy of galaxy morphology using unsupervised machine learning

    Science.gov (United States)

    Hocking, Alex; Geach, James E.; Sun, Yi; Davey, Neil

    2018-01-01

    We present an unsupervised machine learning technique that automatically segments and labels galaxies in astronomical imaging surveys using only pixel data. Distinct from previous unsupervised machine learning approaches used in astronomy we use no pre-selection or pre-filtering of target galaxy type to identify galaxies that are similar. We demonstrate the technique on the Hubble Space Telescope (HST) Frontier Fields. By training the algorithm using galaxies from one field (Abell 2744) and applying the result to another (MACS 0416.1-2403), we show how the algorithm can cleanly separate early and late type galaxies without any form of pre-directed training for what an 'early' or 'late' type galaxy is. We then apply the technique to the HST Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey (CANDELS) fields, creating a catalogue of approximately 60 000 classifications. We show how the automatic classification groups galaxies of similar morphological (and photometric) type and make the classifications public via a catalogue, a visual catalogue and galaxy similarity search. We compare the CANDELS machine-based classifications to human-classifications from the Galaxy Zoo: CANDELS project. Although there is not a direct mapping between Galaxy Zoo and our hierarchical labelling, we demonstrate a good level of concordance between human and machine classifications. Finally, we show how the technique can be used to identify rarer objects and present lensed galaxy candidates from the CANDELS imaging.

  15. Unsupervised learning of binary vectors: A Gaussian scenario

    International Nuclear Information System (INIS)

    Copelli, Mauro; Van den Broeck, Christian

    2000-01-01

    We study a model of unsupervised learning where the real-valued data vectors are isotropically distributed, except for a single symmetry-breaking binary direction B(set-membership sign){-1,+1} N , onto which the projections have a Gaussian distribution. We show that a candidate vector J undergoing Gibbs learning in this discrete space, approaches the perfect match J=B exponentially. In addition to the second-order ''retarded learning'' phase transition for unbiased distributions, we show that first-order transitions can also occur. Extending the known result that the center of mass of the Gibbs ensemble has Bayes-optimal performance, we show that taking the sign of the components of this vector (clipping) leads to the vector with optimal performance in the binary space. These upper bounds are shown generally not to be saturated with the technique of transforming the components of a special continuous vector, except in asymptotic limits and in a special linear case. Simulations are presented which are in excellent agreement with the theoretical results. (c) 2000 The American Physical Society

  16. Unsupervised learning of a steerable basis for invariant image representations

    Science.gov (United States)

    Bethge, Matthias; Gerwinn, Sebastian; Macke, Jakob H.

    2007-02-01

    There are two aspects to unsupervised learning of invariant representations of images: First, we can reduce the dimensionality of the representation by finding an optimal trade-off between temporal stability and informativeness. We show that the answer to this optimization problem is generally not unique so that there is still considerable freedom in choosing a suitable basis. Which of the many optimal representations should be selected? Here, we focus on this second aspect, and seek to find representations that are invariant under geometrical transformations occuring in sequences of natural images. We utilize ideas of 'steerability' and Lie groups, which have been developed in the context of filter design. In particular, we show how an anti-symmetric version of canonical correlation analysis can be used to learn a full-rank image basis which is steerable with respect to rotations. We provide a geometric interpretation of this algorithm by showing that it finds the two-dimensional eigensubspaces of the average bivector. For data which exhibits a variety of transformations, we develop a bivector clustering algorithm, which we use to learn a basis of generalized quadrature pairs (i.e. 'complex cells') from sequences of natural images.

  17. Automatic microseismic event picking via unsupervised machine learning

    Science.gov (United States)

    Chen, Yangkang

    2018-01-01

    Effective and efficient arrival picking plays an important role in microseismic and earthquake data processing and imaging. Widely used short-term-average long-term-average ratio (STA/LTA) based arrival picking algorithms suffer from the sensitivity to moderate-to-strong random ambient noise. To make the state-of-the-art arrival picking approaches effective, microseismic data need to be first pre-processed, for example, removing sufficient amount of noise, and second analysed by arrival pickers. To conquer the noise issue in arrival picking for weak microseismic or earthquake event, I leverage the machine learning techniques to help recognizing seismic waveforms in microseismic or earthquake data. Because of the dependency of supervised machine learning algorithm on large volume of well-designed training data, I utilize an unsupervised machine learning algorithm to help cluster the time samples into two groups, that is, waveform points and non-waveform points. The fuzzy clustering algorithm has been demonstrated to be effective for such purpose. A group of synthetic, real microseismic and earthquake data sets with different levels of complexity show that the proposed method is much more robust than the state-of-the-art STA/LTA method in picking microseismic events, even in the case of moderately strong background noise.

  18. Application of unsupervised learning methods in high energy physics

    Energy Technology Data Exchange (ETDEWEB)

    Koevesarki, Peter; Nuncio Quiroz, Adriana Elizabeth; Brock, Ian C. [Physikalisches Institut, Universitaet Bonn, Bonn (Germany)

    2011-07-01

    High energy physics is a home for a variety of multivariate techniques, mainly due to the fundamentally probabilistic behaviour of nature. These methods generally require training based on some theory, in order to discriminate a known signal from a background. Nevertheless, new physics can show itself in ways that previously no one thought about, and in these cases conventional methods give little or no help. A possible way to discriminate between known processes (like vector bosons or top-quark production) or look for new physics is using unsupervised machine learning to extract the features of the data. A technique was developed, based on the combination of neural networks and the method of principal curves, to find a parametrisation of the non-linear correlations of the data. The feasibility of the method is shown on ATLAS data.

  19. Unsupervised/supervised learning concept for 24-hour load forecasting

    Energy Technology Data Exchange (ETDEWEB)

    Djukanovic, M [Electrical Engineering Inst. ' Nikola Tesla' , Belgrade (Yugoslavia); Babic, B [Electrical Power Industry of Serbia, Belgrade (Yugoslavia); Sobajic, D J; Pao, Y -H [Case Western Reserve Univ., Cleveland, OH (United States). Dept. of Electrical Engineering and Computer Science

    1993-07-01

    An application of artificial neural networks in short-term load forecasting is described. An algorithm using an unsupervised/supervised learning concept and historical relationship between the load and temperature for a given season, day type and hour of the day to forecast hourly electric load with a lead time of 24 hours is proposed. An additional approach using functional link net, temperature variables, average load and last one-hour load of previous day is introduced and compared with the ANN model with one hidden layer load forecast. In spite of limited available weather variables (maximum, minimum and average temperature for the day) quite acceptable results have been achieved. The 24-hour-ahead forecast errors (absolute average) ranged from 2.78% for Saturdays and 3.12% for working days to 3.54% for Sundays. (Author)

  20. Learning from label proportions in brain-computer interfaces: Online unsupervised learning with guarantees

    Science.gov (United States)

    Verhoeven, Thibault; Schmid, Konstantin; Müller, Klaus-Robert; Tangermann, Michael; Kindermans, Pieter-Jan

    2017-01-01

    Objective Using traditional approaches, a brain-computer interface (BCI) requires the collection of calibration data for new subjects prior to online use. Calibration time can be reduced or eliminated e.g., by subject-to-subject transfer of a pre-trained classifier or unsupervised adaptive classification methods which learn from scratch and adapt over time. While such heuristics work well in practice, none of them can provide theoretical guarantees. Our objective is to modify an event-related potential (ERP) paradigm to work in unison with the machine learning decoder, and thus to achieve a reliable unsupervised calibrationless decoding with a guarantee to recover the true class means. Method We introduce learning from label proportions (LLP) to the BCI community as a new unsupervised, and easy-to-implement classification approach for ERP-based BCIs. The LLP estimates the mean target and non-target responses based on known proportions of these two classes in different groups of the data. We present a visual ERP speller to meet the requirements of LLP. For evaluation, we ran simulations on artificially created data sets and conducted an online BCI study with 13 subjects performing a copy-spelling task. Results Theoretical considerations show that LLP is guaranteed to minimize the loss function similar to a corresponding supervised classifier. LLP performed well in simulations and in the online application, where 84.5% of characters were spelled correctly on average without prior calibration. Significance The continuously adapting LLP classifier is the first unsupervised decoder for ERP BCIs guaranteed to find the optimal decoder. This makes it an ideal solution to avoid tedious calibration sessions. Additionally, LLP works on complementary principles compared to existing unsupervised methods, opening the door for their further enhancement when combined with LLP. PMID:28407016

  1. Towards Statistical Unsupervised Online Learning for Music Listening with Hearing Devices

    DEFF Research Database (Denmark)

    Purwins, Hendrik; Marchini, Marco; Marxer, Richard

    of sounds into phonetic/instrument categories and learning of instrument event sequences is performed jointly using a Hierarchical Dirichlet Process Hidden Markov Model. Whereas machines often learn by processing a large data base and subsequently updating parameters of the algorithm, humans learn...... and their respective transition counts. We propose to use online learning for the co-evolution of both CI user and machine in (re-)learning musical language. [1] Marco Marchini and Hendrik Purwins. Unsupervised analysis and generation of audio percussion sequences. In International Symposium on Computer Music Modeling...... categories) as well as the temporal context horizon (e.g. storing up to 2-note sequences or up to 10-note sequences) is adaptable. The framework in [1] is based on two cognitively plausible principles: unsupervised learning and statistical learning. Opposed to supervised learning in primary school children...

  2. Supervised and Unsupervised Learning of Multidimensional Acoustic Categories

    Science.gov (United States)

    Goudbeek, Martijn; Swingley, Daniel; Smits, Roel

    2009-01-01

    Learning to recognize the contrasts of a language-specific phonemic repertoire can be viewed as forming categories in a multidimensional psychophysical space. Research on the learning of distributionally defined visual categories has shown that categories defined over 1 dimension are easy to learn and that learning multidimensional categories is…

  3. A comparative evaluation of supervised and unsupervised representation learning approaches for anaplastic medulloblastoma differentiation

    Science.gov (United States)

    Cruz-Roa, Angel; Arevalo, John; Basavanhally, Ajay; Madabhushi, Anant; González, Fabio

    2015-01-01

    Learning data representations directly from the data itself is an approach that has shown great success in different pattern recognition problems, outperforming state-of-the-art feature extraction schemes for different tasks in computer vision, speech recognition and natural language processing. Representation learning applies unsupervised and supervised machine learning methods to large amounts of data to find building-blocks that better represent the information in it. Digitized histopathology images represents a very good testbed for representation learning since it involves large amounts of high complex, visual data. This paper presents a comparative evaluation of different supervised and unsupervised representation learning architectures to specifically address open questions on what type of learning architectures (deep or shallow), type of learning (unsupervised or supervised) is optimal. In this paper we limit ourselves to addressing these questions in the context of distinguishing between anaplastic and non-anaplastic medulloblastomas from routine haematoxylin and eosin stained images. The unsupervised approaches evaluated were sparse autoencoders and topographic reconstruct independent component analysis, and the supervised approach was convolutional neural networks. Experimental results show that shallow architectures with more neurons are better than deeper architectures without taking into account local space invariances and that topographic constraints provide useful invariant features in scale and rotations for efficient tumor differentiation.

  4. Unsupervised Learning and Pattern Recognition of Biological Data Structures with Density Functional Theory and Machine Learning.

    Science.gov (United States)

    Chen, Chien-Chang; Juan, Hung-Hui; Tsai, Meng-Yuan; Lu, Henry Horng-Shing

    2018-01-11

    By introducing the methods of machine learning into the density functional theory, we made a detour for the construction of the most probable density function, which can be estimated by learning relevant features from the system of interest. Using the properties of universal functional, the vital core of density functional theory, the most probable cluster numbers and the corresponding cluster boundaries in a studying system can be simultaneously and automatically determined and the plausibility is erected on the Hohenberg-Kohn theorems. For the method validation and pragmatic applications, interdisciplinary problems from physical to biological systems were enumerated. The amalgamation of uncharged atomic clusters validated the unsupervised searching process of the cluster numbers and the corresponding cluster boundaries were exhibited likewise. High accurate clustering results of the Fisher's iris dataset showed the feasibility and the flexibility of the proposed scheme. Brain tumor detections from low-dimensional magnetic resonance imaging datasets and segmentations of high-dimensional neural network imageries in the Brainbow system were also used to inspect the method practicality. The experimental results exhibit the successful connection between the physical theory and the machine learning methods and will benefit the clinical diagnoses.

  5. Bayesian feature weighting for unsupervised learning, with application to object recognition

    OpenAIRE

    Carbonetto , Peter; De Freitas , Nando; Gustafson , Paul; Thompson , Natalie

    2003-01-01

    International audience; We present a method for variable selection/weighting in an unsupervised learning context using Bayesian shrinkage. The basis for the model parameters and cluster assignments can be computed simultaneous using an efficient EM algorithm. Applying our Bayesian shrinkage model to a complex problem in object recognition (Duygulu, Barnard, de Freitas and Forsyth 2002), our experiments yied good results.

  6. An Introduction to Topic Modeling as an Unsupervised Machine Learning Way to Organize Text Information

    Science.gov (United States)

    Snyder, Robin M.

    2015-01-01

    The field of topic modeling has become increasingly important over the past few years. Topic modeling is an unsupervised machine learning way to organize text (or image or DNA, etc.) information such that related pieces of text can be identified. This paper/session will present/discuss the current state of topic modeling, why it is important, and…

  7. Advancing Affect Modeling via Preference Learning and Unsupervised Feature Extraction

    DEFF Research Database (Denmark)

    Martínez, Héctor Pérez

    strategies (error functions and training algorithms) for artificial neural networks are examined across synthetic and psycho-physiological datasets, and compared against support vector machines and Cohen’s method. Results reveal the best training strategies for neural networks and suggest their superiority...... difficulties, ordinal reports such as rankings and ratings can yield more reliable affect annotations than alternative tools. This thesis explores preference learning methods to automatically learn computational models from ordinal annotations of affect. In particular, an extensive collection of training...... over the other examined methods. The second challenge addressed in this thesis refers to the extraction of relevant information from physiological modalities. Deep learning is proposed as an automatic approach to extract input features for models of affect from physiological signals. Experiments...

  8. Learning rates in supervised and unsupervised intelligent systems

    International Nuclear Information System (INIS)

    Hora, S.C.

    1986-01-01

    Classifying observations from a mixture distribution is considered a simple model for learning. Existing results are integrated to obtain asymptotically optimal estimators of the classification rule. The asymptotic relative efficiencies show that a tutored learner is considerably more efficient on difficult problems, but only slightly more efficient on easy problems. This suggests a combined method that seeks instruction on hard cases

  9. A Novel Unsupervised Adaptive Learning Method for Long-Term Electromyography (EMG) Pattern Recognition

    Science.gov (United States)

    Huang, Qi; Yang, Dapeng; Jiang, Li; Zhang, Huajie; Liu, Hong; Kotani, Kiyoshi

    2017-01-01

    Performance degradation will be caused by a variety of interfering factors for pattern recognition-based myoelectric control methods in the long term. This paper proposes an adaptive learning method with low computational cost to mitigate the effect in unsupervised adaptive learning scenarios. We presents a particle adaptive classifier (PAC), by constructing a particle adaptive learning strategy and universal incremental least square support vector classifier (LS-SVC). We compared PAC performance with incremental support vector classifier (ISVC) and non-adapting SVC (NSVC) in a long-term pattern recognition task in both unsupervised and supervised adaptive learning scenarios. Retraining time cost and recognition accuracy were compared by validating the classification performance on both simulated and realistic long-term EMG data. The classification results of realistic long-term EMG data showed that the PAC significantly decreased the performance degradation in unsupervised adaptive learning scenarios compared with NSVC (9.03% ± 2.23%, p < 0.05) and ISVC (13.38% ± 2.62%, p = 0.001), and reduced the retraining time cost compared with ISVC (2 ms per updating cycle vs. 50 ms per updating cycle). PMID:28608824

  10. A Novel Unsupervised Adaptive Learning Method for Long-Term Electromyography (EMG Pattern Recognition

    Directory of Open Access Journals (Sweden)

    Qi Huang

    2017-06-01

    Full Text Available Performance degradation will be caused by a variety of interfering factors for pattern recognition-based myoelectric control methods in the long term. This paper proposes an adaptive learning method with low computational cost to mitigate the effect in unsupervised adaptive learning scenarios. We presents a particle adaptive classifier (PAC, by constructing a particle adaptive learning strategy and universal incremental least square support vector classifier (LS-SVC. We compared PAC performance with incremental support vector classifier (ISVC and non-adapting SVC (NSVC in a long-term pattern recognition task in both unsupervised and supervised adaptive learning scenarios. Retraining time cost and recognition accuracy were compared by validating the classification performance on both simulated and realistic long-term EMG data. The classification results of realistic long-term EMG data showed that the PAC significantly decreased the performance degradation in unsupervised adaptive learning scenarios compared with NSVC (9.03% ± 2.23%, p < 0.05 and ISVC (13.38% ± 2.62%, p = 0.001, and reduced the retraining time cost compared with ISVC (2 ms per updating cycle vs. 50 ms per updating cycle.

  11. Intelligent Fault Diagnosis of Rotary Machinery Based on Unsupervised Multiscale Representation Learning

    Science.gov (United States)

    Jiang, Guo-Qian; Xie, Ping; Wang, Xiao; Chen, Meng; He, Qun

    2017-11-01

    The performance of traditional vibration based fault diagnosis methods greatly depends on those handcrafted features extracted using signal processing algorithms, which require significant amounts of domain knowledge and human labor, and do not generalize well to new diagnosis domains. Recently, unsupervised representation learning provides an alternative promising solution to feature extraction in traditional fault diagnosis due to its superior learning ability from unlabeled data. Given that vibration signals usually contain multiple temporal structures, this paper proposes a multiscale representation learning (MSRL) framework to learn useful features directly from raw vibration signals, with the aim to capture rich and complementary fault pattern information at different scales. In our proposed approach, a coarse-grained procedure is first employed to obtain multiple scale signals from an original vibration signal. Then, sparse filtering, a newly developed unsupervised learning algorithm, is applied to automatically learn useful features from each scale signal, respectively, and then the learned features at each scale to be concatenated one by one to obtain multiscale representations. Finally, the multiscale representations are fed into a supervised classifier to achieve diagnosis results. Our proposed approach is evaluated using two different case studies: motor bearing and wind turbine gearbox fault diagnosis. Experimental results show that the proposed MSRL approach can take full advantages of the availability of unlabeled data to learn discriminative features and achieved better performance with higher accuracy and stability compared to the traditional approaches.

  12. Deep Unsupervised Learning on a Desktop PC: A Primer for Cognitive Scientists.

    Science.gov (United States)

    Testolin, Alberto; Stoianov, Ivilin; De Filippo De Grazia, Michele; Zorzi, Marco

    2013-01-01

    Deep belief networks hold great promise for the simulation of human cognition because they show how structured and abstract representations may emerge from probabilistic unsupervised learning. These networks build a hierarchy of progressively more complex distributed representations of the sensory data by fitting a hierarchical generative model. However, learning in deep networks typically requires big datasets and it can involve millions of connection weights, which implies that simulations on standard computers are unfeasible. Developing realistic, medium-to-large-scale learning models of cognition would therefore seem to require expertise in programing parallel-computing hardware, and this might explain why the use of this promising approach is still largely confined to the machine learning community. Here we show how simulations of deep unsupervised learning can be easily performed on a desktop PC by exploiting the processors of low cost graphic cards (graphic processor units) without any specific programing effort, thanks to the use of high-level programming routines (available in MATLAB or Python). We also show that even an entry-level graphic card can outperform a small high-performance computing cluster in terms of learning time and with no loss of learning quality. We therefore conclude that graphic card implementations pave the way for a widespread use of deep learning among cognitive scientists for modeling cognition and behavior.

  13. Deep unsupervised learning on a desktop PC: A primer for cognitive scientists

    Directory of Open Access Journals (Sweden)

    Alberto eTestolin

    2013-05-01

    Full Text Available Deep belief networks hold great promise for the simulation of human cognition because they show how structured and abstract representations may emerge from probabilistic unsupervised learning. These networks build a hierarchy of progressively more complex distributed representations of the sensory data by fitting a hierarchical generative model. However, learning in deep networks typically requires big datasets and it can involve millions of connection weights, which implies that simulations on standard computers are unfeasible. Developing realistic, medium-to-large-scale learning models of cognition would therefore seem to require expertise in programming parallel-computing hardware, and this might explain why the use of this promising approach is still largely confined to the machine learning community. Here we show how simulations of deep unsupervised learning can be easily performed on a desktop PC by exploiting the processors of low-cost graphic cards (GPUs without any specific programming effort, thanks to the use of high-level programming routines (available in MATLAB or Python. We also show that even an entry-level graphic card can outperform a small high-performance computing cluster in terms of learning time and with no loss of learning quality. We therefore conclude that graphic card implementations pave the way for a widespread use of deep learning among cognitive scientists for modeling cognition and behavior.

  14. Deep Unsupervised Learning on a Desktop PC: A Primer for Cognitive Scientists

    Science.gov (United States)

    Testolin, Alberto; Stoianov, Ivilin; De Filippo De Grazia, Michele; Zorzi, Marco

    2013-01-01

    Deep belief networks hold great promise for the simulation of human cognition because they show how structured and abstract representations may emerge from probabilistic unsupervised learning. These networks build a hierarchy of progressively more complex distributed representations of the sensory data by fitting a hierarchical generative model. However, learning in deep networks typically requires big datasets and it can involve millions of connection weights, which implies that simulations on standard computers are unfeasible. Developing realistic, medium-to-large-scale learning models of cognition would therefore seem to require expertise in programing parallel-computing hardware, and this might explain why the use of this promising approach is still largely confined to the machine learning community. Here we show how simulations of deep unsupervised learning can be easily performed on a desktop PC by exploiting the processors of low cost graphic cards (graphic processor units) without any specific programing effort, thanks to the use of high-level programming routines (available in MATLAB or Python). We also show that even an entry-level graphic card can outperform a small high-performance computing cluster in terms of learning time and with no loss of learning quality. We therefore conclude that graphic card implementations pave the way for a widespread use of deep learning among cognitive scientists for modeling cognition and behavior. PMID:23653617

  15. Modeling Visit Behaviour in Smart Homes using Unsupervised Learning

    NARCIS (Netherlands)

    Nait Aicha, A.; Englebienne, G.; Kröse, B.

    2014-01-01

    Many algorithms on health monitoring from ambient sensor networks assume that only a single person is present in the home. We present an unsupervised method that models visit behaviour. A Markov modulated multidimensional non-homogeneous Poisson process (M3P2) is described that allows us to model

  16. Large-Scale Unsupervised Hashing with Shared Structure Learning.

    Science.gov (United States)

    Liu, Xianglong; Mu, Yadong; Zhang, Danchen; Lang, Bo; Li, Xuelong

    2015-09-01

    Hashing methods are effective in generating compact binary signatures for images and videos. This paper addresses an important open issue in the literature, i.e., how to learn compact hash codes by enhancing the complementarity among different hash functions. Most of prior studies solve this problem either by adopting time-consuming sequential learning algorithms or by generating the hash functions which are subject to some deliberately-designed constraints (e.g., enforcing hash functions orthogonal to one another). We analyze the drawbacks of past works and propose a new solution to this problem. Our idea is to decompose the feature space into a subspace shared by all hash functions and its complementary subspace. On one hand, the shared subspace, corresponding to the common structure across different hash functions, conveys most relevant information for the hashing task. Similar to data de-noising, irrelevant information is explicitly suppressed during hash function generation. On the other hand, in case that the complementary subspace also contains useful information for specific hash functions, the final form of our proposed hashing scheme is a compromise between these two kinds of subspaces. To make hash functions not only preserve the local neighborhood structure but also capture the global cluster distribution of the whole data, an objective function incorporating spectral embedding loss, binary quantization loss, and shared subspace contribution is introduced to guide the hash function learning. We propose an efficient alternating optimization method to simultaneously learn both the shared structure and the hash functions. Experimental results on three well-known benchmarks CIFAR-10, NUS-WIDE, and a-TRECVID demonstrate that our approach significantly outperforms state-of-the-art hashing methods.

  17. Information-Based Approach to Unsupervised Machine Learning

    Science.gov (United States)

    2013-06-19

    samples with large fitting error. The above optimization problem can be reduced to a quadratic program (Mangasarian & Musicant , 2000), which can be...recognition. Technicheskaya Kibernetica, 3. in Russian. Mallows, C. L. (1973). Some comments on CP . Technometrics, 15, 661–675. Mangasarian, O. L., & Musicant ...to find correspondence between two sets of objects in different domains in an unsupervised way. Photo album summa- rization is a typical application

  18. Unsupervised learning in neural networks with short range synapses

    Science.gov (United States)

    Brunnet, L. G.; Agnes, E. J.; Mizusaki, B. E. P.; Erichsen, R., Jr.

    2013-01-01

    Different areas of the brain are involved in specific aspects of the information being processed both in learning and in memory formation. For example, the hippocampus is important in the consolidation of information from short-term memory to long-term memory, while emotional memory seems to be dealt by the amygdala. On the microscopic scale the underlying structures in these areas differ in the kind of neurons involved, in their connectivity, or in their clustering degree but, at this level, learning and memory are attributed to neuronal synapses mediated by longterm potentiation and long-term depression. In this work we explore the properties of a short range synaptic connection network, a nearest neighbor lattice composed mostly by excitatory neurons and a fraction of inhibitory ones. The mechanism of synaptic modification responsible for the emergence of memory is Spike-Timing-Dependent Plasticity (STDP), a Hebbian-like rule, where potentiation/depression is acquired when causal/non-causal spikes happen in a synapse involving two neurons. The system is intended to store and recognize memories associated to spatial external inputs presented as simple geometrical forms. The synaptic modifications are continuously applied to excitatory connections, including a homeostasis rule and STDP. In this work we explore the different scenarios under which a network with short range connections can accomplish the task of storing and recognizing simple connected patterns.

  19. Unsupervised learning via self-organization a dynamic approach

    CERN Document Server

    Kyan, Matthew; Jarrah, Kambiz; Guan, Ling

    2014-01-01

    To aid in intelligent data mining, this book introduces a new family of unsupervised algorithms that have a basis in self-organization, yet are free from many of the constraints typical of other well known self-organizing architectures. It then moves through a series of pertinent real world applications with regards to the processing of multimedia data from its role in generic image processing techniques such as the automated modeling and removal of impulse noise in digital images, to problems in digital asset management, and its various roles in feature extraction, visual enhancement, segmentation, and analysis of microbiological image data.

  20. Unsupervised Learning of Word-Sequence Representations from Scratch via Convolutional Tensor Decomposition

    OpenAIRE

    Huang, Furong; Anandkumar, Animashree

    2016-01-01

    Unsupervised text embeddings extraction is crucial for text understanding in machine learning. Word2Vec and its variants have received substantial success in mapping words with similar syntactic or semantic meaning to vectors close to each other. However, extracting context-aware word-sequence embedding remains a challenging task. Training over large corpus is difficult as labels are difficult to get. More importantly, it is challenging for pre-trained models to obtain word-...

  1. Modeling Language and Cognition with Deep Unsupervised Learning:A Tutorial Overview

    OpenAIRE

    Marco eZorzi; Marco eZorzi; Alberto eTestolin; Ivilin Peev Stoianov; Ivilin Peev Stoianov

    2013-01-01

    Deep unsupervised learning in stochastic recurrent neural networks with many layers of hidden units is a recent breakthrough in neural computation research. These networks build a hierarchy of progressively more complex distributed representations of the sensory data by fitting a hierarchical generative model. In this article we discuss the theoretical foundations of this approach and we review key issues related to training, testing and analysis of deep networks for modeling language and cog...

  2. Modeling language and cognition with deep unsupervised learning: a tutorial overview

    OpenAIRE

    Zorzi, Marco; Testolin, Alberto; Stoianov, Ivilin P.

    2013-01-01

    Deep unsupervised learning in stochastic recurrent neural networks with many layers of hidden units is a recent breakthrough in neural computation research. These networks build a hierarchy of progressively more complex distributed representations of the sensory data by fitting a hierarchical generative model. In this article we discuss the theoretical foundations of this approach and we review key issues related to training, testing and analysis of deep networks for modeling language and cog...

  3. Modeling language and cognition with deep unsupervised learning: a tutorial overview.

    Science.gov (United States)

    Zorzi, Marco; Testolin, Alberto; Stoianov, Ivilin P

    2013-01-01

    Deep unsupervised learning in stochastic recurrent neural networks with many layers of hidden units is a recent breakthrough in neural computation research. These networks build a hierarchy of progressively more complex distributed representations of the sensory data by fitting a hierarchical generative model. In this article we discuss the theoretical foundations of this approach and we review key issues related to training, testing and analysis of deep networks for modeling language and cognitive processing. The classic letter and word perception problem of McClelland and Rumelhart (1981) is used as a tutorial example to illustrate how structured and abstract representations may emerge from deep generative learning. We argue that the focus on deep architectures and generative (rather than discriminative) learning represents a crucial step forward for the connectionist modeling enterprise, because it offers a more plausible model of cortical learning as well as a way to bridge the gap between emergentist connectionist models and structured Bayesian models of cognition.

  4. Modeling Language and Cognition with Deep Unsupervised Learning:A Tutorial Overview

    Directory of Open Access Journals (Sweden)

    Marco eZorzi

    2013-08-01

    Full Text Available Deep unsupervised learning in stochastic recurrent neural networks with many layers of hidden units is a recent breakthrough in neural computation research. These networks build a hierarchy of progressively more complex distributed representations of the sensory data by fitting a hierarchical generative model. In this article we discuss the theoretical foundations of this approach and we review key issues related to training, testing and analysis of deep networks for modeling language and cognitive processing. The classic letter and word perception problem of McClelland and Rumelhart (1981 is used as a tutorial example to illustrate how structured and abstract representations may emerge from deep generative learning. We argue that the focus on deep architectures and generative (rather than discriminative learning represents a crucial step forward for the connectionist modeling enterprise, because it offers a more plausible model of cortical learning as well as way to bridge the gap between emergentist connectionist models and structured Bayesian models of cognition.

  5. Modeling language and cognition with deep unsupervised learning: a tutorial overview

    Science.gov (United States)

    Zorzi, Marco; Testolin, Alberto; Stoianov, Ivilin P.

    2013-01-01

    Deep unsupervised learning in stochastic recurrent neural networks with many layers of hidden units is a recent breakthrough in neural computation research. These networks build a hierarchy of progressively more complex distributed representations of the sensory data by fitting a hierarchical generative model. In this article we discuss the theoretical foundations of this approach and we review key issues related to training, testing and analysis of deep networks for modeling language and cognitive processing. The classic letter and word perception problem of McClelland and Rumelhart (1981) is used as a tutorial example to illustrate how structured and abstract representations may emerge from deep generative learning. We argue that the focus on deep architectures and generative (rather than discriminative) learning represents a crucial step forward for the connectionist modeling enterprise, because it offers a more plausible model of cortical learning as well as a way to bridge the gap between emergentist connectionist models and structured Bayesian models of cognition. PMID:23970869

  6. Massively parallel unsupervised single-particle cryo-EM data clustering via statistical manifold learning.

    Science.gov (United States)

    Wu, Jiayi; Ma, Yong-Bei; Congdon, Charles; Brett, Bevin; Chen, Shuobing; Xu, Yaofang; Ouyang, Qi; Mao, Youdong

    2017-01-01

    Structural heterogeneity in single-particle cryo-electron microscopy (cryo-EM) data represents a major challenge for high-resolution structure determination. Unsupervised classification may serve as the first step in the assessment of structural heterogeneity. However, traditional algorithms for unsupervised classification, such as K-means clustering and maximum likelihood optimization, may classify images into wrong classes with decreasing signal-to-noise-ratio (SNR) in the image data, yet demand increased computational costs. Overcoming these limitations requires further development of clustering algorithms for high-performance cryo-EM data processing. Here we introduce an unsupervised single-particle clustering algorithm derived from a statistical manifold learning framework called generative topographic mapping (GTM). We show that unsupervised GTM clustering improves classification accuracy by about 40% in the absence of input references for data with lower SNRs. Applications to several experimental datasets suggest that our algorithm can detect subtle structural differences among classes via a hierarchical clustering strategy. After code optimization over a high-performance computing (HPC) environment, our software implementation was able to generate thousands of reference-free class averages within hours in a massively parallel fashion, which allows a significant improvement on ab initio 3D reconstruction and assists in the computational purification of homogeneous datasets for high-resolution visualization.

  7. Massively parallel unsupervised single-particle cryo-EM data clustering via statistical manifold learning.

    Directory of Open Access Journals (Sweden)

    Jiayi Wu

    Full Text Available Structural heterogeneity in single-particle cryo-electron microscopy (cryo-EM data represents a major challenge for high-resolution structure determination. Unsupervised classification may serve as the first step in the assessment of structural heterogeneity. However, traditional algorithms for unsupervised classification, such as K-means clustering and maximum likelihood optimization, may classify images into wrong classes with decreasing signal-to-noise-ratio (SNR in the image data, yet demand increased computational costs. Overcoming these limitations requires further development of clustering algorithms for high-performance cryo-EM data processing. Here we introduce an unsupervised single-particle clustering algorithm derived from a statistical manifold learning framework called generative topographic mapping (GTM. We show that unsupervised GTM clustering improves classification accuracy by about 40% in the absence of input references for data with lower SNRs. Applications to several experimental datasets suggest that our algorithm can detect subtle structural differences among classes via a hierarchical clustering strategy. After code optimization over a high-performance computing (HPC environment, our software implementation was able to generate thousands of reference-free class averages within hours in a massively parallel fashion, which allows a significant improvement on ab initio 3D reconstruction and assists in the computational purification of homogeneous datasets for high-resolution visualization.

  8. Unsupervised multiple kernel learning for heterogeneous data integration.

    Science.gov (United States)

    Mariette, Jérôme; Villa-Vialaneix, Nathalie

    2018-03-15

    Recent high-throughput sequencing advances have expanded the breadth of available omics datasets and the integrated analysis of multiple datasets obtained on the same samples has allowed to gain important insights in a wide range of applications. However, the integration of various sources of information remains a challenge for systems biology since produced datasets are often of heterogeneous types, with the need of developing generic methods to take their different specificities into account. We propose a multiple kernel framework that allows to integrate multiple datasets of various types into a single exploratory analysis. Several solutions are provided to learn either a consensus meta-kernel or a meta-kernel that preserves the original topology of the datasets. We applied our framework to analyse two public multi-omics datasets. First, the multiple metagenomic datasets, collected during the TARA Oceans expedition, was explored to demonstrate that our method is able to retrieve previous findings in a single kernel PCA as well as to provide a new image of the sample structures when a larger number of datasets are included in the analysis. To perform this analysis, a generic procedure is also proposed to improve the interpretability of the kernel PCA in regards with the original data. Second, the multi-omics breast cancer datasets, provided by The Cancer Genome Atlas, is analysed using a kernel Self-Organizing Maps with both single and multi-omics strategies. The comparison of these two approaches demonstrates the benefit of our integration method to improve the representation of the studied biological system. Proposed methods are available in the R package mixKernel, released on CRAN. It is fully compatible with the mixOmics package and a tutorial describing the approach can be found on mixOmics web site http://mixomics.org/mixkernel/. jerome.mariette@inra.fr or nathalie.villa-vialaneix@inra.fr. Supplementary data are available at Bioinformatics online.

  9. Learning representation hierarchies by sharing visual features: a computational investigation of Persian character recognition with unsupervised deep learning.

    Science.gov (United States)

    Sadeghi, Zahra; Testolin, Alberto

    2017-08-01

    In humans, efficient recognition of written symbols is thought to rely on a hierarchical processing system, where simple features are progressively combined into more abstract, high-level representations. Here, we present a computational model of Persian character recognition based on deep belief networks, where increasingly more complex visual features emerge in a completely unsupervised manner by fitting a hierarchical generative model to the sensory data. Crucially, high-level internal representations emerging from unsupervised deep learning can be easily read out by a linear classifier, achieving state-of-the-art recognition accuracy. Furthermore, we tested the hypothesis that handwritten digits and letters share many common visual features: A generative model that captures the statistical structure of the letters distribution should therefore also support the recognition of written digits. To this aim, deep networks trained on Persian letters were used to build high-level representations of Persian digits, which were indeed read out with high accuracy. Our simulations show that complex visual features, such as those mediating the identification of Persian symbols, can emerge from unsupervised learning in multilayered neural networks and can support knowledge transfer across related domains.

  10. Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP.

    Directory of Open Access Journals (Sweden)

    Yoonsik Shim

    2016-10-01

    Full Text Available We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP. The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture.

  11. Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP.

    Science.gov (United States)

    Shim, Yoonsik; Philippides, Andrew; Staras, Kevin; Husbands, Phil

    2016-10-01

    We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP). The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM) networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture.

  12. Unsupervised Learning Through Randomized Algorithms for High-Volume High-Velocity Data (ULTRA-HV).

    Energy Technology Data Exchange (ETDEWEB)

    Pinar, Ali [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Kolda, Tamara G. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Carlberg, Kevin Thomas [Wake Forest Univ., Winston-Salem, MA (United States); Ballard, Grey [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Mahoney, Michael [Univ. of California, Berkeley, CA (United States)

    2018-01-01

    Through long-term investments in computing, algorithms, facilities, and instrumentation, DOE is an established leader in massive-scale, high-fidelity simulations, as well as science-leading experimentation. In both cases, DOE is generating more data than it can analyze and the problem is intensifying quickly. The need for advanced algorithms that can automatically convert the abundance of data into a wealth of useful information by discovering hidden structures is well recognized. Such efforts however, are hindered by the massive volume of the data and its high velocity. Here, the challenge is developing unsupervised learning methods to discover hidden structure in high-volume, high-velocity data.

  13. Characterizing Interference in Radio Astronomy Observations through Active and Unsupervised Learning

    Science.gov (United States)

    Doran, G.

    2013-01-01

    In the process of observing signals from astronomical sources, radio astronomers must mitigate the effects of manmade radio sources such as cell phones, satellites, aircraft, and observatory equipment. Radio frequency interference (RFI) often occurs as short bursts (active learning approach in which an astronomer labels events that are most confusing to a classifier, minimizing the human effort required for classification. We also explore the use of unsupervised clustering techniques, which automatically group events into classes without user input. We apply these techniques to data from the Parkes Multibeam Pulsar Survey to characterize several million detected RFI events from over a thousand hours of observation.

  14. Unsupervised learning by spike timing dependent plasticity in phase change memory (PCM synapses

    Directory of Open Access Journals (Sweden)

    Stefano eAmbrogio

    2016-03-01

    Full Text Available We present a novel one-transistor/one-resistor (1T1R synapse for neuromorphic networks, based on phase change memory (PCM technology. The synapse is capable of spike-timing dependent plasticity (STDP, where gradual potentiation relies on set transition, namely crystallization, in the PCM, while depression is achieved via reset or amorphization of a chalcogenide active volume. STDP characteristics are demonstrated by experiments under variable initial conditions and number of pulses. Finally, we support the applicability of the 1T1R synapse for learning and recognition of visual patterns by simulations of fully connected neuromorphic networks with 2 or 3 layers with high recognition efficiency. The proposed scheme provides a feasible low-power solution for on-line unsupervised machine learning in smart reconfigurable sensors.

  15. An Improved EMD-Based Dissimilarity Metric for Unsupervised Linear Subspace Learning

    Directory of Open Access Journals (Sweden)

    Xiangchun Yu

    2018-01-01

    Full Text Available We investigate a novel way of robust face image feature extraction by adopting the methods based on Unsupervised Linear Subspace Learning to extract a small number of good features. Firstly, the face image is divided into blocks with the specified size, and then we propose and extract pooled Histogram of Oriented Gradient (pHOG over each block. Secondly, an improved Earth Mover’s Distance (EMD metric is adopted to measure the dissimilarity between blocks of one face image and the corresponding blocks from the rest of face images. Thirdly, considering the limitations of the original Locality Preserving Projections (LPP, we proposed the Block Structure LPP (BSLPP, which effectively preserves the structural information of face images. Finally, an adjacency graph is constructed and a small number of good features of a face image are obtained by methods based on Unsupervised Linear Subspace Learning. A series of experiments have been conducted on several well-known face databases to evaluate the effectiveness of the proposed algorithm. In addition, we construct the noise, geometric distortion, slight translation, slight rotation AR, and Extended Yale B face databases, and we verify the robustness of the proposed algorithm when faced with a certain degree of these disturbances.

  16. Wavelet-based unsupervised learning method for electrocardiogram suppression in surface electromyograms.

    Science.gov (United States)

    Niegowski, Maciej; Zivanovic, Miroslav

    2016-03-01

    We present a novel approach aimed at removing electrocardiogram (ECG) perturbation from single-channel surface electromyogram (EMG) recordings by means of unsupervised learning of wavelet-based intensity images. The general idea is to combine the suitability of certain wavelet decomposition bases which provide sparse electrocardiogram time-frequency representations, with the capacity of non-negative matrix factorization (NMF) for extracting patterns from images. In order to overcome convergence problems which often arise in NMF-related applications, we design a novel robust initialization strategy which ensures proper signal decomposition in a wide range of ECG contamination levels. Moreover, the method can be readily used because no a priori knowledge or parameter adjustment is needed. The proposed method was evaluated on real surface EMG signals against two state-of-the-art unsupervised learning algorithms and a singular spectrum analysis based method. The results, expressed in terms of high-to-low energy ratio, normalized median frequency, spectral power difference and normalized average rectified value, suggest that the proposed method enables better ECG-EMG separation quality than the reference methods. Copyright © 2015 IPEM. Published by Elsevier Ltd. All rights reserved.

  17. Automated age-related macular degeneration classification in OCT using unsupervised feature learning

    Science.gov (United States)

    Venhuizen, Freerk G.; van Ginneken, Bram; Bloemen, Bart; van Grinsven, Mark J. J. P.; Philipsen, Rick; Hoyng, Carel; Theelen, Thomas; Sánchez, Clara I.

    2015-03-01

    Age-related Macular Degeneration (AMD) is a common eye disorder with high prevalence in elderly people. The disease mainly affects the central part of the retina, and could ultimately lead to permanent vision loss. Optical Coherence Tomography (OCT) is becoming the standard imaging modality in diagnosis of AMD and the assessment of its progression. However, the evaluation of the obtained volumetric scan is time consuming, expensive and the signs of early AMD are easy to miss. In this paper we propose a classification method to automatically distinguish AMD patients from healthy subjects with high accuracy. The method is based on an unsupervised feature learning approach, and processes the complete image without the need for an accurate pre-segmentation of the retina. The method can be divided in two steps: an unsupervised clustering stage that extracts a set of small descriptive image patches from the training data, and a supervised training stage that uses these patches to create a patch occurrence histogram for every image on which a random forest classifier is trained. Experiments using 384 volume scans show that the proposed method is capable of identifying AMD patients with high accuracy, obtaining an area under the Receiver Operating Curve of 0:984. Our method allows for a quick and reliable assessment of the presence of AMD pathology in OCT volume scans without the need for accurate layer segmentation algorithms.

  18. Conduction Delay Learning Model for Unsupervised and Supervised Classification of Spatio-Temporal Spike Patterns.

    Science.gov (United States)

    Matsubara, Takashi

    2017-01-01

    Precise spike timing is considered to play a fundamental role in communications and signal processing in biological neural networks. Understanding the mechanism of spike timing adjustment would deepen our understanding of biological systems and enable advanced engineering applications such as efficient computational architectures. However, the biological mechanisms that adjust and maintain spike timing remain unclear. Existing algorithms adopt a supervised approach, which adjusts the axonal conduction delay and synaptic efficacy until the spike timings approximate the desired timings. This study proposes a spike timing-dependent learning model that adjusts the axonal conduction delay and synaptic efficacy in both unsupervised and supervised manners. The proposed learning algorithm approximates the Expectation-Maximization algorithm, and classifies the input data encoded into spatio-temporal spike patterns. Even in the supervised classification, the algorithm requires no external spikes indicating the desired spike timings unlike existing algorithms. Furthermore, because the algorithm is consistent with biological models and hypotheses found in existing biological studies, it could capture the mechanism underlying biological delay learning.

  19. A Distributed Algorithm for the Cluster-Based Outlier Detection Using Unsupervised Extreme Learning Machines

    Directory of Open Access Journals (Sweden)

    Xite Wang

    2017-01-01

    Full Text Available Outlier detection is an important data mining task, whose target is to find the abnormal or atypical objects from a given dataset. The techniques for detecting outliers have a lot of applications, such as credit card fraud detection and environment monitoring. Our previous work proposed the Cluster-Based (CB outlier and gave a centralized method using unsupervised extreme learning machines to compute CB outliers. In this paper, we propose a new distributed algorithm for the CB outlier detection (DACB. On the master node, we collect a small number of points from the slave nodes to obtain a threshold. On each slave node, we design a new filtering method that can use the threshold to efficiently speed up the computation. Furthermore, we also propose a ranking method to optimize the order of cluster scanning. At last, the effectiveness and efficiency of the proposed approaches are verified through a plenty of simulation experiments.

  20. Noise-robust unsupervised spike sorting based on discriminative subspace learning with outlier handling.

    Science.gov (United States)

    Keshtkaran, Mohammad Reza; Yang, Zhi

    2017-06-01

    Spike sorting is a fundamental preprocessing step for many neuroscience studies which rely on the analysis of spike trains. Most of the feature extraction and dimensionality reduction techniques that have been used for spike sorting give a projection subspace which is not necessarily the most discriminative one. Therefore, the clusters which appear inherently separable in some discriminative subspace may overlap if projected using conventional feature extraction approaches leading to a poor sorting accuracy especially when the noise level is high. In this paper, we propose a noise-robust and unsupervised spike sorting algorithm based on learning discriminative spike features for clustering. The proposed algorithm uses discriminative subspace learning to extract low dimensional and most discriminative features from the spike waveforms and perform clustering with automatic detection of the number of the clusters. The core part of the algorithm involves iterative subspace selection using linear discriminant analysis and clustering using Gaussian mixture model with outlier detection. A statistical test in the discriminative subspace is proposed to automatically detect the number of the clusters. Comparative results on publicly available simulated and real in vivo datasets demonstrate that our algorithm achieves substantially improved cluster distinction leading to higher sorting accuracy and more reliable detection of clusters which are highly overlapping and not detectable using conventional feature extraction techniques such as principal component analysis or wavelets. By providing more accurate information about the activity of more number of individual neurons with high robustness to neural noise and outliers, the proposed unsupervised spike sorting algorithm facilitates more detailed and accurate analysis of single- and multi-unit activities in neuroscience and brain machine interface studies.

  1. Noise-robust unsupervised spike sorting based on discriminative subspace learning with outlier handling

    Science.gov (United States)

    Keshtkaran, Mohammad Reza; Yang, Zhi

    2017-06-01

    Objective. Spike sorting is a fundamental preprocessing step for many neuroscience studies which rely on the analysis of spike trains. Most of the feature extraction and dimensionality reduction techniques that have been used for spike sorting give a projection subspace which is not necessarily the most discriminative one. Therefore, the clusters which appear inherently separable in some discriminative subspace may overlap if projected using conventional feature extraction approaches leading to a poor sorting accuracy especially when the noise level is high. In this paper, we propose a noise-robust and unsupervised spike sorting algorithm based on learning discriminative spike features for clustering. Approach. The proposed algorithm uses discriminative subspace learning to extract low dimensional and most discriminative features from the spike waveforms and perform clustering with automatic detection of the number of the clusters. The core part of the algorithm involves iterative subspace selection using linear discriminant analysis and clustering using Gaussian mixture model with outlier detection. A statistical test in the discriminative subspace is proposed to automatically detect the number of the clusters. Main results. Comparative results on publicly available simulated and real in vivo datasets demonstrate that our algorithm achieves substantially improved cluster distinction leading to higher sorting accuracy and more reliable detection of clusters which are highly overlapping and not detectable using conventional feature extraction techniques such as principal component analysis or wavelets. Significance. By providing more accurate information about the activity of more number of individual neurons with high robustness to neural noise and outliers, the proposed unsupervised spike sorting algorithm facilitates more detailed and accurate analysis of single- and multi-unit activities in neuroscience and brain machine interface studies.

  2. A Hybrid Supervised/Unsupervised Machine Learning Approach to Solar Flare Prediction

    Science.gov (United States)

    Benvenuto, Federico; Piana, Michele; Campi, Cristina; Massone, Anna Maria

    2018-01-01

    This paper introduces a novel method for flare forecasting, combining prediction accuracy with the ability to identify the most relevant predictive variables. This result is obtained by means of a two-step approach: first, a supervised regularization method for regression, namely, LASSO is applied, where a sparsity-enhancing penalty term allows the identification of the significance with which each data feature contributes to the prediction; then, an unsupervised fuzzy clustering technique for classification, namely, Fuzzy C-Means, is applied, where the regression outcome is partitioned through the minimization of a cost function and without focusing on the optimization of a specific skill score. This approach is therefore hybrid, since it combines supervised and unsupervised learning; realizes classification in an automatic, skill-score-independent way; and provides effective prediction performances even in the case of imbalanced data sets. Its prediction power is verified against NOAA Space Weather Prediction Center data, using as a test set, data in the range between 1996 August and 2010 December and as training set, data in the range between 1988 December and 1996 June. To validate the method, we computed several skill scores typically utilized in flare prediction and compared the values provided by the hybrid approach with the ones provided by several standard (non-hybrid) machine learning methods. The results showed that the hybrid approach performs classification better than all other supervised methods and with an effectiveness comparable to the one of clustering methods; but, in addition, it provides a reliable ranking of the weights with which the data properties contribute to the forecast.

  3. Classification and unsupervised clustering of LIGO data with Deep Transfer Learning

    Science.gov (United States)

    George, Daniel; Shen, Hongyu; Huerta, E. A.

    2018-05-01

    Gravitational wave detection requires a detailed understanding of the response of the LIGO and Virgo detectors to true signals in the presence of environmental and instrumental noise. Of particular interest is the study of anomalous non-Gaussian transients, such as glitches, since their occurrence rate in LIGO and Virgo data can obscure or even mimic true gravitational wave signals. Therefore, successfully identifying and excising these anomalies from gravitational wave data is of utmost importance for the detection and characterization of true signals and for the accurate computation of their significance. To facilitate this work, we present the first application of deep learning combined with transfer learning to show that knowledge from pretrained models for real-world object recognition can be transferred for classifying spectrograms of glitches. To showcase this new method, we use a data set of twenty-two classes of glitches, curated and labeled by the Gravity Spy project using data collected during LIGO's first discovery campaign. We demonstrate that our Deep Transfer Learning method enables an optimal use of very deep convolutional neural networks for glitch classification given small and unbalanced training data sets, significantly reduces the training time, and achieves state-of-the-art accuracy above 98.8%, lowering the previous error rate by over 60%. More importantly, once trained via transfer learning on the known classes, we show that our neural networks can be truncated and used as feature extractors for unsupervised clustering to automatically group together new unknown classes of glitches and anomalous signals. This novel capability is of paramount importance to identify and remove new types of glitches which will occur as the LIGO/Virgo detectors gradually attain design sensitivity.

  4. CAPES: Unsupervised Storage Performance Tuning Using Neural Network-Based Deep Reinforcement Learning

    CERN Multimedia

    CERN. Geneva

    2017-01-01

    Parameter tuning is an important task of storage performance optimization. Current practice usually involves numerous tweak-benchmark cycles that are slow and costly. To address this issue, we developed CAPES, a model-less deep reinforcement learning-based unsupervised parameter tuning system driven by a deep neural network (DNN). It is designed to nd the optimal values of tunable parameters in computer systems, from a simple client-server system to a large data center, where human tuning can be costly and often cannot achieve optimal performance. CAPES takes periodic measurements of a target computer system’s state, and trains a DNN which uses Q-learning to suggest changes to the system’s current parameter values. CAPES is minimally intrusive, and can be deployed into a production system to collect training data and suggest tuning actions during the system’s daily operation. Evaluation of a prototype on a Lustre system demonstrates an increase in I/O throughput up to 45% at saturation point. About the...

  5. Unsupervised Labeling Of Data For Supervised Learning And Its Application To Medical Claims Prediction

    Directory of Open Access Journals (Sweden)

    Che Ngufor

    2013-01-01

    Full Text Available The task identifying changes and irregularities in medical insurance claim pay-ments is a difficult process of which the traditional practice involves queryinghistorical claims databases and flagging potential claims as normal or abnor-mal. Because what is considered as normal payment is usually unknown andmay change over time, abnormal payments often pass undetected; only to bediscovered when the payment period has passed.This paper presents the problem of on-line unsupervised learning from datastreams when the distribution that generates the data changes or drifts overtime. Automated algorithms for detecting drifting concepts in a probabilitydistribution of the data are presented. The idea behind the presented driftdetection methods is to transform the distribution of the data within a slidingwindow into a more convenient distribution. Then, a test statistics p-value ata given significance level can be used to infer the drift rate, adjust the windowsize and decide on the status of the drift. The detected concepts drifts areused to label the data, for subsequent learning of classification models by asupervised learner. The algorithms were tested on several synthetic and realmedical claims data sets.

  6. Unsupervised obstacle detection in driving environments using deep-learning-based stereovision

    KAUST Repository

    Dairi, Abdelkader; Harrou, Fouzi; Senouci, Mohamed; Sun, Ying

    2017-01-01

    A vision-based obstacle detection system is a key enabler for the development of autonomous robots and vehicles and intelligent transportation systems. This paper addresses the problem of urban scene monitoring and tracking of obstacles based on unsupervised, deep-learning approaches. Here, we design an innovative hybrid encoder that integrates deep Boltzmann machines (DBM) and auto-encoders (AE). This hybrid auto-encode (HAE) model combines the greedy learning features of DBM with the dimensionality reduction capacity of AE to accurately and reliably detect the presence of obstacles. We combine the proposed hybrid model with the one-class support vector machines (OCSVM) to visually monitor an urban scene. We also propose an efficient approach to estimating obstacles location and track their positions via scene densities. Specifically, we address obstacle detection as an anomaly detection problem. If an obstacle is detected by the OCSVM algorithm, then localization and tracking algorithm is executed. We validated the effectiveness of our approach by using experimental data from two publicly available dataset, the Malaga stereovision urban dataset (MSVUD) and the Daimler urban segmentation dataset (DUSD). Results show the capacity of the proposed approach to reliably detect obstacles.

  7. Unsupervised obstacle detection in driving environments using deep-learning-based stereovision

    KAUST Repository

    Dairi, Abdelkader

    2017-12-06

    A vision-based obstacle detection system is a key enabler for the development of autonomous robots and vehicles and intelligent transportation systems. This paper addresses the problem of urban scene monitoring and tracking of obstacles based on unsupervised, deep-learning approaches. Here, we design an innovative hybrid encoder that integrates deep Boltzmann machines (DBM) and auto-encoders (AE). This hybrid auto-encode (HAE) model combines the greedy learning features of DBM with the dimensionality reduction capacity of AE to accurately and reliably detect the presence of obstacles. We combine the proposed hybrid model with the one-class support vector machines (OCSVM) to visually monitor an urban scene. We also propose an efficient approach to estimating obstacles location and track their positions via scene densities. Specifically, we address obstacle detection as an anomaly detection problem. If an obstacle is detected by the OCSVM algorithm, then localization and tracking algorithm is executed. We validated the effectiveness of our approach by using experimental data from two publicly available dataset, the Malaga stereovision urban dataset (MSVUD) and the Daimler urban segmentation dataset (DUSD). Results show the capacity of the proposed approach to reliably detect obstacles.

  8. Extracting aerobic system dynamics during unsupervised activities of daily living using wearable sensor machine learning models.

    Science.gov (United States)

    Beltrame, Thomas; Amelard, Robert; Wong, Alexander; Hughson, Richard L

    2018-02-01

    sensors in unsupervised activities of daily living in combination with novel machine learning algorithms to investigate the aerobic system dynamics with the potential to contribute to models of functional health status and guide future individualized health care in the normal population.

  9. Unsupervised Learning of Digit Recognition Using Spike-Timing-Dependent Plasticity

    Directory of Open Access Journals (Sweden)

    Peter U. Diehl

    2015-08-01

    Full Text Available In order to understand how the mammalian neocortex is performing computations, two things are necessary; we need to have a good understanding of the available neuronal processing units and mechanisms, and we need to gain a better understanding of how those mechanisms are combined to build functioning systems. Therefore, in recent years there is an increasing interest in how spiking neural networks (SNN can be used to perform complex computations or solve pattern recognition tasks. However, it remains a challenging task to design SNNs which use biologically plausible mechanisms (especially for learning new patterns, since most of such SNN architectures rely on training in a rate-based network and subsequent conversion to a SNN. We present a SNN for digit recognition which is based on mechanisms with increased biological plausibility, i.e. conductance-based instead of current-based synapses, spike-timing-dependent plasticity with time-dependent weight change, lateral inhibition, and an adaptive spiking threshold. Unlike most other systems, we do not use a teaching signal and do not present any class labels to the network. Using this unsupervised learning scheme, our architecture achieves 95% accuracy on the MNIST benchmark, which is better than previous SNN implementations without supervision. The fact that we used no domain-specific knowledge points toward the general applicability of our network design. Also, the performance of our network scales well with the number of neurons used and shows similar performance for four different learning rules, indicating robustness of the full combination of mechanisms, which suggests applicability in heterogeneous biological neural networks.

  10. Unsupervised learning of mixture models based on swarm intelligence and neural networks with optimal completion using incomplete data

    Directory of Open Access Journals (Sweden)

    Ahmed R. Abas

    2012-07-01

    Full Text Available In this paper, a new algorithm is presented for unsupervised learning of finite mixture models (FMMs using data set with missing values. This algorithm overcomes the local optima problem of the Expectation-Maximization (EM algorithm via integrating the EM algorithm with Particle Swarm Optimization (PSO. In addition, the proposed algorithm overcomes the problem of biased estimation due to overlapping clusters in estimating missing values in the input data set by integrating locally-tuned general regression neural networks with Optimal Completion Strategy (OCS. A comparison study shows the superiority of the proposed algorithm over other algorithms commonly used in the literature in unsupervised learning of FMM parameters that result in minimum mis-classification errors when used in clustering incomplete data set that is generated from overlapping clusters and these clusters are largely different in their sizes.

  11. Unsupervised machine learning account of magnetic transitions in the Hubbard model

    Science.gov (United States)

    Ch'ng, Kelvin; Vazquez, Nick; Khatami, Ehsan

    2018-01-01

    We employ several unsupervised machine learning techniques, including autoencoders, random trees embedding, and t -distributed stochastic neighboring ensemble (t -SNE), to reduce the dimensionality of, and therefore classify, raw (auxiliary) spin configurations generated, through Monte Carlo simulations of small clusters, for the Ising and Fermi-Hubbard models at finite temperatures. Results from a convolutional autoencoder for the three-dimensional Ising model can be shown to produce the magnetization and the susceptibility as a function of temperature with a high degree of accuracy. Quantum fluctuations distort this picture and prevent us from making such connections between the output of the autoencoder and physical observables for the Hubbard model. However, we are able to define an indicator based on the output of the t -SNE algorithm that shows a near perfect agreement with the antiferromagnetic structure factor of the model in two and three spatial dimensions in the weak-coupling regime. t -SNE also predicts a transition to the canted antiferromagnetic phase for the three-dimensional model when a strong magnetic field is present. We show that these techniques cannot be expected to work away from half filling when the "sign problem" in quantum Monte Carlo simulations is present.

  12. Unsupervised Learning for Efficient Texture Estimation From Limited Discrete Orientation Data

    Science.gov (United States)

    Niezgoda, Stephen R.; Glover, Jared

    2013-11-01

    The estimation of orientation distribution functions (ODFs) from discrete orientation data, as produced by electron backscatter diffraction or crystal plasticity micromechanical simulations, is typically achieved via techniques such as the Williams-Imhof-Matthies-Vinel (WIMV) algorithm or generalized spherical harmonic expansions, which were originally developed for computing an ODF from pole figures measured by X-ray or neutron diffraction. These techniques rely on ad-hoc methods for choosing parameters, such as smoothing half-width and bandwidth, and for enforcing positivity constraints and appropriate normalization. In general, such approaches provide little or no information-theoretic guarantees as to their optimality in describing the given dataset. In the current study, an unsupervised learning algorithm is proposed which uses a finite mixture of Bingham distributions for the estimation of ODFs from discrete orientation data. The Bingham distribution is an antipodally-symmetric, max-entropy distribution on the unit quaternion hypersphere. The proposed algorithm also introduces a minimum message length criterion, a common tool in information theory for balancing data likelihood with model complexity, to determine the number of components in the Bingham mixture. This criterion leads to ODFs which are less likely to overfit (or underfit) the data, eliminating the need for a priori parameter choices.

  13. Audio-based, unsupervised machine learning reveals cyclic changes in earthquake mechanisms in the Geysers geothermal field, California

    Science.gov (United States)

    Holtzman, B. K.; Paté, A.; Paisley, J.; Waldhauser, F.; Repetto, D.; Boschi, L.

    2017-12-01

    The earthquake process reflects complex interactions of stress, fracture and frictional properties. New machine learning methods reveal patterns in time-dependent spectral properties of seismic signals and enable identification of changes in faulting processes. Our methods are based closely on those developed for music information retrieval and voice recognition, using the spectrogram instead of the waveform directly. Unsupervised learning involves identification of patterns based on differences among signals without any additional information provided to the algorithm. Clustering of 46,000 earthquakes of $0.3

  14. Machine learning in APOGEE. Unsupervised spectral classification with K-means

    Science.gov (United States)

    Garcia-Dias, Rafael; Allende Prieto, Carlos; Sánchez Almeida, Jorge; Ordovás-Pascual, Ignacio

    2018-05-01

    Context. The volume of data generated by astronomical surveys is growing rapidly. Traditional analysis techniques in spectroscopy either demand intensive human interaction or are computationally expensive. In this scenario, machine learning, and unsupervised clustering algorithms in particular, offer interesting alternatives. The Apache Point Observatory Galactic Evolution Experiment (APOGEE) offers a vast data set of near-infrared stellar spectra, which is perfect for testing such alternatives. Aims: Our research applies an unsupervised classification scheme based on K-means to the massive APOGEE data set. We explore whether the data are amenable to classification into discrete classes. Methods: We apply the K-means algorithm to 153 847 high resolution spectra (R ≈ 22 500). We discuss the main virtues and weaknesses of the algorithm, as well as our choice of parameters. Results: We show that a classification based on normalised spectra captures the variations in stellar atmospheric parameters, chemical abundances, and rotational velocity, among other factors. The algorithm is able to separate the bulge and halo populations, and distinguish dwarfs, sub-giants, RC, and RGB stars. However, a discrete classification in flux space does not result in a neat organisation in the parameters' space. Furthermore, the lack of obvious groups in flux space causes the results to be fairly sensitive to the initialisation, and disrupts the efficiency of commonly-used methods to select the optimal number of clusters. Our classification is publicly available, including extensive online material associated with the APOGEE Data Release 12 (DR12). Conclusions: Our description of the APOGEE database can help greatly with the identification of specific types of targets for various applications. We find a lack of obvious groups in flux space, and identify limitations of the K-means algorithm in dealing with this kind of data. Full Tables B.1-B.4 are only available at the CDS via

  15. Resting-state fMRI activity predicts unsupervised learning and memory in an immersive virtual reality environment.

    Directory of Open Access Journals (Sweden)

    Chi Wah Wong

    Full Text Available In the real world, learning often proceeds in an unsupervised manner without explicit instructions or feedback. In this study, we employed an experimental paradigm in which subjects explored an immersive virtual reality environment on each of two days. On day 1, subjects implicitly learned the location of 39 objects in an unsupervised fashion. On day 2, the locations of some of the objects were changed, and object location recall performance was assessed and found to vary across subjects. As prior work had shown that functional magnetic resonance imaging (fMRI measures of resting-state brain activity can predict various measures of brain performance across individuals, we examined whether resting-state fMRI measures could be used to predict object location recall performance. We found a significant correlation between performance and the variability of the resting-state fMRI signal in the basal ganglia, hippocampus, amygdala, thalamus, insula, and regions in the frontal and temporal lobes, regions important for spatial exploration, learning, memory, and decision making. In addition, performance was significantly correlated with resting-state fMRI connectivity between the left caudate and the right fusiform gyrus, lateral occipital complex, and superior temporal gyrus. Given the basal ganglia's role in exploration, these findings suggest that tighter integration of the brain systems responsible for exploration and visuospatial processing may be critical for learning in a complex environment.

  16. Superior arm-movement decoding from cortex with a new, unsupervised-learning algorithm

    Science.gov (United States)

    Makin, Joseph G.; O'Doherty, Joseph E.; Cardoso, Mariana M. B.; Sabes, Philip N.

    2018-04-01

    Objective. The aim of this work is to improve the state of the art for motor-control with a brain-machine interface (BMI). BMIs use neurological recording devices and decoding algorithms to transform brain activity directly into real-time control of a machine, archetypically a robotic arm or a cursor. The standard procedure treats neural activity—vectors of spike counts in small temporal windows—as noisy observations of the kinematic state (position, velocity, acceleration) of the fingertip. Inferring the state from the observations then takes the form of a dynamical filter, typically some variant on Kalman’s (KF). The KF, however, although fairly robust in practice, is optimal only when the relationships between variables are linear and the noise is Gaussian, conditions usually violated in practice. Approach. To overcome these limitations we introduce a new filter, the ‘recurrent exponential-family harmonium’ (rEFH), that models the spike counts explicitly as Poisson-distributed, and allows for arbitrary nonlinear dynamics and observation models. Furthermore, the model underlying the filter is acquired through unsupervised learning, which allows temporal correlations in spike counts to be explained by latent dynamics that do not necessarily correspond to the kinematic state of the fingertip. Main results. We test the rEFH on offline reconstruction of the kinematics of reaches in the plane. The rEFH outperforms the standard, as well as three other state-of-the-art, decoders, across three monkeys, two different tasks, most kinematic variables, and a range of bin widths, amounts of training data, and numbers of neurons. Significance. Our algorithm establishes a new state of the art for offline decoding of reaches—in particular, for fingertip velocities, the variable used for control in most online decoders.

  17. Double-Barrier Memristive Devices for Unsupervised Learning and Pattern Recognition.

    Science.gov (United States)

    Hansen, Mirko; Zahari, Finn; Ziegler, Martin; Kohlstedt, Hermann

    2017-01-01

    The use of interface-based resistive switching devices for neuromorphic computing is investigated. In a combined experimental and numerical study, the important device parameters and their impact on a neuromorphic pattern recognition system are studied. The memristive cells consist of a layer sequence Al/Al 2 O 3 /Nb x O y /Au and are fabricated on a 4-inch wafer. The key functional ingredients of the devices are a 1.3 nm thick Al 2 O 3 tunnel barrier and a 2.5 mm thick Nb x O y memristive layer. Voltage pulse measurements are used to study the electrical conditions for the emulation of synaptic functionality of single cells for later use in a recognition system. The results are evaluated and modeled in the framework of the plasticity model of Ziegler et al. Based on this model, which is matched to experimental data from 84 individual devices, the network performance with regard to yield, reliability, and variability is investigated numerically. As the network model, a computing scheme for pattern recognition and unsupervised learning based on the work of Querlioz et al. (2011), Sheridan et al. (2014), Zahari et al. (2015) is employed. This is a two-layer feedforward network with a crossbar array of memristive devices, leaky integrate-and-fire output neurons including a winner-takes-all strategy, and a stochastic coding scheme for the input pattern. As input pattern, the full data set of digits from the MNIST database is used. The numerical investigation indicates that the experimentally obtained yield, reliability, and variability of the memristive cells are suitable for such a network. Furthermore, evidence is presented that their strong I - V non-linearity might avoid the need for selector devices in crossbar array structures.

  18. On the Multi-Modal Object Tracking and Image Fusion Using Unsupervised Deep Learning Methodologies

    Science.gov (United States)

    LaHaye, N.; Ott, J.; Garay, M. J.; El-Askary, H. M.; Linstead, E.

    2017-12-01

    The number of different modalities of remote-sensors has been on the rise, resulting in large datasets with different complexity levels. Such complex datasets can provide valuable information separately, yet there is a bigger value in having a comprehensive view of them combined. As such, hidden information can be deduced through applying data mining techniques on the fused data. The curse of dimensionality of such fused data, due to the potentially vast dimension space, hinders our ability to have deep understanding of them. This is because each dataset requires a user to have instrument-specific and dataset-specific knowledge for optimum and meaningful usage. Once a user decides to use multiple datasets together, deeper understanding of translating and combining these datasets in a correct and effective manner is needed. Although there exists data centric techniques, generic automated methodologies that can potentially solve this problem completely don't exist. Here we are developing a system that aims to gain a detailed understanding of different data modalities. Such system will provide an analysis environment that gives the user useful feedback and can aid in research tasks. In our current work, we show the initial outputs our system implementation that leverages unsupervised deep learning techniques so not to burden the user with the task of labeling input data, while still allowing for a detailed machine understanding of the data. Our goal is to be able to track objects, like cloud systems or aerosols, across different image-like data-modalities. The proposed system is flexible, scalable and robust to understand complex likenesses within multi-modal data in a similar spatio-temporal range, and also to be able to co-register and fuse these images when needed.

  19. Glaucomatous patterns in Frequency Doubling Technology (FDT) perimetry data identified by unsupervised machine learning classifiers.

    Science.gov (United States)

    Bowd, Christopher; Weinreb, Robert N; Balasubramanian, Madhusudhanan; Lee, Intae; Jang, Giljin; Yousefi, Siamak; Zangwill, Linda M; Medeiros, Felipe A; Girkin, Christopher A; Liebmann, Jeffrey M; Goldbaum, Michael H

    2014-01-01

    The variational Bayesian independent component analysis-mixture model (VIM), an unsupervised machine-learning classifier, was used to automatically separate Matrix Frequency Doubling Technology (FDT) perimetry data into clusters of healthy and glaucomatous eyes, and to identify axes representing statistically independent patterns of defect in the glaucoma clusters. FDT measurements were obtained from 1,190 eyes with normal FDT results and 786 eyes with abnormal FDT results from the UCSD-based Diagnostic Innovations in Glaucoma Study (DIGS) and African Descent and Glaucoma Evaluation Study (ADAGES). For all eyes, VIM input was 52 threshold test points from the 24-2 test pattern, plus age. FDT mean deviation was -1.00 dB (S.D. = 2.80 dB) and -5.57 dB (S.D. = 5.09 dB) in FDT-normal eyes and FDT-abnormal eyes, respectively (p<0.001). VIM identified meaningful clusters of FDT data and positioned a set of statistically independent axes through the mean of each cluster. The optimal VIM model separated the FDT fields into 3 clusters. Cluster N contained primarily normal fields (1109/1190, specificity 93.1%) and clusters G1 and G2 combined, contained primarily abnormal fields (651/786, sensitivity 82.8%). For clusters G1 and G2 the optimal number of axes were 2 and 5, respectively. Patterns automatically generated along axes within the glaucoma clusters were similar to those known to be indicative of glaucoma. Fields located farther from the normal mean on each glaucoma axis showed increasing field defect severity. VIM successfully separated FDT fields from healthy and glaucoma eyes without a priori information about class membership, and identified familiar glaucomatous patterns of loss.

  20. Recent progresses of neural network unsupervised learning: I. Independent component analyses generalizing PCA

    Science.gov (United States)

    Szu, Harold H.

    1999-03-01

    The early vision principle of redundancy reduction of 108 sensor excitations is understandable from computer vision viewpoint toward sparse edge maps. It is only recently derived using a truly unsupervised learning paradigm of artificial neural networks (ANN). In fact, the biological vision, Hubel- Wiesel edge maps, is reproduced seeking the underlying independent components analyses (ICA) among 102 image samples by maximizing the ANN output entropy (partial)H(V)/(partial)[W] equals (partial)[W]/(partial)t. When a pair of newborn eyes or ears meet the bustling and hustling world without supervision, they seek ICA by comparing 2 sensory measurements (x1(t), x2(t))T equalsV X(t). Assuming a linear and instantaneous mixture model of the external world X(t) equals [A] S(t), where both the mixing matrix ([A] equalsV [a1, a2] of ICA vectors and the source percentages (s1(t), s2(t))T equalsV S(t) are unknown, we seek the independent sources approximately equals [I] where the approximated sign indicates that higher order statistics (HOS) may not be trivial. Without a teacher, the ANN weight matrix [W] equalsV [w1, w2] adjusts the outputs V(t) equals tanh([W]X(t)) approximately equals [W]X(t) until no desired outputs except the (Gaussian) 'garbage' (neither YES '1' nor NO '-1' but at linear may-be range 'origin 0') defined by Gaussian covariance G equals [I] equals [W][A] the internal knowledge representation [W], as the inverse of the external world matrix [A]-1. To unify IC, PCA, ANN & HOS theories since 1991 (advanced by Jutten & Herault, Comon, Oja, Bell-Sejnowski, Amari-Cichocki, Cardoso), the LYAPONOV function L(v1,...,vn, w1,...wn,) equals E(v1,...,vn) - H(w1,...wn) is constructed as the HELMHOTZ free energy to prove both convergences of supervised energy E and unsupervised entropy H learning. Consequently, rather using the faithful but dumb computer: 'GARBAGE-IN, GARBAGE-OUT,' the smarter neurocomputer will be equipped with an unsupervised learning that extracts

  1. Learning Microbial Community Structures with Supervised and Unsupervised Non-negative Matrix Factorization.

    Science.gov (United States)

    Cai, Yun; Gu, Hong; Kenney, Toby

    2017-08-31

    Learning the structure of microbial communities is critical in understanding the different community structures and functions of microbes in distinct individuals. We view microbial communities as consisting of many subcommunities which are formed by certain groups of microbes functionally dependent on each other. The focus of this paper is on methods for extracting the subcommunities from the data, in particular Non-Negative Matrix Factorization (NMF). Our methods can be applied to both OTU data and functional metagenomic data. We apply the existing unsupervised NMF method and also develop a new supervised NMF method for extracting interpretable information from classification problems. The relevance of the subcommunities identified by NMF is demonstrated by their excellent performance for classification. Through three data examples, we demonstrate how to interpret the features identified by NMF to draw meaningful biological conclusions and discover hitherto unidentified patterns in the data. Comparing whole metagenomes of various mammals, (Muegge et al., Science 332:970-974, 2011), the biosynthesis of macrolides pathway is found in hindgut-fermenting herbivores, but not carnivores. This is consistent with results in veterinary science that macrolides should not be given to non-ruminant herbivores. For time series microbiome data from various body sites (Caporaso et al., Genome Biol 12:50, 2011), a shift in the microbial communities is identified for one individual. The shift occurs at around the same time in the tongue and gut microbiomes, indicating that the shift is a genuine biological trait, rather than an artefact of the method. For whole metagenome data from IBD patients and healthy controls (Qin et al., Nature 464:59-65, 2010), we identify differences in a number of pathways (some known, others new). NMF is a powerful tool for identifying the key features of microbial communities. These identified features can not only be used to perform difficult

  2. Mining FDA drug labels using an unsupervised learning technique--topic modeling.

    Science.gov (United States)

    Bisgin, Halil; Liu, Zhichao; Fang, Hong; Xu, Xiaowei; Tong, Weida

    2011-10-18

    The Food and Drug Administration (FDA) approved drug labels contain a broad array of information, ranging from adverse drug reactions (ADRs) to drug efficacy, risk-benefit consideration, and more. However, the labeling language used to describe these information is free text often containing ambiguous semantic descriptions, which poses a great challenge in retrieving useful information from the labeling text in a consistent and accurate fashion for comparative analysis across drugs. Consequently, this task has largely relied on the manual reading of the full text by experts, which is time consuming and labor intensive. In this study, a novel text mining method with unsupervised learning in nature, called topic modeling, was applied to the drug labeling with a goal of discovering "topics" that group drugs with similar safety concerns and/or therapeutic uses together. A total of 794 FDA-approved drug labels were used in this study. First, the three labeling sections (i.e., Boxed Warning, Warnings and Precautions, Adverse Reactions) of each drug label were processed by the Medical Dictionary for Regulatory Activities (MedDRA) to convert the free text of each label to the standard ADR terms. Next, the topic modeling approach with latent Dirichlet allocation (LDA) was applied to generate 100 topics, each associated with a set of drugs grouped together based on the probability analysis. Lastly, the efficacy of the topic modeling was evaluated based on known information about the therapeutic uses and safety data of drugs. The results demonstrate that drugs grouped by topics are associated with the same safety concerns and/or therapeutic uses with statistical significance (P<0.05). The identified topics have distinct context that can be directly linked to specific adverse events (e.g., liver injury or kidney injury) or therapeutic application (e.g., antiinfectives for systemic use). We were also able to identify potential adverse events that might arise from specific

  3. Mining FDA drug labels using an unsupervised learning technique - topic modeling

    Science.gov (United States)

    2011-01-01

    Background The Food and Drug Administration (FDA) approved drug labels contain a broad array of information, ranging from adverse drug reactions (ADRs) to drug efficacy, risk-benefit consideration, and more. However, the labeling language used to describe these information is free text often containing ambiguous semantic descriptions, which poses a great challenge in retrieving useful information from the labeling text in a consistent and accurate fashion for comparative analysis across drugs. Consequently, this task has largely relied on the manual reading of the full text by experts, which is time consuming and labor intensive. Method In this study, a novel text mining method with unsupervised learning in nature, called topic modeling, was applied to the drug labeling with a goal of discovering “topics” that group drugs with similar safety concerns and/or therapeutic uses together. A total of 794 FDA-approved drug labels were used in this study. First, the three labeling sections (i.e., Boxed Warning, Warnings and Precautions, Adverse Reactions) of each drug label were processed by the Medical Dictionary for Regulatory Activities (MedDRA) to convert the free text of each label to the standard ADR terms. Next, the topic modeling approach with latent Dirichlet allocation (LDA) was applied to generate 100 topics, each associated with a set of drugs grouped together based on the probability analysis. Lastly, the efficacy of the topic modeling was evaluated based on known information about the therapeutic uses and safety data of drugs. Results The results demonstrate that drugs grouped by topics are associated with the same safety concerns and/or therapeutic uses with statistical significance (P<0.05). The identified topics have distinct context that can be directly linked to specific adverse events (e.g., liver injury or kidney injury) or therapeutic application (e.g., antiinfectives for systemic use). We were also able to identify potential adverse events that

  4. ISO learning approximates a solution to the inverse-controller problem in an unsupervised behavioral paradigm.

    Science.gov (United States)

    Porr, Bernd; von Ferber, Christian; Wörgötter, Florentin

    2003-04-01

    In "Isotropic Sequence Order Learning" (pp. 831-864 in this issue), we introduced a novel algorithm for temporal sequence learning (ISO learning). Here, we embed this algorithm into a formal nonevaluating (teacher free) environment, which establishes a sensor-motor feedback. The system is initially guided by a fixed reflex reaction, which has the objective disadvantage that it can react only after a disturbance has occurred. ISO learning eliminates this disadvantage by replacing the reflex-loop reactions with earlier anticipatory actions. In this article, we analytically demonstrate that this process can be understood in terms of control theory, showing that the system learns the inverse controller of its own reflex. Thereby, this system is able to learn a simple form of feedforward motor control.

  5. Spiking Neural Networks with Unsupervised Learning Based on STDP Using Resistive Synaptic Devices and Analog CMOS Neuron Circuit.

    Science.gov (United States)

    Kwon, Min-Woo; Baek, Myung-Hyun; Hwang, Sungmin; Kim, Sungjun; Park, Byung-Gook

    2018-09-01

    We designed the CMOS analog integrate and fire (I&F) neuron circuit can drive resistive synaptic device. The neuron circuit consists of a current mirror for spatial integration, a capacitor for temporal integration, asymmetric negative and positive pulse generation part, a refractory part, and finally a back-propagation pulse generation part for learning of the synaptic devices. The resistive synaptic devices were fabricated using HfOx switching layer by atomic layer deposition (ALD). The resistive synaptic device had gradual set and reset characteristics and the conductance was adjusted by spike-timing-dependent-plasticity (STDP) learning rule. We carried out circuit simulation of synaptic device and CMOS neuron circuit. And we have developed an unsupervised spiking neural networks (SNNs) for 5 × 5 pattern recognition and classification using the neuron circuit and synaptic devices. The hardware-based SNNs can autonomously and efficiently control the weight updates of the synapses between neurons, without the aid of software calculations.

  6. Unsupervised deep learning applied to breast density segmentation and mammographic risk scoring

    DEFF Research Database (Denmark)

    Kallenberg, Michiel Gijsbertus J.; Petersen, Peter Kersten; Nielsen, Mads

    2016-01-01

    Mammographic risk scoring has commonly been automated by extracting a set of handcrafted features from mammograms, and relating the responses directly or indirectly to breast cancer risk. We present a method that learns a feature hierarchy from unlabeled data. When the learned features are used...... as the input to a simple classifier, two different tasks can be addressed: i) breast density segmentation, and ii) scoring of mammographic texture. The proposed model learns features at multiple scales. To control the models capacity a novel sparsity regularizer is introduced that incorporates both lifetime...... and population sparsity. We evaluated our method on three different clinical datasets. Our state-of-the-art results show that the learned breast density scores have a very strong positive relationship with manual ones, and that the learned texture scores are predictive of breast cancer. The model is easy...

  7. Model-Based Learning of Local Image Features for Unsupervised Texture Segmentation

    Science.gov (United States)

    Kiechle, Martin; Storath, Martin; Weinmann, Andreas; Kleinsteuber, Martin

    2018-04-01

    Features that capture well the textural patterns of a certain class of images are crucial for the performance of texture segmentation methods. The manual selection of features or designing new ones can be a tedious task. Therefore, it is desirable to automatically adapt the features to a certain image or class of images. Typically, this requires a large set of training images with similar textures and ground truth segmentation. In this work, we propose a framework to learn features for texture segmentation when no such training data is available. The cost function for our learning process is constructed to match a commonly used segmentation model, the piecewise constant Mumford-Shah model. This means that the features are learned such that they provide an approximately piecewise constant feature image with a small jump set. Based on this idea, we develop a two-stage algorithm which first learns suitable convolutional features and then performs a segmentation. We note that the features can be learned from a small set of images, from a single image, or even from image patches. The proposed method achieves a competitive rank in the Prague texture segmentation benchmark, and it is effective for segmenting histological images.

  8. Ensemble learning with trees and rules: supervised, semi-supervised, unsupervised

    Science.gov (United States)

    In this article, we propose several new approaches for post processing a large ensemble of conjunctive rules for supervised and semi-supervised learning problems. We show with various examples that for high dimensional regression problems the models constructed by the post processing the rules with ...

  9. Application of cluster analysis and unsupervised learning to multivariate tissue characterization

    International Nuclear Information System (INIS)

    Momenan, R.; Insana, M.F.; Wagner, R.F.; Garra, B.S.; Loew, M.H.

    1987-01-01

    This paper describes a procedure for classifying tissue types from unlabeled acoustic measurements (data type unknown) using unsupervised cluster analysis. These techniques are being applied to unsupervised ultrasonic image segmentation and tissue characterization. The performance of a new clustering technique is measured and compared with supervised methods, such as a linear Bayes classifier. In these comparisons two objectives are sought: a) How well does the clustering method group the data?; b) Do the clusters correspond to known tissue classes? The first question is investigated by a measure of cluster similarity and dispersion. The second question involves a comparison with a supervised technique using labeled data

  10. Model–Free Visualization of Suspicious Lesions in Breast MRI Based on Supervised and Unsupervised Learning

    NARCIS (Netherlands)

    Twellmann, T.; Meyer-Bäse, A.; Lange, O.; Foo, S.; Nattkemper, T.W.

    2008-01-01

    Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has become an important tool in breast cancer diagnosis, but evaluation of multitemporal 3D image data holds new challenges for human observers. To aid the image analysis process, we apply supervised and unsupervised pattern recognition

  11. Multiresolutional schemata for unsupervised learning of autonomous robots for 3D space operation

    Science.gov (United States)

    Lacaze, Alberto; Meystel, Michael; Meystel, Alex

    1994-01-01

    This paper describes a novel approach to the development of a learning control system for autonomous space robot (ASR) which presents the ASR as a 'baby' -- that is, a system with no a priori knowledge of the world in which it operates, but with behavior acquisition techniques that allows it to build this knowledge from the experiences of actions within a particular environment (we will call it an Astro-baby). The learning techniques are rooted in the recursive algorithm for inductive generation of nested schemata molded from processes of early cognitive development in humans. The algorithm extracts data from the environment and by means of correlation and abduction, it creates schemata that are used for control. This system is robust enough to deal with a constantly changing environment because such changes provoke the creation of new schemata by generalizing from experiences, while still maintaining minimal computational complexity, thanks to the system's multiresolutional nature.

  12. Combining Unsupervised and Supervised Statistical Learning Methods for Currency Exchange Rate Forecasting

    OpenAIRE

    Vasiljeva, Polina

    2016-01-01

    In this thesis we revisit the challenging problem of forecasting currency exchange rate. We combine machine learning methods such as agglomerative hierarchical clustering and random forest to construct a two-step approach for predicting movements in currency exchange prices of the Swedish krona and the US dollar. We use a data set with over 200 predictors comprised of different financial and macro-economic time series and their transformations. We perform forecasting for one week ahead with d...

  13. Using Unsupervised Machine Learning for Outlier Detection in Data to Improve Wind Power Production Prediction

    OpenAIRE

    Åkerberg, Ludvig

    2017-01-01

    The expansion of wind power for electrical energy production has increased in recent years and shows no signs of slowing down. This unpredictable source of energy has contributed to destabilization of the electrical grid causing the energy market prices to vary significantly on a daily basis. For energy producers and consumers to make good investments, methods have been developed to make predictions of wind power production. These methods are often based on machine learning were historical we...

  14. Real time unsupervised learning of visual stimuli in neuromorphic VLSI systems

    Science.gov (United States)

    Giulioni, Massimiliano; Corradi, Federico; Dante, Vittorio; Del Giudice, Paolo

    2015-10-01

    Neuromorphic chips embody computational principles operating in the nervous system, into microelectronic devices. In this domain it is important to identify computational primitives that theory and experiments suggest as generic and reusable cognitive elements. One such element is provided by attractor dynamics in recurrent networks. Point attractors are equilibrium states of the dynamics (up to fluctuations), determined by the synaptic structure of the network; a ‘basin’ of attraction comprises all initial states leading to a given attractor upon relaxation, hence making attractor dynamics suitable to implement robust associative memory. The initial network state is dictated by the stimulus, and relaxation to the attractor state implements the retrieval of the corresponding memorized prototypical pattern. In a previous work we demonstrated that a neuromorphic recurrent network of spiking neurons and suitably chosen, fixed synapses supports attractor dynamics. Here we focus on learning: activating on-chip synaptic plasticity and using a theory-driven strategy for choosing network parameters, we show that autonomous learning, following repeated presentation of simple visual stimuli, shapes a synaptic connectivity supporting stimulus-selective attractors. Associative memory develops on chip as the result of the coupled stimulus-driven neural activity and ensuing synaptic dynamics, with no artificial separation between learning and retrieval phases.

  15. An evaluation of unsupervised and supervised learning algorithms for clustering landscape types in the United States

    Science.gov (United States)

    Wendel, Jochen; Buttenfield, Barbara P.; Stanislawski, Larry V.

    2016-01-01

    Knowledge of landscape type can inform cartographic generalization of hydrographic features, because landscape characteristics provide an important geographic context that affects variation in channel geometry, flow pattern, and network configuration. Landscape types are characterized by expansive spatial gradients, lacking abrupt changes between adjacent classes; and as having a limited number of outliers that might confound classification. The US Geological Survey (USGS) is exploring methods to automate generalization of features in the National Hydrography Data set (NHD), to associate specific sequences of processing operations and parameters with specific landscape characteristics, thus obviating manual selection of a unique processing strategy for every NHD watershed unit. A chronology of methods to delineate physiographic regions for the United States is described, including a recent maximum likelihood classification based on seven input variables. This research compares unsupervised and supervised algorithms applied to these seven input variables, to evaluate and possibly refine the recent classification. Evaluation metrics for unsupervised methods include the Davies–Bouldin index, the Silhouette index, and the Dunn index as well as quantization and topographic error metrics. Cross validation and misclassification rate analysis are used to evaluate supervised classification methods. The paper reports the comparative analysis and its impact on the selection of landscape regions. The compared solutions show problems in areas of high landscape diversity. There is some indication that additional input variables, additional classes, or more sophisticated methods can refine the existing classification.

  16. Unsupervised Learning —A Novel Clustering Method for Rolling Bearing Faults Identification

    Science.gov (United States)

    Kai, Li; Bo, Luo; Tao, Ma; Xuefeng, Yang; Guangming, Wang

    2017-12-01

    To promptly process the massive fault data and automatically provide accurate diagnosis results, numerous studies have been conducted on intelligent fault diagnosis of rolling bearing. Among these studies, such as artificial neural networks, support vector machines, decision trees and other supervised learning methods are used commonly. These methods can detect the failure of rolling bearing effectively, but to achieve better detection results, it often requires a lot of training samples. Based on above, a novel clustering method is proposed in this paper. This novel method is able to find the correct number of clusters automatically the effectiveness of the proposed method is validated using datasets from rolling element bearings. The diagnosis results show that the proposed method can accurately detect the fault types of small samples. Meanwhile, the diagnosis results are also relative high accuracy even for massive samples.

  17. ClusterTAD: an unsupervised machine learning approach to detecting topologically associated domains of chromosomes from Hi-C data.

    Science.gov (United States)

    Oluwadare, Oluwatosin; Cheng, Jianlin

    2017-11-14

    With the development of chromosomal conformation capturing techniques, particularly, the Hi-C technique, the study of the spatial conformation of a genome is becoming an important topic in bioinformatics and computational biology. The Hi-C technique can generate genome-wide chromosomal interaction (contact) data, which can be used to investigate the higher-level organization of chromosomes, such as Topologically Associated Domains (TAD), i.e., locally packed chromosome regions bounded together by intra chromosomal contacts. The identification of the TADs for a genome is useful for studying gene regulation, genomic interaction, and genome function. Here, we formulate the TAD identification problem as an unsupervised machine learning (clustering) problem, and develop a new TAD identification method called ClusterTAD. We introduce a novel method to represent chromosomal contacts as features to be used by the clustering algorithm. Our results show that ClusterTAD can accurately predict the TADs on a simulated Hi-C data. Our method is also largely complementary and consistent with existing methods on the real Hi-C datasets of two mouse cells. The validation with the chromatin immunoprecipitation (ChIP) sequencing (ChIP-Seq) data shows that the domain boundaries identified by ClusterTAD have a high enrichment of CTCF binding sites, promoter-related marks, and enhancer-related histone modifications. As ClusterTAD is based on a proven clustering approach, it opens a new avenue to apply a large array of clustering methods developed in the machine learning field to the TAD identification problem. The source code, the results, and the TADs generated for the simulated and real Hi-C datasets are available here: https://github.com/BDM-Lab/ClusterTAD .

  18. An unsupervised learning algorithm: application to the discrimination of seismic events and quarry blasts in the vicinity of Istanbul

    Directory of Open Access Journals (Sweden)

    H. S. Kuyuk

    2011-01-01

    Full Text Available The results of the application of an unsupervised learning (neural network approach comprising a Self Organizing Map (SOM, to distinguish micro-earthquakes from quarry blasts in the vicinity of Istanbul, Turkey, are presented and discussed. The SOM is constructed as a neural classifier and complementary reliability estimator to distinguish seismic events, and was employed for varying map sizes. Input parameters consisting of frequency and time domain data (complexity, spectral ratio, S/P wave amplitude peak ratio and origin time of events extracted from the vertical components of digital seismograms were estimated as discriminants for 179 (1.8 < Md < 3.0 local events. The results show that complexity and amplitude peak ratio parameters of the observed velocity seismogram may suffice for a reliable discrimination, while origin time and spectral ratio were found to be fuzzy and misleading classifiers for this problem. The SOM discussed here achieved a discrimination reliability that could be employed routinely in observatory practice; however, about 6% of all events were classified as ambiguous cases. This approach was developed independently for this particular classification, but it could be applied to different earthquake regions.

  19. Scaling up spike-and-slab models for unsupervised feature learning.

    Science.gov (United States)

    Goodfellow, Ian J; Courville, Aaron; Bengio, Yoshua

    2013-08-01

    We describe the use of two spike-and-slab models for modeling real-valued data, with an emphasis on their applications to object recognition. The first model, which we call spike-and-slab sparse coding (S3C), is a preexisting model for which we introduce a faster approximate inference algorithm. We introduce a deep variant of S3C, which we call the partially directed deep Boltzmann machine (PD-DBM) and extend our S3C inference algorithm for use on this model. We describe learning procedures for each. We demonstrate that our inference procedure for S3C enables scaling the model to unprecedented large problem sizes, and demonstrate that using S3C as a feature extractor results in very good object recognition performance, particularly when the number of labeled examples is low. We show that the PD-DBM generates better samples than its shallow counterpart, and that unlike DBMs or DBNs, the PD-DBM may be trained successfully without greedy layerwise training.

  20. Mastication Evaluation With Unsupervised Learning: Using an Inertial Sensor-Based System

    Science.gov (United States)

    Lucena, Caroline Vieira; Lacerda, Marcelo; Caldas, Rafael; De Lima Neto, Fernando Buarque

    2018-01-01

    There is a direct relationship between the prevalence of musculoskeletal disorders of the temporomandibular joint and orofacial disorders. A well-elaborated analysis of the jaw movements provides relevant information for healthcare professionals to conclude their diagnosis. Different approaches have been explored to track jaw movements such that the mastication analysis is getting less subjective; however, all methods are still highly subjective, and the quality of the assessments depends much on the experience of the health professional. In this paper, an accurate and non-invasive method based on a commercial low-cost inertial sensor (MPU6050) to measure jaw movements is proposed. The jaw-movement feature values are compared to the obtained with clinical analysis, showing no statistically significant difference between both methods. Moreover, We propose to use unsupervised paradigm approaches to cluster mastication patterns of healthy subjects and simulated patients with facial trauma. Two techniques were used in this paper to instantiate the method: Kohonen’s Self-Organizing Maps and K-Means Clustering. Both algorithms have excellent performances to process jaw-movements data, showing encouraging results and potential to bring a full assessment of the masticatory function. The proposed method can be applied in real-time providing relevant dynamic information for health-care professionals. PMID:29651365

  1. Spectrum Hole Identification in IEEE 802.22 WRAN using Unsupervised Learning

    Directory of Open Access Journals (Sweden)

    V. Balaji

    2016-01-01

    Full Text Available In this paper we present a Cooperative Spectrum Sensing (CSS algorithm for Cognitive Radios (CR based on IEEE 802.22Wireless Regional Area Network (WRAN standard. The core objective is to improve cooperative sensing efficiency which specifies how fast a decision can be reached in each round of cooperation (iteration to sense an appropriate number of channels/bands (i.e. 86 channels of 7MHz bandwidth as per IEEE 802.22 within a time constraint (channel sensing time. To meet this objective, we have developed CSS algorithm using unsupervised K-means clustering classification approach. The received energy level of each Secondary User (SU is considered as the parameter for determining channel availability. The performance of proposed algorithm is quantified in terms of detection accuracy, training and classification delay time. Further, the detection accuracy of our proposed scheme meets the requirement of IEEE 802.22 WRAN with the target probability of falsealrm as 0.1. All the simulations are carried out using Matlab tool.

  2. Mastication Evaluation With Unsupervised Learning: Using an Inertial Sensor-Based System.

    Science.gov (United States)

    Lucena, Caroline Vieira; Lacerda, Marcelo; Caldas, Rafael; De Lima Neto, Fernando Buarque; Rativa, Diego

    2018-01-01

    There is a direct relationship between the prevalence of musculoskeletal disorders of the temporomandibular joint and orofacial disorders. A well-elaborated analysis of the jaw movements provides relevant information for healthcare professionals to conclude their diagnosis. Different approaches have been explored to track jaw movements such that the mastication analysis is getting less subjective; however, all methods are still highly subjective, and the quality of the assessments depends much on the experience of the health professional. In this paper, an accurate and non-invasive method based on a commercial low-cost inertial sensor (MPU6050) to measure jaw movements is proposed. The jaw-movement feature values are compared to the obtained with clinical analysis, showing no statistically significant difference between both methods. Moreover, We propose to use unsupervised paradigm approaches to cluster mastication patterns of healthy subjects and simulated patients with facial trauma. Two techniques were used in this paper to instantiate the method: Kohonen's Self-Organizing Maps and K-Means Clustering. Both algorithms have excellent performances to process jaw-movements data, showing encouraging results and potential to bring a full assessment of the masticatory function. The proposed method can be applied in real-time providing relevant dynamic information for health-care professionals.

  3. Learning

    Directory of Open Access Journals (Sweden)

    Mohsen Laabidi

    2014-01-01

    Full Text Available Nowadays learning technologies transformed educational systems with impressive progress of Information and Communication Technologies (ICT. Furthermore, when these technologies are available, affordable and accessible, they represent more than a transformation for people with disabilities. They represent real opportunities with access to an inclusive education and help to overcome the obstacles they met in classical educational systems. In this paper, we will cover basic concepts of e-accessibility, universal design and assistive technologies, with a special focus on accessible e-learning systems. Then, we will present recent research works conducted in our research Laboratory LaTICE toward the development of an accessible online learning environment for persons with disabilities from the design and specification step to the implementation. We will present, in particular, the accessible version “MoodleAcc+” of the well known e-learning platform Moodle as well as new elaborated generic models and a range of tools for authoring and evaluating accessible educational content.

  4. An Accurate CT Saturation Classification Using a Deep Learning Approach Based on Unsupervised Feature Extraction and Supervised Fine-Tuning Strategy

    Directory of Open Access Journals (Sweden)

    Muhammad Ali

    2017-11-01

    Full Text Available Current transformer (CT saturation is one of the significant problems for protection engineers. If CT saturation is not tackled properly, it can cause a disastrous effect on the stability of the power system, and may even create a complete blackout. To cope with CT saturation properly, an accurate detection or classification should be preceded. Recently, deep learning (DL methods have brought a subversive revolution in the field of artificial intelligence (AI. This paper presents a new DL classification method based on unsupervised feature extraction and supervised fine-tuning strategy to classify the saturated and unsaturated regions in case of CT saturation. In other words, if protection system is subjected to a CT saturation, proposed method will correctly classify the different levels of saturation with a high accuracy. Traditional AI methods are mostly based on supervised learning and rely heavily on human crafted features. This paper contributes to an unsupervised feature extraction, using autoencoders and deep neural networks (DNNs to extract features automatically without prior knowledge of optimal features. To validate the effectiveness of proposed method, a variety of simulation tests are conducted, and classification results are analyzed using standard classification metrics. Simulation results confirm that proposed method classifies the different levels of CT saturation with a remarkable accuracy and has unique feature extraction capabilities. Lastly, we provided a potential future research direction to conclude this paper.

  5. An Overview of Deep Learning Based Methods for Unsupervised and Semi-Supervised Anomaly Detection in Videos

    Directory of Open Access Journals (Sweden)

    B. Ravi Kiran

    2018-02-01

    Full Text Available Videos represent the primary source of information for surveillance applications. Video material is often available in large quantities but in most cases it contains little or no annotation for supervised learning. This article reviews the state-of-the-art deep learning based methods for video anomaly detection and categorizes them based on the type of model and criteria of detection. We also perform simple studies to understand the different approaches and provide the criteria of evaluation for spatio-temporal anomaly detection.

  6. Towards a new classification of stable phase schizophrenia into major and simple neuro-cognitive psychosis: Results of unsupervised machine learning analysis.

    Science.gov (United States)

    Kanchanatawan, Buranee; Sriswasdi, Sira; Thika, Supaksorn; Stoyanov, Drozdstoy; Sirivichayakul, Sunee; Carvalho, André F; Geffard, Michel; Maes, Michael

    2018-05-23

    Deficit schizophrenia, as defined by the Schedule for Deficit Syndrome, may represent a distinct diagnostic class defined by neurocognitive impairments coupled with changes in IgA/IgM responses to tryptophan catabolites (TRYCATs). Adequate classifications should be based on supervised and unsupervised learning rather than on consensus criteria. This study used machine learning as means to provide a more accurate classification of patients with stable phase schizophrenia. We found that using negative symptoms as discriminatory variables, schizophrenia patients may be divided into two distinct classes modelled by (A) impairments in IgA/IgM responses to noxious and generally more protective tryptophan catabolites, (B) impairments in episodic and semantic memory, paired associative learning and false memory creation, and (C) psychotic, excitation, hostility, mannerism, negative, and affective symptoms. The first cluster shows increased negative, psychotic, excitation, hostility, mannerism, depression and anxiety symptoms, and more neuroimmune and cognitive disorders and is therefore called "major neurocognitive psychosis" (MNP). The second cluster, called "simple neurocognitive psychosis" (SNP) is discriminated from normal controls by the same features although the impairments are less well developed than in MNP. The latter is additionally externally validated by lowered quality of life, body mass (reflecting a leptosome body type), and education (reflecting lower cognitive reserve). Previous distinctions including "type 1" (positive)/"type 2" (negative) and DSM-IV-TR (eg, paranoid) schizophrenia could not be validated using machine learning techniques. Previous names of the illness, including schizophrenia, are not very adequate because they do not describe the features of the illness, namely, interrelated neuroimmune, cognitive, and clinical features. Stable-phase schizophrenia consists of 2 relevant qualitatively distinct categories or nosological entities with SNP

  7. Content-Based High-Resolution Remote Sensing Image Retrieval via Unsupervised Feature Learning and Collaborative Affinity Metric Fusion

    Directory of Open Access Journals (Sweden)

    Yansheng Li

    2016-08-01

    Full Text Available With the urgent demand for automatic management of large numbers of high-resolution remote sensing images, content-based high-resolution remote sensing image retrieval (CB-HRRS-IR has attracted much research interest. Accordingly, this paper proposes a novel high-resolution remote sensing image retrieval approach via multiple feature representation and collaborative affinity metric fusion (IRMFRCAMF. In IRMFRCAMF, we design four unsupervised convolutional neural networks with different layers to generate four types of unsupervised features from the fine level to the coarse level. In addition to these four types of unsupervised features, we also implement four traditional feature descriptors, including local binary pattern (LBP, gray level co-occurrence (GLCM, maximal response 8 (MR8, and scale-invariant feature transform (SIFT. In order to fully incorporate the complementary information among multiple features of one image and the mutual information across auxiliary images in the image dataset, this paper advocates collaborative affinity metric fusion to measure the similarity between images. The performance evaluation of high-resolution remote sensing image retrieval is implemented on two public datasets, the UC Merced (UCM dataset and the Wuhan University (WH dataset. Large numbers of experiments show that our proposed IRMFRCAMF can significantly outperform the state-of-the-art approaches.

  8. Scikit-learn: Machine Learning in Python

    OpenAIRE

    Pedregosa, Fabian; Varoquaux, Gaël; Gramfort, Alexandre; Michel, Vincent; Thirion, Bertrand; Grisel, Olivier; Blondel, Mathieu; Prettenhofer, Peter; Weiss, Ron; Dubourg, Vincent; Vanderplas, Jake; Passos, Alexandre; Cournapeau, David; Brucher, Matthieu; Perrot, Matthieu

    2011-01-01

    International audience; Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing machine learning to non-specialists using a general-purpose high-level language. Emphasis is put on ease of use, performance, documentation, and API consistency. It has minimal dependencies and is distributed under the simplified BSD license, encouraging its use in both academic ...

  9. Scikit-learn: Machine Learning in Python

    OpenAIRE

    Pedregosa, Fabian; Varoquaux, Gaël; Gramfort, Alexandre; Michel, Vincent; Thirion, Bertrand; Grisel, Olivier; Blondel, Mathieu; Louppe, Gilles; Prettenhofer, Peter; Weiss, Ron; Dubourg, Vincent; Vanderplas, Jake; Passos, Alexandre; Cournapeau, David; Brucher, Matthieu

    2012-01-01

    Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing machine learning to non-specialists using a general-purpose high-level language. Emphasis is put on ease of use, performance, documentation, and API consistency. It has minimal dependencies and is distributed under the simplified BSD license, encouraging its use in both academic and commercial settings....

  10. Facebook Blocket with Unsupervised Learning

    OpenAIRE

    Amin, Khizer; Minhas, Mehmood ul haq

    2014-01-01

    The Internet has become a valuable channel for both business-to- consumer and business-to-business e-commerce. It has changed the way for many companies to manage the business. Every day, more and more companies are making their presence on Internet. Web sites are launched for online shopping as web shops or on-line stores are a popular means of goods distribution. The number of items sold through the internet has sprung up significantly in the past few years. Moreover, it has become a choice...

  11. Unsupervised Feature Subset Selection

    DEFF Research Database (Denmark)

    Søndberg-Madsen, Nicolaj; Thomsen, C.; Pena, Jose

    2003-01-01

    This paper studies filter and hybrid filter-wrapper feature subset selection for unsupervised learning (data clustering). We constrain the search for the best feature subset by scoring the dependence of every feature on the rest of the features, conjecturing that these scores discriminate some ir...... irrelevant features. We report experimental results on artificial and real data for unsupervised learning of naive Bayes models. Both the filter and hybrid approaches perform satisfactorily....

  12. Varieties of perceptual learning.

    Science.gov (United States)

    Mackintosh, N J

    2009-05-01

    Although most studies of perceptual learning in human participants have concentrated on the changes in perception assumed to be occurring, studies of nonhuman animals necessarily measure discrimination learning and generalization and remain agnostic on the question of whether changes in behavior reflect changes in perception. On the other hand, animal studies do make it easier to draw a distinction between supervised and unsupervised learning. Differential reinforcement will surely teach animals to attend to some features of a stimulus array rather than to others. But it is an open question as to whether such changes in attention underlie the enhanced discrimination seen after unreinforced exposure to such an array. I argue that most instances of unsupervised perceptual learning observed in animals (and at least some in human animals) are better explained by appeal to well-established principles and phenomena of associative learning theory: excitatory and inhibitory associations between stimulus elements, latent inhibition, and habituation.

  13. Learning How to Learn

    DEFF Research Database (Denmark)

    Lauridsen, Karen M.; Lauridsen, Ole

    Ole Lauridsen, Aarhus School of Business and Social Sciences, Aarhus University, Denmark Karen M. Lauridsen, Aarhus School of Business and Social Sciences, Aarhus University, Denmark Learning Styles in Higher Education – Learning How to Learn Applying learning styles (LS) in higher education...... by Constructivist learning theory and current basic knowledge of how the brain learns. The LS concept will thus be placed in a broader learning theoretical context as a strong learning and teaching tool. Participants will be offered the opportunity to have their own LS preferences established before...... teaching leads to positive results and enhanced student learning. However, learning styles should not only be considered a didactic matter for the teacher, but also a tool for the individual students to improve their learning capabilities – not least in contexts where information is not necessarily...

  14. Learning Outlier Ensembles

    DEFF Research Database (Denmark)

    Micenková, Barbora; McWilliams, Brian; Assent, Ira

    into the existing unsupervised algorithms. In this paper, we show how to use powerful machine learning approaches to combine labeled examples together with arbitrary unsupervised outlier scoring algorithms. We aim to get the best out of the two worlds—supervised and unsupervised. Our approach is also a viable......Years of research in unsupervised outlier detection have produced numerous algorithms to score data according to their exceptionality. wever, the nature of outliers heavily depends on the application context and different algorithms are sensitive to outliers of different nature. This makes it very...... difficult to assess suitability of a particular algorithm without a priori knowledge. On the other hand, in many applications, some examples of outliers exist or can be obtain edin addition to the vast amount of unlabeled data. Unfortunately, this extra knowledge cannot be simply incorporated...

  15. Learning to Learn.

    Science.gov (United States)

    Weiss, Helen; Weiss, Martin

    1988-01-01

    The article reviews theories of learning (e.g., stimulus-response, trial and error, operant conditioning, cognitive), considers the role of motivation, and summarizes nine research-supported rules of effective learning. Suggestions are applied to teaching learning strategies to learning-disabled students. (DB)

  16. Manifold Regularized Reinforcement Learning.

    Science.gov (United States)

    Li, Hongliang; Liu, Derong; Wang, Ding

    2018-04-01

    This paper introduces a novel manifold regularized reinforcement learning scheme for continuous Markov decision processes. Smooth feature representations for value function approximation can be automatically learned using the unsupervised manifold regularization method. The learned features are data-driven, and can be adapted to the geometry of the state space. Furthermore, the scheme provides a direct basis representation extension for novel samples during policy learning and control. The performance of the proposed scheme is evaluated on two benchmark control tasks, i.e., the inverted pendulum and the energy storage problem. Simulation results illustrate the concepts of the proposed scheme and show that it can obtain excellent performance.

  17. Machine Learning for Neuroimaging with Scikit-Learn

    Directory of Open Access Journals (Sweden)

    Alexandre eAbraham

    2014-02-01

    Full Text Available Statistical machine learning methods are increasingly used for neuroimaging data analysis. Their main virtue is their ability to model high-dimensional datasets, e.g. multivariate analysis of activation images or resting-state time series. Supervised learning is typically used in decoding or encoding settings to relate brain images to behavioral or clinical observations, while unsupervised learning can uncover hidden structures in sets of images (e.g. resting state functional MRI or find sub-populations in large cohorts. By considering different functional neuroimaging applications, we illustrate how scikit-learn, a Python machine learning library, can be used to perform some key analysis steps. Scikit-learn contains a very large set of statistical learning algorithms, both supervised and unsupervised, and its application to neuroimaging data provides a versatile tool to study the brain.

  18. Machine learning for neuroimaging with scikit-learn.

    Science.gov (United States)

    Abraham, Alexandre; Pedregosa, Fabian; Eickenberg, Michael; Gervais, Philippe; Mueller, Andreas; Kossaifi, Jean; Gramfort, Alexandre; Thirion, Bertrand; Varoquaux, Gaël

    2014-01-01

    Statistical machine learning methods are increasingly used for neuroimaging data analysis. Their main virtue is their ability to model high-dimensional datasets, e.g., multivariate analysis of activation images or resting-state time series. Supervised learning is typically used in decoding or encoding settings to relate brain images to behavioral or clinical observations, while unsupervised learning can uncover hidden structures in sets of images (e.g., resting state functional MRI) or find sub-populations in large cohorts. By considering different functional neuroimaging applications, we illustrate how scikit-learn, a Python machine learning library, can be used to perform some key analysis steps. Scikit-learn contains a very large set of statistical learning algorithms, both supervised and unsupervised, and its application to neuroimaging data provides a versatile tool to study the brain.

  19. Learning Styles.

    Science.gov (United States)

    Missouri Univ., Columbia. Coll. of Education.

    Information is provided regarding major learning styles and other factors important to student learning. Several typically asked questions are presented regarding different learning styles (visual, auditory, tactile and kinesthetic, and multisensory learning), associated considerations, determining individuals' learning styles, and appropriate…

  20. Introduction to machine learning.

    Science.gov (United States)

    Baştanlar, Yalin; Ozuysal, Mustafa

    2014-01-01

    The machine learning field, which can be briefly defined as enabling computers make successful predictions using past experiences, has exhibited an impressive development recently with the help of the rapid increase in the storage capacity and processing power of computers. Together with many other disciplines, machine learning methods have been widely employed in bioinformatics. The difficulties and cost of biological analyses have led to the development of sophisticated machine learning approaches for this application area. In this chapter, we first review the fundamental concepts of machine learning such as feature assessment, unsupervised versus supervised learning and types of classification. Then, we point out the main issues of designing machine learning experiments and their performance evaluation. Finally, we introduce some supervised learning methods.

  1. Learning Networks, Networked Learning

    NARCIS (Netherlands)

    Sloep, Peter; Berlanga, Adriana

    2010-01-01

    Sloep, P. B., & Berlanga, A. J. (2011). Learning Networks, Networked Learning [Redes de Aprendizaje, Aprendizaje en Red]. Comunicar, XIX(37), 55-63. Retrieved from http://dx.doi.org/10.3916/C37-2011-02-05

  2. Online adaptation of a c-VEP Brain-computer Interface(BCI) based on error-related potentials and unsupervised learning.

    Science.gov (United States)

    Spüler, Martin; Rosenstiel, Wolfgang; Bogdan, Martin

    2012-01-01

    The goal of a Brain-Computer Interface (BCI) is to control a computer by pure brain activity. Recently, BCIs based on code-modulated visual evoked potentials (c-VEPs) have shown great potential to establish high-performance communication. In this paper we present a c-VEP BCI that uses online adaptation of the classifier to reduce calibration time and increase performance. We compare two different approaches for online adaptation of the system: an unsupervised method and a method that uses the detection of error-related potentials. Both approaches were tested in an online study, in which an average accuracy of 96% was achieved with adaptation based on error-related potentials. This accuracy corresponds to an average information transfer rate of 144 bit/min, which is the highest bitrate reported so far for a non-invasive BCI. In a free-spelling mode, the subjects were able to write with an average of 21.3 error-free letters per minute, which shows the feasibility of the BCI system in a normal-use scenario. In addition we show that a calibration of the BCI system solely based on the detection of error-related potentials is possible, without knowing the true class labels.

  3. Learning Problems

    Science.gov (United States)

    ... Staying Safe Videos for Educators Search English Español Learning Problems KidsHealth / For Kids / Learning Problems What's in ... for how to make it better. What Are Learning Disabilities? Learning disabilities aren't contagious, but they ...

  4. SU-F-R-08: Can Normalization of Brain MRI Texture Features Reduce Scanner-Dependent Effects in Unsupervised Machine Learning?

    Energy Technology Data Exchange (ETDEWEB)

    Ogden, K; O’Dwyer, R [SUNY Upstate Medical University, Syracuse, NY (United States); Bradford, T [Syracuse University, Syracuse, NY (United States); Cussen, L [Rochester Institute of Technology, Rochester, NY (United States)

    2016-06-15

    Purpose: To reduce differences in features calculated from MRI brain scans acquired at different field strengths with or without Gadolinium contrast. Methods: Brain scans were processed for 111 epilepsy patients to extract hippocampus and thalamus features. Scans were acquired on 1.5 T scanners with Gadolinium contrast (group A), 1.5T scanners without Gd (group B), and 3.0 T scanners without Gd (group C). A total of 72 features were extracted. Features were extracted from original scans and from scans where the image pixel values were rescaled to the mean of the hippocampi and thalami values. For each data set, cluster analysis was performed on the raw feature set and for feature sets with normalization (conversion to Z scores). Two methods of normalization were used: The first was over all values of a given feature, and the second by normalizing within the patient group membership. The clustering software was configured to produce 3 clusters. Group fractions in each cluster were calculated. Results: For features calculated from both the non-rescaled and rescaled data, cluster membership was identical for both the non-normalized and normalized data sets. Cluster 1 was comprised entirely of Group A data, Cluster 2 contained data from all three groups, and Cluster 3 contained data from only groups 1 and 2. For the categorically normalized data sets there was a more uniform distribution of group data in the three Clusters. A less pronounced effect was seen in the rescaled image data features. Conclusion: Image Rescaling and feature renormalization can have a significant effect on the results of clustering analysis. These effects are also likely to influence the results of supervised machine learning algorithms. It may be possible to partly remove the influence of scanner field strength and the presence of Gadolinium based contrast in feature extraction for radiomics applications.

  5. SU-F-R-08: Can Normalization of Brain MRI Texture Features Reduce Scanner-Dependent Effects in Unsupervised Machine Learning?

    International Nuclear Information System (INIS)

    Ogden, K; O’Dwyer, R; Bradford, T; Cussen, L

    2016-01-01

    Purpose: To reduce differences in features calculated from MRI brain scans acquired at different field strengths with or without Gadolinium contrast. Methods: Brain scans were processed for 111 epilepsy patients to extract hippocampus and thalamus features. Scans were acquired on 1.5 T scanners with Gadolinium contrast (group A), 1.5T scanners without Gd (group B), and 3.0 T scanners without Gd (group C). A total of 72 features were extracted. Features were extracted from original scans and from scans where the image pixel values were rescaled to the mean of the hippocampi and thalami values. For each data set, cluster analysis was performed on the raw feature set and for feature sets with normalization (conversion to Z scores). Two methods of normalization were used: The first was over all values of a given feature, and the second by normalizing within the patient group membership. The clustering software was configured to produce 3 clusters. Group fractions in each cluster were calculated. Results: For features calculated from both the non-rescaled and rescaled data, cluster membership was identical for both the non-normalized and normalized data sets. Cluster 1 was comprised entirely of Group A data, Cluster 2 contained data from all three groups, and Cluster 3 contained data from only groups 1 and 2. For the categorically normalized data sets there was a more uniform distribution of group data in the three Clusters. A less pronounced effect was seen in the rescaled image data features. Conclusion: Image Rescaling and feature renormalization can have a significant effect on the results of clustering analysis. These effects are also likely to influence the results of supervised machine learning algorithms. It may be possible to partly remove the influence of scanner field strength and the presence of Gadolinium based contrast in feature extraction for radiomics applications.

  6. Learning about Learning

    Science.gov (United States)

    Siegler, Robert S.

    2004-01-01

    The field of children's learning was thriving when the Merrill-Palmer Quarterly was launched; the field later went into eclipse and now is in the midst of a resurgence. This commentary examines reasons for these trends, and describes the emerging field of children's learning. In particular, the new field is seen as differing from the old in its…

  7. Learning to Learn Differently

    Science.gov (United States)

    Olsen, Trude Høgvold; Glad, Tone; Filstad, Cathrine

    2018-01-01

    Purpose: This paper aims to investigate whether the formal and informal learning patterns of community health-care nurses changed in the wake of a reform that altered their work by introducing new patient groups, and to explore whether conditions in the new workplaces facilitated or impeded shifts in learning patterns. Design/methodology/approach:…

  8. Distance Learning

    National Research Council Canada - National Science Library

    Braddock, Joseph

    1997-01-01

    A study reviewing the existing Army Distance Learning Plan (ADLP) and current Distance Learning practices, with a focus on the Army's training and educational challenges and the benefits of applying Distance Learning techniques...

  9. Blended learning

    DEFF Research Database (Denmark)

    Dau, Susanne

    2016-01-01

    Blended Learning has been implemented, evaluated and researched for the last decades within different educational areas and levels. Blended learning has been coupled with different epistemological understandings and learning theories, but the fundamental character and dimensions of learning...... in blended learning are still insufficient. Moreover, blended learning is a misleading concept described as learning, despite the fact that it fundamentally is an instructional and didactic approach (Oliver & Trigwell, 2005) addressing the learning environment (Inglis, Palipoana, Trenhom & Ward, 2011......) instead of the learning processes behind. Much of the existing research within the field seems to miss this perspective. The consequence is a lack of acknowledgement of the driven forces behind the context and the instructional design limiting the knowledge foundation of learning in blended learning. Thus...

  10. Unsupervised learning for robust bitcoin fraud detection

    CSIR Research Space (South Africa)

    Monamo, Patrick

    2016-08-01

    Full Text Available The rampant absorption of Bitcoin as a cryptographic currency, along with rising cybercrime activities, warrants utilization of anomaly detection to identify potential fraud. Anomaly detection plays a pivotal role in data mining since most outlying...

  11. Scalable Unsupervised Learning for Unmanned Exploration

    Data.gov (United States)

    National Aeronautics and Space Administration — Though we dream of the day when humans will first walk on Mars, these dreams remain in the distance. For now, we explore vicariously by sending robotic agents like...

  12. SUSTAIN: a network model of category learning.

    Science.gov (United States)

    Love, Bradley C; Medin, Douglas L; Gureckis, Todd M

    2004-04-01

    SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a model of how humans learn categories from examples. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g., it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly recruited clusters are available to explain future events and can themselves evolve into prototypes-attractors-rules. SUSTAIN's discovery of category substructure is affected not only by the structure of the world but by the nature of the learning task and the learner's goals. SUSTAIN successfully extends category learning models to studies of inference learning, unsupervised learning, category construction, and contexts in which identification learning is faster than classification learning.

  13. Phonological Concept Learning.

    Science.gov (United States)

    Moreton, Elliott; Pater, Joe; Pertsova, Katya

    2017-01-01

    Linguistic and non-linguistic pattern learning have been studied separately, but we argue for a comparative approach. Analogous inductive problems arise in phonological and visual pattern learning. Evidence from three experiments shows that human learners can solve them in analogous ways, and that human performance in both cases can be captured by the same models. We test GMECCS (Gradual Maximum Entropy with a Conjunctive Constraint Schema), an implementation of the Configural Cue Model (Gluck & Bower, ) in a Maximum Entropy phonotactic-learning framework (Goldwater & Johnson, ; Hayes & Wilson, ) with a single free parameter, against the alternative hypothesis that learners seek featurally simple algebraic rules ("rule-seeking"). We study the full typology of patterns introduced by Shepard, Hovland, and Jenkins () ("SHJ"), instantiated as both phonotactic patterns and visual analogs, using unsupervised training. Unlike SHJ, Experiments 1 and 2 found that both phonotactic and visual patterns that depended on fewer features could be more difficult than those that depended on more features, as predicted by GMECCS but not by rule-seeking. GMECCS also correctly predicted performance differences between stimulus subclasses within each pattern. A third experiment tried supervised training (which can facilitate rule-seeking in visual learning) to elicit simple rule-seeking phonotactic learning, but cue-based behavior persisted. We conclude that similar cue-based cognitive processes are available for phonological and visual concept learning, and hence that studying either kind of learning can lead to significant insights about the other. Copyright © 2015 Cognitive Science Society, Inc.

  14. TF.Learn: TensorFlow's High-level Module for Distributed Machine Learning

    OpenAIRE

    Tang, Yuan

    2016-01-01

    TF.Learn is a high-level Python module for distributed machine learning inside TensorFlow. It provides an easy-to-use Scikit-learn style interface to simplify the process of creating, configuring, training, evaluating, and experimenting a machine learning model. TF.Learn integrates a wide range of state-of-art machine learning algorithms built on top of TensorFlow's low level APIs for small to large-scale supervised and unsupervised problems. This module focuses on bringing machine learning t...

  15. Learn, how to learn

    Science.gov (United States)

    Narayanan, M.

    2002-12-01

    Ernest L. Boyer, in his 1990 book, "Scholarship Reconsidered: Priorities of the Professorate" cites some ground breaking studies and offers a new paradigm that identifies the need to recognize the growing conversation about teaching, scholarship and research in the Universities. The use of `ACORN' model suggested by Hawkins and Winter to conquer and mastering change, may offer some helpful hints for the novice professor, whose primary objective might be to teach students to `learn how to learn'. Action : It is possible to effectively change things only when a teaching professor actually tries out a new idea. Communication : Changes are successful only when the new ideas effectively communicated and implemented. Ownership : Support for change is extremely important and is critical. Only strong commitment for accepting changes demonstrates genuine leadership. Reflection : Feedback helps towards thoughtful evaluation of the changes implemented. Only reflection can provide a tool for continuous improvement. Nurture : Implemented changes deliver results only when nurtured and promoted with necessary support systems, documentation and infrastructures. Inspired by the ACORN model, the author experimented on implementing certain principles of `Total Quality Management' in the classroom. The author believes that observing the following twenty principles would indeed help the student learners how to learn, on their own towards achieving the goal of `Lifelong Learning'. The author uses an acronym : QUOTES : Quality Underscored On Teaching Excellence Strategy, to describe his methods for improving classroom teacher-learner participation. 1. Break down all barriers. 2. Create consistency of purpose with a plan. 3. Adopt the new philosophy of quality. 4. Establish high Standards. 5. Establish Targets / Goals. 6. Reduce dependence on Lectures. 7. Employ Modern Methods. 8. Control the Process. 9. Organize to reach goals. 10. Prevention vs. Correction. 11. Periodic Improvements. 12

  16. Intentional Learning Vs Incidental Learning

    OpenAIRE

    Shahbaz Ahmed

    2017-01-01

    This study is conducted to demonstrate the knowledge of intentional learning and incidental learning. Hypothesis of this experiment is intentional learning is better than incidental learning, participants were demonstrated and were asked to learn the 10 non sense syllables in a specific sequence from the colored cards in the end they were asked to recall the background color of each card instead of non-sense syllables. Independent variables of the experiment are the colored cards containing n...

  17. Posthuman learning

    DEFF Research Database (Denmark)

    Hasse, Cathrine

    This book shall explore the concept of learning from the new perspective of the posthuman. The vast majority of cognitive, behavioral and part of the constructionist learning theories operate with an autonomous individual who learn in a world of separate objects. Technology is (if mentioned at all......) understood as separate from the individual learner and perceived as tools. Learning theory has in general not been acknowledging materiality in their theorizing about what learning is. A new posthuman learning theory is needed to keep up with the transformations of human learning resulting from new...... technological experiences. One definition of learning is that it is a relatively permanent change in behavior as the result of experience. During the first half of the twentieth century, two theoretical approaches dominated the domain of learning theory: the schools of thought commonly known as behaviorism...

  18. Learning e-Learning

    Directory of Open Access Journals (Sweden)

    Gabriel ZAMFIR

    2009-01-01

    Full Text Available What You Understand Is What Your Cognitive Integrates. Scientific research develops, as a native environment, knowledge. This environment consists of two interdependent divisions: theory and technology. First division occurs as a recursive research, while the second one becomes an application of the research activity. Over time, theories integrate methodologies and technology extends as infrastructure. The engine of this environment is learning, as the human activity of knowledge work. The threshold term of this model is the concepts map; it is based on Bloom’ taxonomy for the cognitive domain and highlights the notion of software scaffolding which is grounded in Vygotsky’s Social Development Theory with its major theme, Zone of Proximal Development. This article is designed as a conceptual paper, which analyzes specific structures of this type of educational research: the model reflects a foundation for a theory and finally, the theory evolves as groundwork for a system. The outcomes of this kind of approach are the examples, which are, theoretically, learning outcomes, and practically exist as educational objects, so-called e-learning.

  19. Blended Learning

    NARCIS (Netherlands)

    Van der Baaren, John

    2009-01-01

    Van der Baaren, J. (2009). Blended Learning. Presentation given at the Mini symposium 'Blended Learning the way to go?'. November, 5, 2009, The Hague, The Netherlands: Netherlands Defence Academy (NDLA).

  20. Interface learning

    DEFF Research Database (Denmark)

    Thorhauge, Sally

    2014-01-01

    "Interface learning - New goals for museum and upper secondary school collaboration" investigates and analyzes the learning that takes place when museums and upper secondary schools in Denmark work together in local partnerships to develop and carry out school-related, museum-based coursework...... for students. The research focuses on the learning that the students experience in the interface of the two learning environments: The formal learning environment of the upper secondary school and the informal learning environment of the museum. Focus is also on the learning that the teachers and museum...... professionals experience as a result of their collaboration. The dissertation demonstrates how a given partnership’s collaboration affects the students’ learning experiences when they are doing the coursework. The dissertation presents findings that museum-school partnerships can use in order to develop...

  1. Learning Disabilities

    Science.gov (United States)

    ... books. While his friends were meeting for pickup soccer games after school, he was back home in ... sometimes thought to contribute to learning disabilities. Poor nutrition early in life also may lead to learning ...

  2. Workplace learning

    DEFF Research Database (Denmark)

    Warring, Niels

    2005-01-01

    In November 2004 the Research Consortium on workplace learning under Learning Lab Denmark arranged the international conference “Workplace Learning – from the learner’s perspective”. The conference’s aim was to bring together researchers from different countries and institutions to explore...... and discuss recent developments in our understanding of workplace and work-related learning. The conference had nearly 100 participants with 59 papers presented, and among these five have been selected for presentation is this Special Issue....

  3. Boltzmann learning of parameters in cellular neural networks

    DEFF Research Database (Denmark)

    Hansen, Lars Kai

    1992-01-01

    The use of Bayesian methods to design cellular neural networks for signal processing tasks and the Boltzmann machine learning rule for parameter estimation is discussed. The learning rule can be used for models with hidden units, or for completely unsupervised learning. The latter is exemplified...

  4. Children's Learning

    Science.gov (United States)

    Siegler, Robert S.

    2005-01-01

    A new field of children's learning is emerging. This new field differs from the old in recognizing that children's learning includes active as well as passive mechanisms and qualitative as well as quantitative changes. Children's learning involves substantial variability of representations and strategies within individual children as well as…

  5. Blended Learning

    Science.gov (United States)

    Imbriale, Ryan

    2013-01-01

    Teachers always have been and always will be the essential element in the classroom. They can create magic inside four walls, but they have never been able to create learning environments outside the classroom like they can today, thanks to blended learning. Blended learning allows students and teachers to break free of the isolation of the…

  6. Transformative Learning

    Science.gov (United States)

    Wang, Victor C. X.; Cranton, Patricia

    2011-01-01

    The theory of transformative learning has been explored by different theorists and scholars. However, few scholars have made an attempt to make a comparison between transformative learning and Confucianism or between transformative learning and andragogy. The authors of this article address these comparisons to develop new and different insights…

  7. Blended Learning

    OpenAIRE

    Bauerová, Andrea

    2013-01-01

    This thesis is focused on a new approach of education called blended learning. The history and developement of Blended Learning is described in the first part. Then the methods and tools of Blended Learning are evaluated and compared to the traditional methods of education. At the final part an efficient developement of the educational programs is emphasized.

  8. Just Learning

    Science.gov (United States)

    Larsen-Freeman, Diane

    2017-01-01

    In this "First Person Singular" essay, the author describes her education, teaching experience, and interest in understanding the learning of language. Anyone reading this essay will not be surprised to learn that the author's questions about language learning and optimal teaching methods were only met with further questions, and no…

  9. Learning Networks for Lifelong Learning

    OpenAIRE

    Sloep, Peter

    2009-01-01

    Presentation in a seminar organized by Christopher Hoadley at Penn State University, October 2004.Contains general introduction into the Learning Network Programme and a demonstration of the Netlogo Simulation of a Learning Network.

  10. Learning organisations

    Directory of Open Access Journals (Sweden)

    Sabina Jelenc Krašovec

    2000-12-01

    Full Text Available A vast array of economical, social, political, cultural and other factors influences the transformed role of learning and education in the society, as well as the functioning of local community and its social and communication patterns. The influences which are manifested as global problems can only be successfully solved on the level of local community. Analogously with the society in general, there is a great need of transforming a local community into a learning, flexible and interconnected environment which takes into account different interests, wishes and needs regarding learning and being active. The fundamental answer to changes is the strategy of lifelong learning and education which requires reorganisation of all walks of life (work, free time, family, mass media, culture, sport, education and transforming of organisations into learning organisations. With learning society based on networks of knowledge individuals are turning into learning individuals, and organisations into learning organisations; people who learn take the responsibility of their progress, learning denotes partnership among learning people, teachers, parents, employers and local community, so that they work together to achieve better results.

  11. Learning Opportunities for Group Learning

    Science.gov (United States)

    Gil, Alfonso J.; Mataveli, Mara

    2017-01-01

    Purpose: This paper aims to analyse the impact of organizational learning culture and learning facilitators in group learning. Design/methodology/approach: This study was conducted using a survey method applied to a statistically representative sample of employees from Rioja wine companies in Spain. A model was tested using a structural equation…

  12. Mimetic Learning

    Directory of Open Access Journals (Sweden)

    Christoph Wulf

    2008-03-01

    Full Text Available Mimetic learning, learning by imitation, constitutes one of the most important forms of learning. Mimetic learning does not, however, just denote mere imitation or copying: Rather, it is a process by which the act of relating to other persons and worlds in a mimetic way leads to an en-hancement of one’s own world view, action, and behaviour. Mimetic learning is productive; it is related to the body, and it establishes a connection between the individual and the world as well as other persons; it creates practical knowledge, which is what makes it constitutive of social, artistic, and practical action. Mimetic learning is cultural learning, and as such it is crucial to teaching and education (Wulf, 2004; 2005.

  13. Deep learning

    CERN Document Server

    Goodfellow, Ian; Courville, Aaron

    2016-01-01

    Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language proces...

  14. Sparse alignment for robust tensor learning.

    Science.gov (United States)

    Lai, Zhihui; Wong, Wai Keung; Xu, Yong; Zhao, Cairong; Sun, Mingming

    2014-10-01

    Multilinear/tensor extensions of manifold learning based algorithms have been widely used in computer vision and pattern recognition. This paper first provides a systematic analysis of the multilinear extensions for the most popular methods by using alignment techniques, thereby obtaining a general tensor alignment framework. From this framework, it is easy to show that the manifold learning based tensor learning methods are intrinsically different from the alignment techniques. Based on the alignment framework, a robust tensor learning method called sparse tensor alignment (STA) is then proposed for unsupervised tensor feature extraction. Different from the existing tensor learning methods, L1- and L2-norms are introduced to enhance the robustness in the alignment step of the STA. The advantage of the proposed technique is that the difficulty in selecting the size of the local neighborhood can be avoided in the manifold learning based tensor feature extraction algorithms. Although STA is an unsupervised learning method, the sparsity encodes the discriminative information in the alignment step and provides the robustness of STA. Extensive experiments on the well-known image databases as well as action and hand gesture databases by encoding object images as tensors demonstrate that the proposed STA algorithm gives the most competitive performance when compared with the tensor-based unsupervised learning methods.

  15. Learning Disabilities and ADHD

    Science.gov (United States)

    ... of illnesses and disabilities Learning disabilities and ADHD Learning disabilities and ADHD Learning disabilities affect how you ... ADHD. Learning disabilities Attention deficit hyperactivity disorder (ADHD) Learning disabilities top Having a learning disability does not ...

  16. Informal learning.

    Science.gov (United States)

    Callanan, Maureen; Cervantes, Christi; Loomis, Molly

    2011-11-01

    We consider research and theory relevant to the notion of informal learning. Beginning with historical and definitional issues, we argue that learning happens not just in schools or in school-aged children. Many theorists have contrasted informal learning with formal learning. Moving beyond this dichotomy, and away from a focus on where learning occurs, we discuss five dimensions of informal learning that are drawn from the literature: (1) non-didactive, (2) highly socially collaborative, (3) embedded in meaningful activity, (4) initiated by learner's interest or choice, and (5) removed from external assessment. We consider these dimensions in the context of four sample domains: learning a first language, learning about the mind and emotions within families and communities, learning about science in family conversations and museum settings, and workplace learning. Finally, we conclude by considering convergences and divergences across the different literatures and suggesting areas for future research. WIREs Cogni Sci 2011 2 646-655 DOI: 10.1002/wcs.143 For further resources related to this article, please visit the WIREs website. Copyright © 2011 John Wiley & Sons, Ltd.

  17. Machine Learning

    CERN Multimedia

    CERN. Geneva

    2017-01-01

    Machine learning, which builds on ideas in computer science, statistics, and optimization, focuses on developing algorithms to identify patterns and regularities in data, and using these learned patterns to make predictions on new observations. Boosted by its industrial and commercial applications, the field of machine learning is quickly evolving and expanding. Recent advances have seen great success in the realms of computer vision, natural language processing, and broadly in data science. Many of these techniques have already been applied in particle physics, for instance for particle identification, detector monitoring, and the optimization of computer resources. Modern machine learning approaches, such as deep learning, are only just beginning to be applied to the analysis of High Energy Physics data to approach more and more complex problems. These classes will review the framework behind machine learning and discuss recent developments in the field.

  18. Doing learning

    DEFF Research Database (Denmark)

    Mathiasen, John Bang; Koch, Christian

    2014-01-01

    Purpose: To investigate how learning occurs in a systems development project, using a company developing wind turbine control systems in collaboration with customers as case. Design/methodology/approach: Dewey’s approach to learning is used, emphasising reciprocity between the individual...... learning processes and that the interchanges between materiality and systems developers block the learning processes due to a customer with imprecise demands and unclear system specifications. In the four cases discussed, learning does occur however. Research limitations/implications: A qualitative study...... focusing on individual systems developers gives limited insight into whether the learning processes found would occur in other systems development processes. Practical implications: Managers should ensure that constitutive means, such as specifications, are available, and that they are sufficiently...

  19. Metric learning

    CERN Document Server

    Bellet, Aurelien; Sebban, Marc

    2015-01-01

    Similarity between objects plays an important role in both human cognitive processes and artificial systems for recognition and categorization. How to appropriately measure such similarities for a given task is crucial to the performance of many machine learning, pattern recognition and data mining methods. This book is devoted to metric learning, a set of techniques to automatically learn similarity and distance functions from data that has attracted a lot of interest in machine learning and related fields in the past ten years. In this book, we provide a thorough review of the metric learnin

  20. On the asymptotic improvement of supervised learning by utilizing additional unlabeled samples - Normal mixture density case

    Science.gov (United States)

    Shahshahani, Behzad M.; Landgrebe, David A.

    1992-01-01

    The effect of additional unlabeled samples in improving the supervised learning process is studied in this paper. Three learning processes. supervised, unsupervised, and combined supervised-unsupervised, are compared by studying the asymptotic behavior of the estimates obtained under each process. Upper and lower bounds on the asymptotic covariance matrices are derived. It is shown that under a normal mixture density assumption for the probability density function of the feature space, the combined supervised-unsupervised learning is always superior to the supervised learning in achieving better estimates. Experimental results are provided to verify the theoretical concepts.

  1. Learning to learn in MOOCs

    DEFF Research Database (Denmark)

    Milligan, Sandra; Ringtved, Ulla Lunde

    This paper outlines one way of understanding what it is about learning in MOOCs that is so distinctive, and explores the implications for the design of MOOCs. It draws on an ongoing research study into the nature of learning in MOOCs at the University of Melbourne.......This paper outlines one way of understanding what it is about learning in MOOCs that is so distinctive, and explores the implications for the design of MOOCs. It draws on an ongoing research study into the nature of learning in MOOCs at the University of Melbourne....

  2. Ellipsoidal fuzzy learning for smart car platoons

    Science.gov (United States)

    Dickerson, Julie A.; Kosko, Bart

    1993-12-01

    A neural-fuzzy system combined supervised and unsupervised learning to find and tune the fuzzy-rules. An additive fuzzy system approximates a function by covering its graph with fuzzy rules. A fuzzy rule patch can take the form of an ellipsoid in the input-output space. Unsupervised competitive learning found the statistics of data clusters. The covariance matrix of each synaptic quantization vector defined on ellipsoid centered at the centroid of the data cluster. Tightly clustered data gave smaller ellipsoids or more certain rules. Sparse data gave larger ellipsoids or less certain rules. Supervised learning tuned the ellipsoids to improve the approximation. The supervised neural system used gradient descent to find the ellipsoidal fuzzy patches. It locally minimized the mean-squared error of the fuzzy approximation. Hybrid ellipsoidal learning estimated the control surface for a smart car controller.

  3. Deep learning in neural networks: an overview.

    Science.gov (United States)

    Schmidhuber, Jürgen

    2015-01-01

    In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.

  4. Learning Cultures

    DEFF Research Database (Denmark)

    Rasmussen, Lauge Baungaard

    1998-01-01

    the article present different concepts and modelsof learning. It discuss some strutural tendenciesof developing environmental management systemsand point out alternatives to increasing formalization of rules.......the article present different concepts and modelsof learning. It discuss some strutural tendenciesof developing environmental management systemsand point out alternatives to increasing formalization of rules....

  5. Blended learning

    DEFF Research Database (Denmark)

    Staugaard, Hans Jørgen

    2012-01-01

    Forsøg på at indkredse begrebet blended learning i forbindelse med forberedelsen af projekt FlexVid.......Forsøg på at indkredse begrebet blended learning i forbindelse med forberedelsen af projekt FlexVid....

  6. Reflective Learning

    African Journals Online (AJOL)

    dell

    The main intent of this study was to identify the impact of using learning log as a learning strategy on the academic performance of university students. Second year psychology students were included as subjects of this study. In the beginning of the study, the students were divided into two: experimental group (N = 60) and ...

  7. Perceptual learning.

    Science.gov (United States)

    Seitz, Aaron R

    2017-07-10

    Perceptual learning refers to how experience can change the way we perceive sights, sounds, smells, tastes, and touch. Examples abound: music training improves our ability to discern tones; experience with food and wines can refine our pallet (and unfortunately more quickly empty our wallet), and with years of training radiologists learn to save lives by discerning subtle details of images that escape the notice of untrained viewers. We often take perceptual learning for granted, but it has a profound impact on how we perceive the world. In this Primer, I will explain how perceptual learning is transformative in guiding our perceptual processes, how research into perceptual learning provides insight into fundamental mechanisms of learning and brain processes, and how knowledge of perceptual learning can be used to develop more effective training approaches for those requiring expert perceptual skills or those in need of perceptual rehabilitation (such as individuals with poor vision). I will make a case that perceptual learning is ubiquitous, scientifically interesting, and has substantial practical utility to us all. Copyright © 2017. Published by Elsevier Ltd.

  8. Pervasive Learning

    DEFF Research Database (Denmark)

    Helms, Niels Henrik; Larsen, Lasse Juel

    2009-01-01

    , it is not a specific place where you can access scarce information. Pervasive or ubiquitous communication opens up for taking the organizing and design of learning landscapes a step further. Furthermore it calls for theoretical developments, which can open up for a deeper understanding of the relationship between...... emerging contexts, design of contexts and learning....

  9. Flipped Learning

    DEFF Research Database (Denmark)

    Holmboe, Peter; Hachmann, Roland

    I FLIPPED LEARNING – FLIP MED VIDEO kan du læse om, hvordan du som underviser kommer godt i gang med at implementere video i undervisning, der har afsæt i tankerne omkring flipped learning. Bogen indeholder fire dele: I Del 1 fokuserer vi på det metarefleksive i at tænke video ind i undervisningen...

  10. Flipped Learning

    DEFF Research Database (Denmark)

    Hachmann, Roland; Holmboe, Peter

    arbejde med faglige problemstillinger gennem problembaserede og undersøgende didaktiske designs. Flipped Learning er dermed andet og mere end at distribuere digitale materialer til eleverne forud for undervisning. Flipped Learning er i lige så høj grad et syn på, hvordan undervisning med digitale medier...

  11. Situating learning

    DEFF Research Database (Denmark)

    Ribeiro, Gustavo; Georg, Susse; Finchman, Rob

    2004-01-01

    This paper looks at learning experiences in South Africa and Thailand by highlighting the role of context and culture in the learning process. The authors are based at Danish and South African higher education institutions and have contributed to DUCED's TFS programme in the positions of overall...

  12. Embodied Learning

    Science.gov (United States)

    Stolz, Steven A.

    2015-01-01

    This article argues that psychological discourse fails miserably to provide an account of learning that can explain how humans come to understand, particularly understanding that has been grasped meaningfully. Part of the problem with psychological approaches to learning is that they are disconnected from the integral role embodiment plays in how…

  13. Distance learning

    Directory of Open Access Journals (Sweden)

    Katarina Pucelj

    2006-12-01

    Full Text Available I would like to underline the role and importance of knowledge, which is acquired by individuals as a result of a learning process and experience. I have established that a form of learning, such as distance learning definitely contributes to a higher learning quality and leads to innovative, dynamic and knowledgebased society. Knowledge and skills enable individuals to cope with and manage changes, solve problems and also create new knowledge. Traditional learning practices face new circumstances, new and modern technologies appear, which enable quick and quality-oriented knowledge implementation. The centre of learning process at distance learning is to increase the quality of life of citizens, their competitiveness on the workforce market and ensure higher economic growth. Intellectual capital is the one, which represents the biggest capital of each society and knowledge is the key factor for succes of everybody, who are fully aware of this. Flexibility, openness and willingness of people to follow new IT solutions form suitable environment for developing and deciding to take up distance learning.

  14. Legitimate Learning.

    Science.gov (United States)

    Stevenson, John

    1997-01-01

    What is considered legitimate learning is culturally and contextually specific, depending on what values are involved. Different values are engaged depending on whether legitimate learning is considered transformation of the individual in relation to self, in relation to society, or in relation to the workplace. (SK)

  15. Machine Learning.

    Science.gov (United States)

    Kirrane, Diane E.

    1990-01-01

    As scientists seek to develop machines that can "learn," that is, solve problems by imitating the human brain, a gold mine of information on the processes of human learning is being discovered, expert systems are being improved, and human-machine interactions are being enhanced. (SK)

  16. IoT Security Techniques Based on Machine Learning

    OpenAIRE

    Xiao, Liang; Wan, Xiaoyue; Lu, Xiaozhen; Zhang, Yanyong; Wu, Di

    2018-01-01

    Internet of things (IoT) that integrate a variety of devices into networks to provide advanced and intelligent services have to protect user privacy and address attacks such as spoofing attacks, denial of service attacks, jamming and eavesdropping. In this article, we investigate the attack model for IoT systems, and review the IoT security solutions based on machine learning techniques including supervised learning, unsupervised learning and reinforcement learning. We focus on the machine le...

  17. Mere exposure alters category learning of novel objects

    Directory of Open Access Journals (Sweden)

    Jonathan R Folstein

    2010-08-01

    Full Text Available We investigated how mere exposure to complex objects with correlated or uncorrelated object features affects later category learning of new objects not seen during exposure. Correlations among pre-exposed object dimensions influenced later category learning. Unlike other published studies, the collection of pre-exposed objects provided no information regarding the categories to be learned, ruling out unsupervised or incidental category learning during pre-exposure. Instead, results are interpreted with respect to statistical learning mechanisms, providing one of the first demonstrations of how statistical learning can influence visual object learning.

  18. Mere exposure alters category learning of novel objects.

    Science.gov (United States)

    Folstein, Jonathan R; Gauthier, Isabel; Palmeri, Thomas J

    2010-01-01

    We investigated how mere exposure to complex objects with correlated or uncorrelated object features affects later category learning of new objects not seen during exposure. Correlations among pre-exposed object dimensions influenced later category learning. Unlike other published studies, the collection of pre-exposed objects provided no information regarding the categories to be learned, ruling out unsupervised or incidental category learning during pre-exposure. Instead, results are interpreted with respect to statistical learning mechanisms, providing one of the first demonstrations of how statistical learning can influence visual object learning.

  19. Blended Learning as Transformational Institutional Learning

    Science.gov (United States)

    VanDerLinden, Kim

    2014-01-01

    This chapter reviews institutional approaches to blended learning and the ways in which institutions support faculty in the intentional redesign of courses to produce optimal learning. The chapter positions blended learning as a strategic opportunity to engage in organizational learning.

  20. Learning LM Specificity for Ganglion Cells

    Science.gov (United States)

    Ahumada, Albert J.

    2015-01-01

    Unsupervised learning models have been proposed based on experience (Ahumada and Mulligan, 1990;Wachtler, Doi, Lee and Sejnowski, 2007) that allow the cortex to develop units with LM specific color opponent receptive fields like the blob cells reported by Hubel and Wiesel on the basis of visual experience. These models used ganglion cells with LM indiscriminate wiring as inputs to the learning mechanism, which was presumed to occur at the cortical level.

  1. Personalized search result diversification via structured learning

    NARCIS (Netherlands)

    Liang, S.; Ren, Z.; de Rijke, M.

    2014-01-01

    This paper is concerned with the problem of personalized diversification of search results, with the goal of enhancing the performance of both plain diversification and plain personalization algorithms. In previous work, the problem has mainly been tackled by means of unsupervised learning. To

  2. Prototype-based models in machine learning

    NARCIS (Netherlands)

    Biehl, Michael; Hammer, Barbara; Villmann, Thomas

    2016-01-01

    An overview is given of prototype-based models in machine learning. In this framework, observations, i.e., data, are stored in terms of typical representatives. Together with a suitable measure of similarity, the systems can be employed in the context of unsupervised and supervised analysis of

  3. "Learned Helplessness" or "Learned Incompetence"?

    Science.gov (United States)

    Sergent, Justine; Lambert, Wallace E.

    Studies in the past have shown that reinforcements independent of the subjects actions may induce a feeling of helplessness. Most experiments on learned helplessness have led researchers to believe that uncontrollability (non-contingency of feedback upon response) was the determining feature of learned helplessness, although in most studies…

  4. Teacher learning as workplace learning

    NARCIS (Netherlands)

    Imants, J.; Van Veen, K.

    2010-01-01

    Against the background of increasing attention in teacher professional development programs for situating teacher learning in the workplace, an overview is given of what is known in general and in educational workplace learning literature on the characteristics and conditions of the workplace.

  5. Learning, Learning Organisations and the Global Enterprise

    Science.gov (United States)

    Manikutty, Sankaran

    2009-01-01

    The steadily increasing degree of globalisation of enterprises implies development of many skills, among which the skills to learn are among the most important. Learning takes place at the individual level, but collective learning and organisational learning are also important. Learning styles of individuals are different and learning styles are…

  6. Can machine learning explain human learning?

    NARCIS (Netherlands)

    Vahdat, M.; Oneto, L.; Anguita, D.; Funk, M.; Rauterberg, G.W.M.

    2016-01-01

    Learning Analytics (LA) has a major interest in exploring and understanding the learning process of humans and, for this purpose, benefits from both Cognitive Science, which studies how humans learn, and Machine Learning, which studies how algorithms learn from data. Usually, Machine Learning is

  7. Human semi-supervised learning.

    Science.gov (United States)

    Gibson, Bryan R; Rogers, Timothy T; Zhu, Xiaojin

    2013-01-01

    Most empirical work in human categorization has studied learning in either fully supervised or fully unsupervised scenarios. Most real-world learning scenarios, however, are semi-supervised: Learners receive a great deal of unlabeled information from the world, coupled with occasional experiences in which items are directly labeled by a knowledgeable source. A large body of work in machine learning has investigated how learning can exploit both labeled and unlabeled data provided to a learner. Using equivalences between models found in human categorization and machine learning research, we explain how these semi-supervised techniques can be applied to human learning. A series of experiments are described which show that semi-supervised learning models prove useful for explaining human behavior when exposed to both labeled and unlabeled data. We then discuss some machine learning models that do not have familiar human categorization counterparts. Finally, we discuss some challenges yet to be addressed in the use of semi-supervised models for modeling human categorization. Copyright © 2013 Cognitive Science Society, Inc.

  8. Evaluation of learning materials

    DEFF Research Database (Denmark)

    Bundsgaard, Jeppe; Hansen, Thomas Illum

    2011-01-01

    This paper presents a holistic framework for evaluating learning materials and designs for learning. A holistic evaluation comprises investigations of the potential learning potential, the actualized learning potential, and the actual learning. Each aspect is explained and exemplified through...

  9. Learning Spaces

    CERN Document Server

    Falmagne, Jean-Claude

    2011-01-01

    Learning spaces offer a rigorous mathematical foundation for practical systems of educational technology. Learning spaces generalize partially ordered sets and are special cases of knowledge spaces. The various structures are investigated from the standpoints of combinatorial properties and stochastic processes. Leaning spaces have become the essential structures to be used in assessing students' competence of various topics. A practical example is offered by ALEKS, a Web-based, artificially intelligent assessment and learning system in mathematics and other scholarly fields. At the heart of A

  10. Unsupervised Language Acquisition

    Science.gov (United States)

    de Marcken, Carl

    1996-11-01

    This thesis presents a computational theory of unsupervised language acquisition, precisely defining procedures for learning language from ordinary spoken or written utterances, with no explicit help from a teacher. The theory is based heavily on concepts borrowed from machine learning and statistical estimation. In particular, learning takes place by fitting a stochastic, generative model of language to the evidence. Much of the thesis is devoted to explaining conditions that must hold for this general learning strategy to arrive at linguistically desirable grammars. The thesis introduces a variety of technical innovations, among them a common representation for evidence and grammars, and a learning strategy that separates the ``content'' of linguistic parameters from their representation. Algorithms based on it suffer from few of the search problems that have plagued other computational approaches to language acquisition. The theory has been tested on problems of learning vocabularies and grammars from unsegmented text and continuous speech, and mappings between sound and representations of meaning. It performs extremely well on various objective criteria, acquiring knowledge that causes it to assign almost exactly the same structure to utterances as humans do. This work has application to data compression, language modeling, speech recognition, machine translation, information retrieval, and other tasks that rely on either structural or stochastic descriptions of language.

  11. Supportive Learning: Linear Learning and Collaborative Learning

    Science.gov (United States)

    Lee, Bih Ni; Abdullah, Sopiah; Kiu, Su Na

    2016-01-01

    This is a conceptual paper which is trying to look at the educational technology is not limited to high technology. However, electronic educational technology, also known as e-learning, has become an important part of today's society, which consists of a wide variety of approaches to digitization, components and methods of delivery. In the…

  12. Learning to learn: self-managed learning

    Directory of Open Access Journals (Sweden)

    Jesús Miranda Izquierdo

    2006-09-01

    Full Text Available Thi is article analyzes the potentialities and weaknesses that non directive Pedagogy presents, an example of the so called self managed pedagogy, whose postulates are good to analyze for the contributions that this position can make to the search of new ways of learning.

  13. On-line Learning of Prototypes and Principal Components

    NARCIS (Netherlands)

    Biehl, M.; Freking, A.; Hölzer, M.; Reents, G.; Schlösser, E.; Saad, David

    1998-01-01

    We review our recent investigation of on-line unsupervised learning from high-dimensional structured data. First, on-line competitive learning is studied as a method for the identification of prototype vectors from overlapping clusters of examples. Specifically, we analyse the dynamics of the

  14. Scaling up machine learning: parallel and distributed approaches

    National Research Council Canada - National Science Library

    Bekkerman, Ron; Bilenko, Mikhail; Langford, John

    2012-01-01

    ... presented in the book cover a range of parallelization platforms from FPGAs and GPUs to multi-core systems and commodity clusters; concurrent programming frameworks that include CUDA, MPI, MapReduce, and DryadLINQ; and various learning settings: supervised, unsupervised, semi-supervised, and online learning. Extensive coverage of parallelizat...

  15. Machine Learning

    Energy Technology Data Exchange (ETDEWEB)

    Chikkagoudar, Satish; Chatterjee, Samrat; Thomas, Dennis G.; Carroll, Thomas E.; Muller, George

    2017-04-21

    The absence of a robust and unified theory of cyber dynamics presents challenges and opportunities for using machine learning based data-driven approaches to further the understanding of the behavior of such complex systems. Analysts can also use machine learning approaches to gain operational insights. In order to be operationally beneficial, cybersecurity machine learning based models need to have the ability to: (1) represent a real-world system, (2) infer system properties, and (3) learn and adapt based on expert knowledge and observations. Probabilistic models and Probabilistic graphical models provide these necessary properties and are further explored in this chapter. Bayesian Networks and Hidden Markov Models are introduced as an example of a widely used data driven classification/modeling strategy.

  16. Learning Leadership

    DEFF Research Database (Denmark)

    Hertel, Frederik; Fast, Alf Michael

    2018-01-01

    Is leadership a result of inheritance or is it something one learns during formal learning in e.g. business schools? This is the essential question addressed in this article. The article is based on a case study involving a new leader in charge of a group of profession practitioners. The leader...... promotes his leadership as a profession comparable to the professions of practitioners. This promotion implies that leadership is something one can and probably must learn during formal learning. The practitioners on the other hand reject this comprehension of leadership and long for a fellow practitioner...... to lead the organization. While asked they are unable to describe how, where and when they think a practitioner develops leadership skills necessary for leading fellows. In the following we will start analysing the case in order to comprehend and discuss both the professional leaders and the practitioners...

  17. Group learning

    DEFF Research Database (Denmark)

    Pimentel, Ricardo; Noguira, Eloy Eros da Silva; Elkjær, Bente

    The article presents a study that aims at the apprehension of the group learning in a top management team composed by teachers in a Brazilian Waldorf school whose management is collective. After deciding to extend the school, they had problems recruiting teachers who were already trained based...... on the Steiner´s ideas, which created practical problems for conducting management activities. The research seeks to understand how that group of teachers collectively manage the school, facing the lack of resources, a significant heterogeneity in the relationships, and the conflicts and contradictions......, and they are interrelated to the group learning as the construction, maintenance and reconstruction of the intelligibility of practices. From this perspective, it can be said that learning is a practice and not an exceptional phenomenon. Building, maintaining and rebuilding the intelligibility is the group learning...

  18. Learning Disabilities

    Science.gov (United States)

    ... NICHD) See all related organizations Publications Problemas de aprendizaje Order NINDS Publications Patient Organizations CHADD - Children and ... NICHD) See all related organizations Publications Problemas de aprendizaje Order NINDS Publications Definition Learning disabilities are disorders ...

  19. Reflective Learning

    African Journals Online (AJOL)

    dell

    The experimental group students used learning log on a weekly basis while the control group did not. ... The term “memory” in psychology usually denotes an interest in the retention ... activities that contribute to information being remembered.

  20. Metric Learning for Hyperspectral Image Segmentation

    Science.gov (United States)

    Bue, Brian D.; Thompson, David R.; Gilmore, Martha S.; Castano, Rebecca

    2011-01-01

    We present a metric learning approach to improve the performance of unsupervised hyperspectral image segmentation. Unsupervised spatial segmentation can assist both user visualization and automatic recognition of surface features. Analysts can use spatially-continuous segments to decrease noise levels and/or localize feature boundaries. However, existing segmentation methods use tasks-agnostic measures of similarity. Here we learn task-specific similarity measures from training data, improving segment fidelity to classes of interest. Multiclass Linear Discriminate Analysis produces a linear transform that optimally separates a labeled set of training classes. The defines a distance metric that generalized to a new scenes, enabling graph-based segmentation that emphasizes key spectral features. We describe tests based on data from the Compact Reconnaissance Imaging Spectrometer (CRISM) in which learned metrics improve segment homogeneity with respect to mineralogical classes.

  1. Learning phacoemulsification. Results of different teaching methods.

    Directory of Open Access Journals (Sweden)

    Hennig Albrecht

    2004-01-01

    Full Text Available We report the learning curves of three eye surgeons converting from sutureless extracapsular cataract extraction to phacoemulsification using different teaching methods. Posterior capsule rupture (PCR as a per-operative complication and visual outcome of the first 100 operations were analysed. The PCR rate was 4% and 15% in supervised and unsupervised surgery respectively. Likewise, an uncorrected visual acuity of > or = 6/18 on the first postoperative day was seen in 62 (62% of patients and in 22 (22% in supervised and unsupervised surgery respectively.

  2. Interorganizational learning systems

    DEFF Research Database (Denmark)

    Hjalager, Anne-Mette

    1999-01-01

    The occurrence of organizational and interorganizational learning processes is not only the result of management endeavors. Industry structures and market related issues have substantial spill-over effects. The article reviews literature, and it establishes a learning model in which elements from...... organizational environments are included into a systematic conceptual framework. The model allows four types of learning to be identified: P-learning (professional/craft systems learning), T-learning (technology embedded learning), D-learning (dualistic learning systems, where part of the labor force is exclude...... from learning), and S-learning (learning in social networks or clans). The situation related to service industries illustrates the typology....

  3. Learning curves for mutual information maximization

    International Nuclear Information System (INIS)

    Urbanczik, R.

    2003-01-01

    An unsupervised learning procedure based on maximizing the mutual information between the outputs of two networks receiving different but statistically dependent inputs is analyzed [S. Becker and G. Hinton, Nature (London) 355, 161 (1992)]. For a generic data model, I show that in the large sample limit the structure in the data is recognized by mutual information maximization. For a more restricted model, where the networks are similar to perceptrons, I calculate the learning curves for zero-temperature Gibbs learning. These show that convergence can be rather slow, and a way of regularizing the procedure is considered

  4. Lifelong Learning

    DEFF Research Database (Denmark)

    Krogh, Lone; Jensen, Annie Aarup

    2010-01-01

    Master education for adults has become a strategy for Lifelong Learning among many well-educated people in Denmark. This type of master education is part of the ‘parallel education system' in Denmark. As one of the first Danish universities who offered this type of Master education, Aalborg...... the intended as well as the unintended effects (personal and professional) of the master education. The data have been gathered among graduates from a specific master education, Master in Learning Processes, and the paper will draw on results from a quantitative survey based on a questionnaire answered by 120...

  5. Learning SPARQL

    CERN Document Server

    DuCharme, Bob

    2011-01-01

    Get hands-on experience with SPARQL, the RDF query language that's become a key component of the semantic web. With this concise book, you will learn how to use the latest version of this W3C standard to retrieve and manipulate the increasing amount of public and private data available via SPARQL endpoints. Several open source and commercial tools already support SPARQL, and this introduction gets you started right away. Begin with how to write and run simple SPARQL 1.1 queries, then dive into the language's powerful features and capabilities for manipulating the data you retrieve. Learn wha

  6. Deep Learning in Open Source Learning Streams

    DEFF Research Database (Denmark)

    Kjærgaard, Thomas

    2016-01-01

    This chapter presents research on deep learning in a digital learning environment and raises the question if digital instructional designs can catalyze deeper learning than traditional classroom teaching. As a theoretical point of departure the notion of ‘situated learning’ is utilized...... and contrasted to the notion of functionalistic learning in a digital context. The mechanism that enables deep learning in this context is ‘The Open Source Learning Stream’. ‘The Open Source Learning Stream’ is the notion of sharing ‘learning instances’ in a digital space (discussion board, Facebook group......, unistructural, multistructural or relational learning. The research concludes that ‘The Open Source Learning Stream’ can catalyze deep learning and that there are four types of ‘Open Source Learning streams’; individual/ asynchronous, individual/synchronous, shared/asynchronous and shared...

  7. Mastering machine learning with scikit-learn

    CERN Document Server

    Hackeling, Gavin

    2014-01-01

    If you are a software developer who wants to learn how machine learning models work and how to apply them effectively, this book is for you. Familiarity with machine learning fundamentals and Python will be helpful, but is not essential.

  8. Transforming learning?

    Science.gov (United States)

    1999-09-01

    A new Learning and Skills Council for post-16 learning is the latest proposal from the UK Government in its attempt to ensure a highly skilled workforce for the next century. Other aims will be to reduce the variability in standards of the existing post-16 system, coordination and coherence between further education and training, and a reduction in the duplication and layers in contracting and funding. The proposals include: a national Learning and Skills Council, with 40-50 local Learning and Skills Councils to develop local plans; a strengthened strategic role for business in education and training, influencing a budget of #5bn a radical new youth programme entitled `Connexions', with dedicated personal advisors for young people; greater cooperation between sixth forms and colleges; and the establishment of an independent inspectorate covering all work-related learning and training, to include a new role for Ofsted in inspecting the provision for 16-19 year-olds in schools and colleges. It is hoped that this programme will build on the successes of the previous systems and that savings of at least #50m can be achieved through streamlining and the reduction in bureaucracy. The intentions are set out in a White Paper, Learning to Succeed, which is available from the Stationery Office and bookshops, as well as on the website www.dfee.gov.uk/post16. Published in addition to the White Paper was `School Sixth form funding: a consultation paper' (available from DfEE publications, Prolog, PO Box 5050, Sherwood Park, Annesley, Nottingham NG15 0DJ) and `Transition plan for the post-16 education and training and for local delivery of support for small firms' (available from Trevor Tucknutt, TECSOP Division, Level 3, Department for Education and Employment, Moorfoot, Sheffield S1 4PQ). The deadline for comments on both the sixth form consultation document and the White Paper is 15 October 1999. Almost simultaneously with the announcement of the above proposals came the

  9. Deepening Learning through Learning-by-Inventing

    OpenAIRE

    Apiola, Mikko; Tedre, Matti

    2013-01-01

    It has been shown that deep approaches to learning, intrinsic motivation, and self-regulated learning have strong positive effects on learning. How those pedagogical theories can be integrated in computing curricula is, however, still lacking empirically grounded analyses. This study integrated, in a robotics-based programming class, a method of learning-by-inventing, and studied its qualitative effects on students’ learning through 144 interviews. Five findings were related with learning the...

  10. Learning and Behavior

    Science.gov (United States)

    ... List About PPMD Events News Login By Area Learning & Behavior Attention, Listening & Learning Autism Spectrum Disorder (ASD) ... Care Guidelines ❯ By Area ❯ Learning & Behavior Share Print Learning & Behavior Facts to Remember People with Duchenne may ...

  11. Learning via Query Synthesis

    KAUST Repository

    Alabdulmohsin, Ibrahim

    2017-01-01

    Active learning is a subfield of machine learning that has been successfully used in many applications. One of the main branches of active learning is query synthe- sis, where the learning agent constructs artificial queries from scratch in order

  12. Managing Learning for Performance.

    Science.gov (United States)

    Kuchinke, K. Peter

    1995-01-01

    Presents findings of organizational learning literature that could substantiate claims of learning organization proponents. Examines four learning processes and their contribution to performance-based learning management: knowledge acquisition, information distribution, information interpretation, and organizational memory. (SK)

  13. Learning Object Repositories

    Science.gov (United States)

    Lehman, Rosemary

    2007-01-01

    This chapter looks at the development and nature of learning objects, meta-tagging standards and taxonomies, learning object repositories, learning object repository characteristics, and types of learning object repositories, with type examples. (Contains 1 table.)

  14. Blocking in Category Learning

    OpenAIRE

    Bott, Lewis; Hoffman, Aaron B.; Murphy, Gregory L.

    2007-01-01

    Many theories of category learning assume that learning is driven by a need to minimize classification error. When there is no classification error, therefore, learning of individual features should be negligible. We tested this hypothesis by conducting three category learning experiments adapted from an associative learning blocking paradigm. Contrary to an error-driven account of learning, participants learned a wide range of information when they learned about categories, and blocking effe...

  15. Adding Learning to Knowledge-Based Systems: Taking the "Artificial" Out of AI

    Science.gov (United States)

    Daniel L. Schmoldt

    1997-01-01

    Both, knowledge-based systems (KBS) development and maintenance require time-consuming analysis of domain knowledge. Where example cases exist, KBS can be built, and later updated, by incorporating learning capabilities into their architecture. This applies to both supervised and unsupervised learning scenarios. In this paper, the important issues for learning systems-...

  16. Learned Helplessness

    Science.gov (United States)

    Hooker, Carol E.

    1976-01-01

    Learned helplessness--the belief that a person's actions have no influence on the outcome of an event--is similar in many respects to the crisis state and depression. The author shows how this impaired social and psychological functioning occurs and identifies techniques that the social worker can use to prevent it. (Author)

  17. Learning Disabilities.

    Science.gov (United States)

    Neuwirth, Sharyn

    This booklet uses hypothetical case examples to illustrate the definition, causal theories, and specific types of learning disabilities (LD). The cognitive and language performance of students with LD is compared to standard developmental milestones, and common approaches to the identification and education of children with LD are outlined.…

  18. Learning Together

    Science.gov (United States)

    Kaufman, Sherry

    2014-01-01

    In spring 2012, Sherry Kaufman, a consultant at Francis W. Parker School in Chicago, was asked to support kindergarten teachers in deepening their practice of constructivism and exploring the Reggio Emilia approach to early childhood education. Central to such an approach is the belief that all learning is socially constructed through interaction…

  19. Learning Mongoid

    CERN Document Server

    Rege, Gautam

    2013-01-01

    A step-by-step tutorial with focused examples that will help you build scalable, high performance Rails web applications with Mongoid.If you are an application developer who wants to learn how to use Mongoid in a Rails application, this book will be great for you. You are expected to be familiar with MongoDB and Ruby.

  20. Learning Lichens

    Science.gov (United States)

    Thorne, Sarah

    2017-01-01

    The lichen is an ideal subject for student study because it is omnipresent in school yards, easily collected and observed year-round, a pioneer of evolution on land, and a bioindicator of air pollution. After doing fieldwork on this unusual composite organism as an apprentice with a team of lichenologists, Sarah Thorne developed Learning Lichens.…

  1. Learning Ionic

    CERN Document Server

    Ravulavaru, Arvind

    2015-01-01

    This book is intended for those who want to learn how to build hybrid mobile applications using Ionic. It is also ideal for people who want to explore theming for Ionic apps. Prior knowledge of AngularJS is essential to complete this book successfully.

  2. Supervised Learning

    Science.gov (United States)

    Rokach, Lior; Maimon, Oded

    This chapter summarizes the fundamental aspects of supervised methods. The chapter provides an overview of concepts from various interrelated fields used in subsequent chapters. It presents basic definitions and arguments from the supervised machine learning literature and considers various issues, such as performance evaluation techniques and challenges for data mining tasks.

  3. Learning Analytics

    Directory of Open Access Journals (Sweden)

    Erik Duval

    2012-06-01

    Full Text Available This paper provides a brief introduction to the domain of ‘learning analytics’. We first explain the background and idea behind the concept. Then we give a brief overview of current research issues. We briefly list some more controversial issues before concluding.

  4. Learning Ansible

    CERN Document Server

    Mohaan, Madhurranjan

    2014-01-01

    If you want to learn how to use Ansible to automate an infrastructure, either from scratch or to augment your current tooling with Ansible, then this is the book for you. It has plenty of practical examples to help you get to grips with Ansible.

  5. Learning Physics

    International Nuclear Information System (INIS)

    Cohen, E.

    2005-01-01

    Full Text:The issue of Teaching physics vs Learning physics in our institutions of higher learning will be discussed. Physics is taught mainly by frontal lectures an old (and proven) method. The great advancements of the Information Age are introduced by exposing the students to vast amounts of computerized information and directing them to numerical problem solving by interacting with the computer. These modern methods have several drawbacks: 1. Students get the impression of easy material acquisition while in fact it becomes superficial. 2. There is little integration of topics that are taught in different courses. 3. Insufficient interest is built among undergraduate students to pursue studies that involve deeper thinking and independent research (namely, studies towards a doctoral degree). Learning physics is a formative process in the education of physicists, natural scientists and engineers. It must be based on discussions and exchange of ideas among the students, since understanding the studied material means being able to explain it to a colleague. Some universities in the US initiated programs of learning physics by creating an environment in which small groups of students are engaged in discussing material, jointly solving problems and jointly conducting simulated experiments. This is done under the supervision of a mentor. Suggestions for implementing this method in Israel will be discussed

  6. Influences of Formal Learning, Personal Learning Orientation, and Supportive Learning Environment on Informal Learning

    Science.gov (United States)

    Choi, Woojae; Jacobs, Ronald L.

    2011-01-01

    While workplace learning includes formal and informal learning, the relationship between the two has been overlooked, because they have been viewed as separate entities. This study investigated the effects of formal learning, personal learning orientation, and supportive learning environment on informal learning among 203 middle managers in Korean…

  7. From learning objects to learning activities

    DEFF Research Database (Denmark)

    Dalsgaard, Christian

    2005-01-01

    This paper discusses and questions the current metadata standards for learning objects from a pedagogical point of view. From a social constructivist approach, the paper discusses how learning objects can support problem based, self-governed learning activities. In order to support this approach......, it is argued that it is necessary to focus on learning activities rather than on learning objects. Further, it is argued that descriptions of learning objectives and learning activities should be separated from learning objects. The paper presents a new conception of learning objects which supports problem...... based, self-governed activities. Further, a new way of thinking pedagogy into learning objects is introduced. It is argued that a lack of pedagogical thinking in learning objects is not solved through pedagogical metadata. Instead, the paper suggests the concept of references as an alternative...

  8. How we learn

    DEFF Research Database (Denmark)

    Illeris, Knud

    How We Learn, deals with the fundamental issues of the processes of learning, critically assessing different types of learning and obstacles to learning. It also considers a broad range of other important questions in relation to learning such as: modern research into learning and brain functions......, self-perception, motivation and competence development, teaching, intelligence and learning style, learning in relation to gender and life age. The book provides a comprehensive introduction to both traditional learning theory and the newest international research into learning processes, while...... at the same time being an innovative contribution to a new and more holistic understanding of learning including discussion on school-based learning, net-based learning, workplace learning and educational politics. How We Learn examines all the key factors that help to create a holistic understanding of what...

  9. Using Learning Games to Meet Learning Objectives

    DEFF Research Database (Denmark)

    Henriksen, Thomas Duus

    2013-01-01

    This paper addresses the question on how learning games can be used to meet with the different levels in Bloom’s and the SOLO taxonomy, which are commonly used for evaluating the learning outcome of educational activities. The paper discusses the quality of game-based learning outcomes based on a...... on a case study of the learning game 6Styles....

  10. Still to Learn from Vicarious Learning

    Science.gov (United States)

    Mayes, J. T.

    2015-01-01

    The term "vicarious learning" was introduced in the 1960s by Bandura, who demonstrated how learning can occur through observing the behaviour of others. Such social learning is effective without the need for the observer to experience feedback directly. More than twenty years later a series of studies on vicarious learning was undertaken…

  11. Learning Effectiveness of a Strategic Learning Course

    Science.gov (United States)

    Burchard, Melinda S.; Swerdzewski, Peter

    2009-01-01

    The effectiveness of a postsecondary strategic learning course for improving metacognitive awareness and regulation was evaluated through systematic program assessment. The course emphasized students' awareness of personal learning through the study of learning theory and through practical application of specific learning strategies. Students…

  12. Social Media and Seamless Learning: Lessons Learned

    Science.gov (United States)

    Panke, Stefanie; Kohls, Christian; Gaiser, Birgit

    2017-01-01

    The paper discusses best practice approaches and metrics for evaluation that support seamless learning with social media. We draw upon the theoretical frameworks of social learning theory, transfer learning (bricolage), and educational design patterns to elaborate upon different ideas for ways in which social media can support seamless learning.…

  13. Deep Learning

    DEFF Research Database (Denmark)

    Jensen, Morten Bornø; Bahnsen, Chris Holmberg; Nasrollahi, Kamal

    2018-01-01

    I løbet af de sidste 10 år er kunstige neurale netværk gået fra at være en støvet, udstødt tekno-logi til at spille en hovedrolle i udviklingen af kunstig intelligens. Dette fænomen kaldes deep learning og er inspireret af hjernens opbygning.......I løbet af de sidste 10 år er kunstige neurale netværk gået fra at være en støvet, udstødt tekno-logi til at spille en hovedrolle i udviklingen af kunstig intelligens. Dette fænomen kaldes deep learning og er inspireret af hjernens opbygning....

  14. Learning Java

    CERN Document Server

    Niemeyer, Patrick

    2005-01-01

    Version 5.0 of the Java 2 Standard Edition SDK is the most important upgrade since Java first appeared a decade ago. With Java 5.0, you'll not only find substantial changes in the platform, but to the language itself-something that developers of Java took five years to complete. The main goal of Java 5.0 is to make it easier for you to develop safe, powerful code, but none of these improvements makes Java any easier to learn, even if you've programmed with Java for years. And that means our bestselling hands-on tutorial takes on even greater significance. Learning Java is the most widely sou

  15. Learning Raspbian

    CERN Document Server

    Harrington, William

    2015-01-01

    This book is intended for developers who have worked with the Raspberry Pi and who want to learn how to make the most of the Raspbian operating system and their Raspberry Pi. Whether you are a beginner to the Raspberry Pi or a seasoned expert, this book will make you familiar with the Raspbian operating system and teach you how to get your Raspberry Pi up and running.

  16. Linear time relational prototype based learning.

    Science.gov (United States)

    Gisbrecht, Andrej; Mokbel, Bassam; Schleif, Frank-Michael; Zhu, Xibin; Hammer, Barbara

    2012-10-01

    Prototype based learning offers an intuitive interface to inspect large quantities of electronic data in supervised or unsupervised settings. Recently, many techniques have been extended to data described by general dissimilarities rather than Euclidean vectors, so-called relational data settings. Unlike the Euclidean counterparts, the techniques have quadratic time complexity due to the underlying quadratic dissimilarity matrix. Thus, they are infeasible already for medium sized data sets. The contribution of this article is twofold: On the one hand we propose a novel supervised prototype based classification technique for dissimilarity data based on popular learning vector quantization (LVQ), on the other hand we transfer a linear time approximation technique, the Nyström approximation, to this algorithm and an unsupervised counterpart, the relational generative topographic mapping (GTM). This way, linear time and space methods result. We evaluate the techniques on three examples from the biomedical domain.

  17. Unsupervised classification of variable stars

    Science.gov (United States)

    Valenzuela, Lucas; Pichara, Karim

    2018-03-01

    During the past 10 years, a considerable amount of effort has been made to develop algorithms for automatic classification of variable stars. That has been primarily achieved by applying machine learning methods to photometric data sets where objects are represented as light curves. Classifiers require training sets to learn the underlying patterns that allow the separation among classes. Unfortunately, building training sets is an expensive process that demands a lot of human efforts. Every time data come from new surveys; the only available training instances are the ones that have a cross-match with previously labelled objects, consequently generating insufficient training sets compared with the large amounts of unlabelled sources. In this work, we present an algorithm that performs unsupervised classification of variable stars, relying only on the similarity among light curves. We tackle the unsupervised classification problem by proposing an untraditional approach. Instead of trying to match classes of stars with clusters found by a clustering algorithm, we propose a query-based method where astronomers can find groups of variable stars ranked by similarity. We also develop a fast similarity function specific for light curves, based on a novel data structure that allows scaling the search over the entire data set of unlabelled objects. Experiments show that our unsupervised model achieves high accuracy in the classification of different types of variable stars and that the proposed algorithm scales up to massive amounts of light curves.

  18. Guided discovery learning in geometry learning

    Science.gov (United States)

    Khasanah, V. N.; Usodo, B.; Subanti, S.

    2018-03-01

    Geometry is a part of the mathematics that must be learned in school. The purpose of this research was to determine the effect of Guided Discovery Learning (GDL) toward geometry learning achievement. This research had conducted at junior high school in Sukoharjo on academic years 2016/2017. Data collection was done based on student’s work test and documentation. Hypothesis testing used two ways analysis of variance (ANOVA) with unequal cells. The results of this research that GDL gave positive effect towards mathematics learning achievement. GDL gave better mathematics learning achievement than direct learning. There was no difference of mathematics learning achievement between male and female. There was no an interaction between sex differences and learning models toward student’s mathematics learning achievement. GDL can be used to improve students’ mathematics learning achievement in geometry.

  19. Learning to Learn Together with CSCL Tools

    Science.gov (United States)

    Schwarz, Baruch B.; de Groot, Reuma; Mavrikis, Manolis; Dragon, Toby

    2015-01-01

    In this paper, we identify "Learning to Learn Together" (L2L2) as a new and important educational goal. Our view of L2L2 is a substantial extension of "Learning to Learn" (L2L): L2L2 consists of learning to collaborate to successfully face L2L challenges. It is inseparable from L2L, as it emerges when individuals face problems…

  20. Classification of behavior using unsupervised temporal neural networks

    International Nuclear Information System (INIS)

    Adair, K.L.

    1998-03-01

    Adding recurrent connections to unsupervised neural networks used for clustering creates a temporal neural network which clusters a sequence of inputs as they appear over time. The model presented combines the Jordan architecture with the unsupervised learning technique Adaptive Resonance Theory, Fuzzy ART. The combination yields a neural network capable of quickly clustering sequential pattern sequences as the sequences are generated. The applicability of the architecture is illustrated through a facility monitoring problem

  1. Technology, Learning, and Individual Differences

    Science.gov (United States)

    Bear, Anne A. Ghost

    2012-01-01

    The learning needs for adults that result from the constant increase in technology are rooted in the adult learning concepts of (a) andragogy, (b) self-directed learning, (c) learning-how-to-learn, (d) real-life learning, and (e) learning strategies. This study described the learning strategies that adults use in learning to engage in an online…

  2. Human Machine Learning Symbiosis

    Science.gov (United States)

    Walsh, Kenneth R.; Hoque, Md Tamjidul; Williams, Kim H.

    2017-01-01

    Human Machine Learning Symbiosis is a cooperative system where both the human learner and the machine learner learn from each other to create an effective and efficient learning environment adapted to the needs of the human learner. Such a system can be used in online learning modules so that the modules adapt to each learner's learning state both…

  3. Machine-Learning Research

    OpenAIRE

    Dietterich, Thomas G.

    1997-01-01

    Machine-learning research has been making great progress in many directions. This article summarizes four of these directions and discusses some current open problems. The four directions are (1) the improvement of classification accuracy by learning ensembles of classifiers, (2) methods for scaling up supervised learning algorithms, (3) reinforcement learning, and (4) the learning of complex stochastic models.

  4. Targeted Learning

    CERN Document Server

    van der Laan, Mark J

    2011-01-01

    The statistics profession is at a unique point in history. The need for valid statistical tools is greater than ever; data sets are massive, often measuring hundreds of thousands of measurements for a single subject. The field is ready to move towards clear objective benchmarks under which tools can be evaluated. Targeted learning allows (1) the full generalization and utilization of cross-validation as an estimator selection tool so that the subjective choices made by humans are now made by the machine, and (2) targeting the fitting of the probability distribution of the data toward the targe

  5. Learning Vaadin

    CERN Document Server

    Frankel, Nicolas

    2011-01-01

    This book begins with a tutorial on Vaadin 7, followed by a process of planning, analyzing, building, and deploying a fully functional RIA while covering troubleshooting details along the way, making it an invaluable resource for answers to all your Vaadin questions. If you are a Java developer with some experience in Java web development and want to enter the world of Rich Internet Applications this technology and book are ideal for you. Learning Vaadin will be perfect as your next step towards building eye-candy dynamic web applications on a Java-based platform.

  6. Learning Cypher

    CERN Document Server

    Panzarino, Onofrio

    2014-01-01

    An easy-to-follow guide full of tips and examples of real-world applications. In each chapter, a thorough example will show you the concepts in action, followed by a detailed explanation.This book is intended for those who want to learn how to create, query, and maintain a graph database, or who want to migrate to a graph database from SQL. It would be helpful to have some familiarity with Java and/or SQL, but no prior experience is required.

  7. Learning Perl

    CERN Document Server

    Schwartz, Randal; Phoenix, Tom

    2011-01-01

    If you're just getting started with Perl, this is the book you want-whether you're a programmer, system administrator, or web hacker. Nicknamed "the Llama" by two generations of users, this bestseller closely follows the popular introductory Perl course taught by the authors since 1991. This 6th edition covers recent changes to the language up to version 5.14. Perl is suitable for almost any task on almost any platform, from short fixes to complete web applications. Learning Perl teaches you the basics and shows you how to write programs up to 128 lines long-roughly the size of 90% of the Pe

  8. Learning scikit-learn machine learning in Python

    CERN Document Server

    Garreta, Raúl

    2013-01-01

    The book adopts a tutorial-based approach to introduce the user to Scikit-learn.If you are a programmer who wants to explore machine learning and data-based methods to build intelligent applications and enhance your programming skills, this the book for you. No previous experience with machine-learning algorithms is required.

  9. Prototype-based models in machine learning.

    Science.gov (United States)

    Biehl, Michael; Hammer, Barbara; Villmann, Thomas

    2016-01-01

    An overview is given of prototype-based models in machine learning. In this framework, observations, i.e., data, are stored in terms of typical representatives. Together with a suitable measure of similarity, the systems can be employed in the context of unsupervised and supervised analysis of potentially high-dimensional, complex datasets. We discuss basic schemes of competitive vector quantization as well as the so-called neural gas approach and Kohonen's topology-preserving self-organizing map. Supervised learning in prototype systems is exemplified in terms of learning vector quantization. Most frequently, the familiar Euclidean distance serves as a dissimilarity measure. We present extensions of the framework to nonstandard measures and give an introduction to the use of adaptive distances in relevance learning. © 2016 Wiley Periodicals, Inc.

  10. Machine learning applications in genetics and genomics.

    Science.gov (United States)

    Libbrecht, Maxwell W; Noble, William Stafford

    2015-06-01

    The field of machine learning, which aims to develop computer algorithms that improve with experience, holds promise to enable computers to assist humans in the analysis of large, complex data sets. Here, we provide an overview of machine learning applications for the analysis of genome sequencing data sets, including the annotation of sequence elements and epigenetic, proteomic or metabolomic data. We present considerations and recurrent challenges in the application of supervised, semi-supervised and unsupervised machine learning methods, as well as of generative and discriminative modelling approaches. We provide general guidelines to assist in the selection of these machine learning methods and their practical application for the analysis of genetic and genomic data sets.

  11. Technology Enhanced Learning

    NARCIS (Netherlands)

    Klemke, Roland; Specht, Marcus

    2013-01-01

    Klemke, R., & Specht, M. (2013, 26-27 September). Technology Enhanced Learning. Presentation at the fourth international conference on eLearning (eLearning 2013), Belgrade, Serbia. http://econference.metropolitan.ac.rs/

  12. Mobile Inquiry Based Learning

    NARCIS (Netherlands)

    Specht, Marcus

    2012-01-01

    Specht, M. (2012, 8 November). Mobile Inquiry Based Learning. Presentation given at the Workshop "Mobile inquiry-based learning" at the Mobile Learning Day 2012 at the Fernuniversität Hagen, Hagen, Germany.

  13. Machine learning in radiation oncology theory and applications

    CERN Document Server

    El Naqa, Issam; Murphy, Martin J

    2015-01-01

    ​This book provides a complete overview of the role of machine learning in radiation oncology and medical physics, covering basic theory, methods, and a variety of applications in medical physics and radiotherapy. An introductory section explains machine learning, reviews supervised and unsupervised learning methods, discusses performance evaluation, and summarizes potential applications in radiation oncology. Detailed individual sections are then devoted to the use of machine learning in quality assurance; computer-aided detection, including treatment planning and contouring; image-guided rad

  14. Learning with three factors: modulating Hebbian plasticity with errors.

    Science.gov (United States)

    Kuśmierz, Łukasz; Isomura, Takuya; Toyoizumi, Taro

    2017-10-01

    Synaptic plasticity is a central theme in neuroscience. A framework of three-factor learning rules provides a powerful abstraction, helping to navigate through the abundance of models of synaptic plasticity. It is well-known that the dopamine modulation of learning is related to reward, but theoretical models predict other functional roles of the modulatory third factor; it may encode errors for supervised learning, summary statistics of the population activity for unsupervised learning or attentional feedback. Specialized structures may be needed in order to generate and propagate third factors in the neural network. Copyright © 2017 The Authors. Published by Elsevier Ltd.. All rights reserved.

  15. Learning and Memory

    OpenAIRE

    1999-01-01

    Under various circumstances and in different species the outward expression of learning varies considerably, and this has led to the classification of different categories of learning. Just as there is no generally agreed on definition of learning, there is no one system of classification. Types of learning commonly recognized are: Habituation, sensitization, classical conditioning, operant conditioning, trial and error, taste aversion, latent learning, cultural learning, imprinting, insight ...

  16. Toward Learning Teams

    DEFF Research Database (Denmark)

    Hoda, Rashina; Babb, Jeff; Nørbjerg, Jacob

    2013-01-01

    to sacrifice learning-focused practices. Effective learning under pressure involves conscious efforts to implement original agile practices such as retrospectives and adapted strategies such as learning spikes. Teams, their management, and customers must all recognize the importance of creating learning teams......Today's software development challenges require learning teams that can continuously apply new engineering and management practices, new and complex technical skills, cross-functional skills, and experiential lessons learned. The pressure of delivering working software often forces software teams...

  17. Greedy Deep Dictionary Learning

    OpenAIRE

    Tariyal, Snigdha; Majumdar, Angshul; Singh, Richa; Vatsa, Mayank

    2016-01-01

    In this work we propose a new deep learning tool called deep dictionary learning. Multi-level dictionaries are learnt in a greedy fashion, one layer at a time. This requires solving a simple (shallow) dictionary learning problem, the solution to this is well known. We apply the proposed technique on some benchmark deep learning datasets. We compare our results with other deep learning tools like stacked autoencoder and deep belief network; and state of the art supervised dictionary learning t...

  18. Learning Networks for Professional Development & Lifelong Learning

    NARCIS (Netherlands)

    Sloep, Peter

    2009-01-01

    Sloep, P. B. (2009). Learning Networks for Professional Development & Lifelong Learning. Presentation at a NeLLL seminar with Etienne Wenger held at the Open Universiteit Nederland. September, 10, 2009, Heerlen, The Netherlands.

  19. Use of blended learning in workplace learning

    DEFF Research Database (Denmark)

    Georgsen, Marianne; Løvstad, Charlotte Vange

    2014-01-01

    -based teaching materials. This paper presents the experiences of this particular project, and goes on to discuss the following points: • The blended learning design – use of IT for teaching, learning and communication • Digital learning materials – principals of design and use • Work place learning and learning......In 2014, a new system has been put in place for the inspection and approval of social welfare institutions in Denmark. In as little as 10 weeks, 330 new employees in five regional centres participated in an introductory course, designed as work place learning with extensive use of e-learning and IT...... from work – the interplay between experiences of the learner and the curriculum of the program •The approach taken to customising the e-learning design to the needs and demands of a particular case....

  20. Learning Design Development for Blended Learning

    DEFF Research Database (Denmark)

    Hansen, Janne Saltoft

    Learning design development for blended learning We started implementing Blackboard at Aarhus University in 2013. At the Health Faculty Blackboard replaced AULA which was a LMS with functionality for file distribution and only a vague focus on learning tools. Most teachers therefore had...... no experiences with blended leaning and technology supported out-of-class activities. At the pedagogical unit at the Health faculty we wanted to follow the Blackboard implementation with pedagogical tools for learning design to evolve the pedagogical use of the system. We needed to make development of blended...... learning courses easier for the teachers and also ensure quality in the courses. This poster describes the process from development of the learning design to implementation of the learning design at the faculty: 1. How to place demands on a learning design-model and how to develop and use such a model. 2...

  1. Judgments of Learning in Collaborative Learning Environments

    NARCIS (Netherlands)

    Helsdingen, Anne

    2010-01-01

    Helsdingen, A. S. (2010, March). Judgments of Learning in Collaborative Learning Environments. Poster presented at the 1st International Air Transport and Operations Symposium (ATOS 2010), Delft, The Netherlands: Delft University of Technology.

  2. Learning design guided learning analytics in MOOCs

    NARCIS (Netherlands)

    Brouns, Francis; Firssova, Olga

    2016-01-01

    Poster presentation for our paper Brouns, F., & Firssova, O. (2016, October).The role of learning design and learning analytics in MOOCs. Paper presented at 9th EDEN Research Workshop, Oldenburg, Germany.

  3. Networked professional learning

    NARCIS (Netherlands)

    Sloep, Peter

    2013-01-01

    Sloep, P. B. (2013). Networked professional learning. In A. Littlejohn, & A. Margaryan (Eds.), Technology-enhanced Professional Learning: Processes, Practices and Tools (pp. 97–108). London: Routledge.

  4. Empirical Studies On Machine Learning Based Text Classification Algorithms

    OpenAIRE

    Shweta C. Dharmadhikari; Maya Ingle; Parag Kulkarni

    2011-01-01

    Automatic classification of text documents has become an important research issue now days. Properclassification of text documents requires information retrieval, machine learning and Natural languageprocessing (NLP) techniques. Our aim is to focus on important approaches to automatic textclassification based on machine learning techniques viz. supervised, unsupervised and semi supervised.In this paper we present a review of various text classification approaches under machine learningparadig...

  5. Learning and Generalisation in Neural Networks with Local Preprocessing

    OpenAIRE

    Kutsia, Merab

    2007-01-01

    We study learning and generalisation ability of a specific two-layer feed-forward neural network and compare its properties to that of a simple perceptron. The input patterns are mapped nonlinearly onto a hidden layer, much larger than the input layer, and this mapping is either fixed or may result from an unsupervised learning process. Such preprocessing of initially uncorrelated random patterns results in the correlated patterns in the hidden layer. The hidden-to-output mapping of the net...

  6. Information theoretic learning Renyi's entropy and Kernel perspectives

    CERN Document Server

    Principe, Jose C

    2010-01-01

    This book presents the first cohesive treatment of Information Theoretic Learning (ITL) algorithms to adapt linear or nonlinear learning machines both in supervised or unsupervised paradigms. ITL is a framework where the conventional concepts of second order statistics (covariance, L2 distances, correlation functions) are substituted by scalars and functions with information theoretic underpinnings, respectively entropy, mutual information and correntropy. ITL quantifies the stochastic structure of the data beyond second order statistics for improved performance without using full-blown Bayesi

  7. II - Multivariate Classification and Machine Learning in HEP

    CERN Multimedia

    CERN. Geneva

    2016-01-01

    A summary of the history of deep-learning is given and the difference to traditional artificial neural networks is discussed. Advanced methods like convoluted neural networks, recurrent neural networks and unsupervised training are introduced. Interesting examples from this emerging field outside HEP are presented. Possible applications in HEP are discussed.

  8. Resonant learning

    DEFF Research Database (Denmark)

    Lindvang, Charlotte

    2013-01-01

    -experience and personal therapy in training, first and foremost from the students’ perspective. The author focuses on presenting the qualitative part of her research which namely addresses the students’ experiences. Semi-structured qualitative interviews and qualitative music analyses were conducted, using a hermeneutic...... approach. The informants were nine music therapy students from Aalborg University, enrolled in the fifth year of their Master’s degree training programme. They were asked to bring a recording of an improvisation of their own choice to the interview. The qualitative data collection of text and music......The article presents a part of the authors PhD-study in music therapy about self-experiential training and the development of music therapeutic competencies. One of the purposes of the study was to explore and generate understanding and insight into the phenomena of learning through self...

  9. Blended Learning: An Innovative Approach

    Science.gov (United States)

    Lalima; Dangwal, Kiran Lata

    2017-01-01

    Blended learning is an innovative concept that embraces the advantages of both traditional teaching in the classroom and ICT supported learning including both offline learning and online learning. It has scope for collaborative learning; constructive learning and computer assisted learning (CAI). Blended learning needs rigorous efforts, right…

  10. Brain Research: Implications for Learning.

    Science.gov (United States)

    Soares, Louise M.; Soares, Anthony T.

    Brain research has illuminated several areas of the learning process: (1) learning as association; (2) learning as reinforcement; (3) learning as perception; (4) learning as imitation; (5) learning as organization; (6) learning as individual style; and (7) learning as brain activity. The classic conditioning model developed by Pavlov advanced…

  11. Blended Learning in Personalized Assistive Learning Environments

    Science.gov (United States)

    Marinagi, Catherine; Skourlas, Christos

    2013-01-01

    In this paper, the special needs/requirements of disabled students and cost-benefits for applying blended learning in Personalized Educational Learning Environments (PELE) in Higher Education are studied. The authors describe how blended learning can form an attractive and helpful framework for assisting Deaf and Hard-of-Hearing (D-HH) students to…

  12. LEARNING ABOUT LEARNING, A CONFERENCE REPORT.

    Science.gov (United States)

    BRUNER, JEROME

    TO EXPLORE THE NATURE OF THE LEARNING PROCESS, THREE IMPORTANT PROBLEM AREAS WERE STUDIED. STUDIES IN THE FIRST AREA, ATTITUDINAL AND AFFECTIVE SKILLS, ARE CONCERNED WITH INDUCING A CHILD TO LEARN AND SUSTAINING HIS ATTENTION. STUDIES IN THE SECOND AREA, COGNITIVE SKILLS, SOUGHT TO DISCOVER WHETHER GENERAL IDEAS AND SKILLS CAN BE LEARNED IN SUCH A…

  13. When Learning Analytics Meets E-Learning

    Science.gov (United States)

    Czerkawski, Betul C.

    2015-01-01

    While student data systems are nothing new and most educators have been dealing with student data for many years, learning analytics has emerged as a new concept to capture educational big data. Learning analytics is about better understanding of the learning and teaching process and interpreting student data to improve their success and learning…

  14. Learning Networks for Professional Development & Lifelong Learning

    NARCIS (Netherlands)

    Brouns, Francis; Sloep, Peter

    2009-01-01

    Brouns, F., & Sloep, P. B. (2009). Learning Networks for Professional Development & Lifelong Learning. Presentation of the Learning Network Programme for a Korean delegation of Chonnam National University and Dankook University (researchers dr. Jeeheon Ryu and dr. Minjeong Kim and a Group of PhD and

  15. Stimulating Deep Learning Using Active Learning Techniques

    Science.gov (United States)

    Yew, Tee Meng; Dawood, Fauziah K. P.; a/p S. Narayansany, Kannaki; a/p Palaniappa Manickam, M. Kamala; Jen, Leong Siok; Hoay, Kuan Chin

    2016-01-01

    When students and teachers behave in ways that reinforce learning as a spectator sport, the result can often be a classroom and overall learning environment that is mostly limited to transmission of information and rote learning rather than deep approaches towards meaningful construction and application of knowledge. A group of college instructors…

  16. Learning Analytics for Networked Learning Models

    Science.gov (United States)

    Joksimovic, Srecko; Hatala, Marek; Gaševic, Dragan

    2014-01-01

    Teaching and learning in networked settings has attracted significant attention recently. The central topic of networked learning research is human-human and human-information interactions occurring within a networked learning environment. The nature of these interactions is highly complex and usually requires a multi-dimensional approach to…

  17. Facilitating Learning Organizations. Making Learning Count.

    Science.gov (United States)

    Marsick, Victoria J.; Watkins, Karen E.

    This book offers advice to facilitators and change agents who wish to build systems-level learning to create knowledge that can be used to gain a competitive advantage. Chapter 1 describes forces driving companies to build, sustain, and effectively use systems-level learning and presents and links a working definition of the learning organization…

  18. Weakly supervised visual dictionary learning by harnessing image attributes.

    Science.gov (United States)

    Gao, Yue; Ji, Rongrong; Liu, Wei; Dai, Qionghai; Hua, Gang

    2014-12-01

    Bag-of-features (BoFs) representation has been extensively applied to deal with various computer vision applications. To extract discriminative and descriptive BoF, one important step is to learn a good dictionary to minimize the quantization loss between local features and codewords. While most existing visual dictionary learning approaches are engaged with unsupervised feature quantization, the latest trend has turned to supervised learning by harnessing the semantic labels of images or regions. However, such labels are typically too expensive to acquire, which restricts the scalability of supervised dictionary learning approaches. In this paper, we propose to leverage image attributes to weakly supervise the dictionary learning procedure without requiring any actual labels. As a key contribution, our approach establishes a generative hidden Markov random field (HMRF), which models the quantized codewords as the observed states and the image attributes as the hidden states, respectively. Dictionary learning is then performed by supervised grouping the observed states, where the supervised information is stemmed from the hidden states of the HMRF. In such a way, the proposed dictionary learning approach incorporates the image attributes to learn a semantic-preserving BoF representation without any genuine supervision. Experiments in large-scale image retrieval and classification tasks corroborate that our approach significantly outperforms the state-of-the-art unsupervised dictionary learning approaches.

  19. Online transfer learning with extreme learning machine

    Science.gov (United States)

    Yin, Haibo; Yang, Yun-an

    2017-05-01

    In this paper, we propose a new transfer learning algorithm for online training. The proposed algorithm, which is called Online Transfer Extreme Learning Machine (OTELM), is based on Online Sequential Extreme Learning Machine (OSELM) while it introduces Semi-Supervised Extreme Learning Machine (SSELM) to transfer knowledge from the source to the target domain. With the manifold regularization, SSELM picks out instances from the source domain that are less relevant to those in the target domain to initialize the online training, so as to improve the classification performance. Experimental results demonstrate that the proposed OTELM can effectively use instances in the source domain to enhance the learning performance.

  20. Professional learning versus interprofessional learning

    DEFF Research Database (Denmark)

    Nielsen, Cathrine Sand

    2014-01-01

    to improve quality in the Danish healthcare system (1). Cooperation between patients and professionals is challenged when patients are transferred between department, hospitals or sectors (2). Sharing and developing knowledge inter-professionally and in particular across sectors is inadequate (3......, which is necessary for development of the future undergraduate health professional education programmes. The PhD project intends to generate knowledge of: - the contributions of InterTværs to the quality of future health professional education programmes and to the future healthcare system....... The transition challenges in the healthcare system do not seem to only affect patients and knowledge, but also the students and learning. References: (1) Institute for Quality and Accreditation in Healthcare. 2012. The Danish Healthcare Quality Programme. Accreditation Standards for Hospitals (2) Siemsen IMD...

  1. When does social learning become cultural learning?

    Science.gov (United States)

    Heyes, Cecilia

    2017-03-01

    Developmental research on selective social learning, or 'social learning strategies', is currently a rich source of information about when children copy behaviour, and who they prefer to copy. It also has the potential to tell us when and how human social learning becomes cultural learning; i.e. mediated by psychological mechanisms that are specialized, genetically or culturally, to promote cultural inheritance. However, this review article argues that, to realize its potential, research on the development of selective social learning needs more clearly to distinguish functional from mechanistic explanation; to achieve integration with research on attention and learning in adult humans and 'dumb' animals; and to recognize that psychological mechanisms can be specialized, not only by genetic evolution, but also by associative learning and cultural evolution. © 2015 John Wiley & Sons Ltd.

  2. Records for learning

    DEFF Research Database (Denmark)

    Binder, Thomas

    2005-01-01

    The article present and discuss findings from a participatory development of new learning practices among intensive care nurses, with an emphasize on the role of place making in informal learning activities.......The article present and discuss findings from a participatory development of new learning practices among intensive care nurses, with an emphasize on the role of place making in informal learning activities....

  3. Mobile Learning Platform

    DEFF Research Database (Denmark)

    Annan, Nana Kofi; Ofori-Dwumfou, George; Falch, Morten

    2012-01-01

    on the first experiences gained by both teachers and students by asking the following questions: What are the perceptions of teachers on m-learning? What are the effects of m-learning on students? What does m-learning contribute to face-to-face teaching and learning? Questionnaires were administered...

  4. Students Engaged in Learning

    Science.gov (United States)

    Ismail, Emad A.; Groccia, James E.

    2018-01-01

    Engaging students in learning is a basic principle of effective undergraduate education. Outcomes of engaging students include meaningful learning experiences and enhanced skills in all learning domains. This chapter reviews the influence of engaging students in different forms of active learning on cognitive, psychomotor, and affective skill…

  5. Cultural Learning Redux

    Science.gov (United States)

    Tomasello, Michael

    2016-01-01

    M. Tomasello, A. Kruger, and H. Ratner (1993) proposed a theory of cultural learning comprising imitative learning, instructed learning, and collaborative learning. Empirical and theoretical advances in the past 20 years suggest modifications to the theory; for example, children do not just imitate but overimitate in order to identify and…

  6. Teaching for Deep Learning

    Science.gov (United States)

    Smith, Tracy Wilson; Colby, Susan A.

    2007-01-01

    The authors have been engaged in research focused on students' depth of learning as well as teachers' efforts to foster deep learning. Findings from a study examining the teaching practices and student learning outcomes of sixty-four teachers in seventeen different states (Smith et al. 2005) indicated that most of the learning in these classrooms…

  7. Culture and Organizational Learning

    NARCIS (Netherlands)

    Cook, N.; Yanow, D.

    2011-01-01

    Traditionally, theories of organizational learning have taken one of two approaches that share a common characterization of learning but differ in focus. One approach focuses on learning by individuals in organizational contexts; the other, on individual learning as a model for organizational

  8. Active Learning Methods

    Science.gov (United States)

    Zayapragassarazan, Z.; Kumar, Santosh

    2012-01-01

    Present generation students are primarily active learners with varied learning experiences and lecture courses may not suit all their learning needs. Effective learning involves providing students with a sense of progress and control over their own learning. This requires creating a situation where learners have a chance to try out or test their…

  9. Algorithms for Reinforcement Learning

    CERN Document Server

    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'

  10. Rethinking e-learning

    DEFF Research Database (Denmark)

    Bang, Jørgen; Dalsgaard, Christian

    2006-01-01

    “Technology alone does not deliver educational success. It only becomes valuable in education if learners and teachers can do something useful with it” (E-Learning: The Partnership Challenge, 2001, p. 24). This quotation could be used as a bon mot for this chapter. Our main goal is to rethink e-learning...... by shifting the focus of attention from learning resources (learning objects) to learning activities, which also implies a refocusing of the pedagogical discussion of the learning process.Firstly, we try to identify why e-learning has not been able to deliver the educational results as expected five years ago...

  11. Learning from Narrated Instruction Videos.

    Science.gov (United States)

    Alayrac, Jean-Baptiste; Bojanowski, Piotr; Agrawal, Nishant; Sivic, Josef; Laptev, Ivan; Lacoste-Julien, Simon

    2017-09-05

    Automatic assistants could guide a person or a robot in performing new tasks, such as changing a car tire or repotting a plant. Creating such assistants, however, is non-trivial and requires understanding of visual and verbal content of a video. Towards this goal, we here address the problem of automatically learning the main steps of a task from a set of narrated instruction videos. We develop a new unsupervised learning approach that takes advantage of the complementary nature of the input video and the associated narration. The method sequentially clusters textual and visual representations of a task, where the two clustering problems are linked by joint constraints to obtain a single coherent sequence of steps in both modalities. To evaluate our method, we collect and annotate a new challenging dataset of real-world instruction videos from the Internet. The dataset contains videos for five different tasks with complex interactions between people and objects, captured in a variety of indoor and outdoor settings. We experimentally demonstrate that the proposed method can automatically discover, learn and localize the main steps of a task input videos.

  12. Lessons Learned

    Directory of Open Access Journals (Sweden)

    Amanda Phelan BNS, MSc, PhD

    2015-03-01

    Full Text Available The public health nurses’ scope of practice explicitly includes child protection within their role, which places them in a prime position to identify child protection concerns. This role compliments that of other professions and voluntary agenices who work with children. Public health nurses are in a privileged position as they form a relationship with the child’s parent(s/guardian(s and are able to see the child in its own environment, which many professionals cannot. Child protection in Ireland, while influenced by other countries, has progressed through a distinct pathway that streamlined protocols and procedures. However, despite the above serious failures have occurred in the Irish system, and inquiries over the past 20 years persistently present similar contributing factors, namely, the lack of standardized and comprehensive service responses. Moreover, poor practice is compounded by the lack of recognition of the various interactional processes taking place within and between the different agencies of child protection, leading to psychological barriers in communication. This article will explore the lessons learned for public health nurses practice in safeguarding children in the Republic of Ireland.

  13. Learning tinnitus

    Science.gov (United States)

    van Hemmen, J. Leo

    Tinnitus, implying the perception of sound without the presence of any acoustical stimulus, is a chronic and serious problem for about 2% of the human population. In many cases, tinnitus is a pitch-like sensation associated with a hearing loss that confines the tinnitus frequency to an interval of the tonotopic axis. Even in patients with a normal audiogram the presence of tinnitus may be associated with damage of hair-cell function in this interval. It has been suggested that homeostatic regulation and, hence, increase of activity leads to the emergence of tinnitus. For patients with hearing loss, we present spike-timing-dependent Hebbian plasticity (STDP) in conjunction with homeostasis as a mechanism for ``learning'' tinnitus in a realistic neuronal network with tonotopically arranged synaptic excitation and inhibition. In so doing we use both dynamical scaling of the synaptic strengths and altering the resting potential of the cells. The corresponding simulations are robust to parameter changes. Understanding the mechanisms of tinnitus induction, such as here, may help improving therapy. Work done in collaboration with Julie Goulet and Michael Schneider. JLvH has been supported partially by BCCN - Munich.

  14. Learning after acquired brain injury. Learning the hard way

    NARCIS (Netherlands)

    Boosman, H.

    2015-01-01

    Background: When the brain has suffered damage, the learning process can be considerably disturbed. Brain damage can influence what is learned, but also how learning takes place. What patients can learn can be viewed in terms of ‘learning ability’ and how patients learn in terms of ‘learning style’.

  15. Interpretable Active Learning

    OpenAIRE

    Phillips, Richard L.; Chang, Kyu Hyun; Friedler, Sorelle A.

    2017-01-01

    Active learning has long been a topic of study in machine learning. However, as increasingly complex and opaque models have become standard practice, the process of active learning, too, has become more opaque. There has been little investigation into interpreting what specific trends and patterns an active learning strategy may be exploring. This work expands on the Local Interpretable Model-agnostic Explanations framework (LIME) to provide explanations for active learning recommendations. W...

  16. e-Learning Mathematics

    OpenAIRE

    Almanasreh, Hasan

    2017-01-01

    This study concerns the use of e-learning in the educational system shedding the light on its advantages and disadvantages, and analyzing its applicability either partially or totally. From mathematical perspectives, theories are developed to test the courses tendency to online transformation. This leads to a new trend of learning, the offline-online-offline learning (fnf-learning), it merges e-learning mode with the traditional orientation of education. The derivation of the new trend is bas...

  17. Learning Theories In Instructional Multimedia For English Learning

    OpenAIRE

    Farani, Rizki

    2016-01-01

    Learning theory is the concept of human learning. This concept is one of the important components in instructional for learning, especially English learning. English subject becomes one of important subjects for students but learning English needs specific strategy since it is not our vernacular. Considering human learning process in English learning is expected to increase students' motivation to understand English better. Nowadays, the application of learning theories in English learning ha...

  18. An unsupervised learning algorithm for fatigue crack detection in waveguides

    International Nuclear Information System (INIS)

    Rizzo, Piervincenzo; Cammarata, Marcello; Kent Harries; Dutta, Debaditya; Sohn, Hoon

    2009-01-01

    Ultrasonic guided waves (UGWs) are a useful tool in structural health monitoring (SHM) applications that can benefit from built-in transduction, moderately large inspection ranges, and high sensitivity to small flaws. This paper describes an SHM method based on UGWs and outlier analysis devoted to the detection and quantification of fatigue cracks in structural waveguides. The method combines the advantages of UGWs with the outcomes of the discrete wavelet transform (DWT) to extract defect-sensitive features aimed at performing a multivariate diagnosis of damage. In particular, the DWT is exploited to generate a set of relevant wavelet coefficients to construct a uni-dimensional or multi-dimensional damage index vector. The vector is fed to an outlier analysis to detect anomalous structural states. The general framework presented in this paper is applied to the detection of fatigue cracks in a steel beam. The probing hardware consists of a National Instruments PXI platform that controls the generation and detection of the ultrasonic signals by means of piezoelectric transducers made of lead zirconate titanate. The effectiveness of the proposed approach to diagnose the presence of defects as small as a few per cent of the waveguide cross-sectional area is demonstrated

  19. Detecting Housing Submarkets using Unsupervised Learning of Finite Mixture Models

    DEFF Research Database (Denmark)

    Ntantamis, Christos

    association between prices that can be attributed, among others, to unobserved neighborhood effects. In this paper, a model of spatial association for housing markets is introduced. Spatial association is treated in the context of spatial heterogeneity, which is explicitly modeled in both a global and a local....... The identified mixtures are considered as the different spatial housing submarkets. The main advantage of the approach is that submarkets are recovered by the housing prices data compared to submarkets imposed by administrative or geographical criteria. The Finite Mixture Model is estimated using the Figueiredo...

  20. Reinforcement Learning Based Artificial Immune Classifier

    Directory of Open Access Journals (Sweden)

    Mehmet Karakose

    2013-01-01

    Full Text Available One of the widely used methods for classification that is a decision-making process is artificial immune systems. Artificial immune systems based on natural immunity system can be successfully applied for classification, optimization, recognition, and learning in real-world problems. In this study, a reinforcement learning based artificial immune classifier is proposed as a new approach. This approach uses reinforcement learning to find better antibody with immune operators. The proposed new approach has many contributions according to other methods in the literature such as effectiveness, less memory cell, high accuracy, speed, and data adaptability. The performance of the proposed approach is demonstrated by simulation and experimental results using real data in Matlab and FPGA. Some benchmark data and remote image data are used for experimental results. The comparative results with supervised/unsupervised based artificial immune system, negative selection classifier, and resource limited artificial immune classifier are given to demonstrate the effectiveness of the proposed new method.

  1. Learning situation models in a smart home.

    Science.gov (United States)

    Brdiczka, Oliver; Crowley, James L; Reignier, Patrick

    2009-02-01

    This paper addresses the problem of learning situation models for providing context-aware services. Context for modeling human behavior in a smart environment is represented by a situation model describing environment, users, and their activities. A framework for acquiring and evolving different layers of a situation model in a smart environment is proposed. Different learning methods are presented as part of this framework: role detection per entity, unsupervised extraction of situations from multimodal data, supervised learning of situation representations, and evolution of a predefined situation model with feedback. The situation model serves as frame and support for the different methods, permitting to stay in an intuitive declarative framework. The proposed methods have been integrated into a whole system for smart home environment. The implementation is detailed, and two evaluations are conducted in the smart home environment. The obtained results validate the proposed approach.

  2. Attribute Learning for SAR Image Classification

    Directory of Open Access Journals (Sweden)

    Chu He

    2017-04-01

    Full Text Available This paper presents a classification approach based on attribute learning for high spatial resolution Synthetic Aperture Radar (SAR images. To explore the representative and discriminative attributes of SAR images, first, an iterative unsupervised algorithm is designed to cluster in the low-level feature space, where the maximum edge response and the ratio of mean-to-variance are included; a cross-validation step is applied to prevent overfitting. Second, the most discriminative clustering centers are sorted out to construct an attribute dictionary. By resorting to the attribute dictionary, a representation vector describing certain categories in the SAR image can be generated, which in turn is used to perform the classifying task. The experiments conducted on TerraSAR-X images indicate that those learned attributes have strong visual semantics, which are characterized by bright and dark spots, stripes, or their combinations. The classification method based on these learned attributes achieves better results.

  3. Designing Learning Resources in Synchronous Learning Environments

    DEFF Research Database (Denmark)

    Christiansen, Rene B

    2015-01-01

    Computer-mediated Communication (CMC) and synchronous learning environments offer new solutions for teachers and students that transcend the singular one-way transmission of content knowledge from teacher to student. CMC makes it possible not only to teach computer mediated but also to design...... and create new learning resources targeted to a specific group of learners. This paper addresses the possibilities of designing learning resources within synchronous learning environments. The empirical basis is a cross-country study involving students and teachers in primary schools in three Nordic...... Countries (Denmark, Sweden and Norway). On the basis of these empirical studies a set of design examples is drawn with the purpose of showing how the design fulfills the dual purpose of functioning as a remote, synchronous learning environment and - using the learning materials used and recordings...

  4. Multimodal sequence learning.

    Science.gov (United States)

    Kemény, Ferenc; Meier, Beat

    2016-02-01

    While sequence learning research models complex phenomena, previous studies have mostly focused on unimodal sequences. The goal of the current experiment is to put implicit sequence learning into a multimodal context: to test whether it can operate across different modalities. We used the Task Sequence Learning paradigm to test whether sequence learning varies across modalities, and whether participants are able to learn multimodal sequences. Our results show that implicit sequence learning is very similar regardless of the source modality. However, the presence of correlated task and response sequences was required for learning to take place. The experiment provides new evidence for implicit sequence learning of abstract conceptual representations. In general, the results suggest that correlated sequences are necessary for implicit sequence learning to occur. Moreover, they show that elements from different modalities can be automatically integrated into one unitary multimodal sequence. Copyright © 2015 Elsevier B.V. All rights reserved.

  5. Transformative learning spaces

    DEFF Research Database (Denmark)

    Maslo, Elina

    Despite rapid development of learning theory in general and language learning theory in particular in the last years, we still cannot provide an unequivocal answer on the question “why do individuals who presumably possess similar cognitive capacities for second language learning achieve such var......, Leo (2010). The ecology of language learning: Practice to theory, theory to practice. Procedia – Social and Behavioral Sciences. Elsevier......., social, personal, cultural, and historical world they live in (van Lier, 2000). People can learn when they discover possibilities for learning, which appear in this complex world – so called affordances (Gibson, 1979). This happens in the interaction between people and their environment on the basis...... to the different ways of interaction of cognitive, affective and social factors by different individuals. Learning stories, where multilingual individuals are telling about their subjective experiences in language learning in particular and learning in general, are constructed by using a special developed...

  6. Unsupervised information extraction by text segmentation

    CERN Document Server

    Cortez, Eli

    2013-01-01

    A new unsupervised approach to the problem of Information Extraction by Text Segmentation (IETS) is proposed, implemented and evaluated herein. The authors' approach relies on information available on pre-existing data to learn how to associate segments in the input string with attributes of a given domain relying on a very effective set of content-based features. The effectiveness of the content-based features is also exploited to directly learn from test data structure-based features, with no previous human-driven training, a feature unique to the presented approach. Based on the approach, a

  7. Supervised versus unsupervised categorization: two sides of the same coin?

    Science.gov (United States)

    Pothos, Emmanuel M; Edwards, Darren J; Perlman, Amotz

    2011-09-01

    Supervised and unsupervised categorization have been studied in separate research traditions. A handful of studies have attempted to explore a possible convergence between the two. The present research builds on these studies, by comparing the unsupervised categorization results of Pothos et al. ( 2011 ; Pothos et al., 2008 ) with the results from two procedures of supervised categorization. In two experiments, we tested 375 participants with nine different stimulus sets and examined the relation between ease of learning of a classification, memory for a classification, and spontaneous preference for a classification. After taking into account the role of the number of category labels (clusters) in supervised learning, we found the three variables to be closely associated with each other. Our results provide encouragement for researchers seeking unified theoretical explanations for supervised and unsupervised categorization, but raise a range of challenging theoretical questions.

  8. Assessing learning at the workplace

    NARCIS (Netherlands)

    Evers, Arnoud

    2018-01-01

    • Defining learning at the workplace • Assessing learning at the workplace • Facilitating learning at the workplace: - Structure - Culture - Leadership - Personal factors • Conclusions • Discussion

  9. Mobile learning in medicine

    Science.gov (United States)

    Serkan Güllüoüǧlu, Sabri

    2013-03-01

    This paper outlines the main infrastructure for implicating mobile learning in medicine and present a sample mobile learning application for medical learning within the framework of mobile learning systems. Mobile technology is developing nowadays. In this case it will be useful to develop different learning environments using these innovations in internet based distance education. M-learning makes the most of being on location, providing immediate access, being connected, and acknowledges learning that occurs beyond formal learning settings, in places such as the workplace, home, and outdoors. Central to m-learning is the principle that it is the learner who is mobile rather than the device used to deliver m learning. The integration of mobile technologies into training has made learning more accessible and portable. Mobile technologies make it possible for a learner to have access to a computer and subsequently learning material and activities; at any time and in any place. Mobile devices can include: mobile phone, personal digital assistants (PDAs), personal digital media players (eg iPods, MP3 players), portable digital media players, portable digital multimedia players. Mobile learning (m-learning) is particularly important in medical education, and the major users of mobile devices are in the field of medicine. The contexts and environment in which learning occurs necessitates m-learning. Medical students are placed in hospital/clinical settings very early in training and require access to course information and to record and reflect on their experiences while on the move. As a result of this paper, this paper strives to compare and contrast mobile learning with normal learning in medicine from various perspectives and give insights and advises into the essential characteristics of both for sustaining medical education.

  10. Implementing Machine Learning in Radiology Practice and Research.

    Science.gov (United States)

    Kohli, Marc; Prevedello, Luciano M; Filice, Ross W; Geis, J Raymond

    2017-04-01

    The purposes of this article are to describe concepts that radiologists should understand to evaluate machine learning projects, including common algorithms, supervised as opposed to unsupervised techniques, statistical pitfalls, and data considerations for training and evaluation, and to briefly describe ethical dilemmas and legal risk. Machine learning includes a broad class of computer programs that improve with experience. The complexity of creating, training, and monitoring machine learning indicates that the success of the algorithms will require radiologist involvement for years to come, leading to engagement rather than replacement.

  11. How Well can We Learn Interpretable Entity Types from Text?

    DEFF Research Database (Denmark)

    Hovy, Dirk

    2014-01-01

    We investigate a largely unsupervised approach to learning interpretable, domain-specific entity types from unlabeled text. It assumes that any common noun in a domain can function as potential entity type, and uses those nouns as hidden variables in a HMM. To constrain training, it extracts co......-occurrence dictionaries of entities and common nouns from the data. We evaluate the learned types by measuring their prediction accuracy for verb arguments in several domains. The results suggest that it is possible to learn domain-specific entity types from unlabeled data. We show significant improvements over...

  12. Learning in Non-Stationary Environments Methods and Applications

    CERN Document Server

    Lughofer, Edwin

    2012-01-01

    Recent decades have seen rapid advances in automatization processes, supported by modern machines and computers. The result is significant increases in system complexity and state changes, information sources, the need for faster data handling and the integration of environmental influences. Intelligent systems, equipped with a taxonomy of data-driven system identification and machine learning algorithms, can handle these problems partially. Conventional learning algorithms in a batch off-line setting fail whenever dynamic changes of the process appear due to non-stationary environments and external influences.   Learning in Non-Stationary Environments: Methods and Applications offers a wide-ranging, comprehensive review of recent developments and important methodologies in the field. The coverage focuses on dynamic learning in unsupervised problems, dynamic learning in supervised classification and dynamic learning in supervised regression problems. A later section is dedicated to applications in which dyna...

  13. Pervasive Learning Environments

    DEFF Research Database (Denmark)

    Hundebøl, Jesper; Helms, Niels Henrik

    2006-01-01

    The potentials of pervasive communication in learning within industry and education are right now being explored through different R&D projects. This paper outlines the background for and the possible learning potentials in what we describe as pervasive learning environments (PLE). PLE?s differ...... from virtual learning environments (VLE) primarily because in PLE?s the learning content is very much related to the actual context in which the learner finds himself. Two local (Denmark) cases illustrate various aspects of pervasive learning. One is the eBag, a pervasive digital portfolio used...

  14. Transnational Learning Processes

    DEFF Research Database (Denmark)

    Nedergaard, Peter

    This paper analyses and compares the transnational learning processes in the employment field in the European Union and among the Nordic countries. Based theoretically on a social constructivist model of learning and methodologically on a questionnaire distributed to the relevant participants......, a number of hypotheses concerning transnational learning processes are tested. The paper closes with a number of suggestions regarding an optimal institutional setting for facilitating transnational learning processes.Key words: Transnational learning, Open Method of Coordination, Learning, Employment......, European Employment Strategy, European Union, Nordic countries....

  15. Learning to Innovate

    DEFF Research Database (Denmark)

    Mei, Maggie

    the relationship between organizational learning and innovation creation in an organizational context. Taking a nuanced view of organizational learning, the dissertation investigates how three different organizational learning processes could affect innovation creation at the firm level and project level...... to the understanding of managing organizational learning for innovation creation at firms. The three studies in this dissertation show how three prominent organizational learning processes impact on firms’ innovation performance. Furthermore, the studies in this dissertation emphasize that there are limitation...... and boundary conditions for different organizational learning processes....

  16. Machine Learning Techniques in Clinical Vision Sciences.

    Science.gov (United States)

    Caixinha, Miguel; Nunes, Sandrina

    2017-01-01

    This review presents and discusses the contribution of machine learning techniques for diagnosis and disease monitoring in the context of clinical vision science. Many ocular diseases leading to blindness can be halted or delayed when detected and treated at its earliest stages. With the recent developments in diagnostic devices, imaging and genomics, new sources of data for early disease detection and patients' management are now available. Machine learning techniques emerged in the biomedical sciences as clinical decision-support techniques to improve sensitivity and specificity of disease detection and monitoring, increasing objectively the clinical decision-making process. This manuscript presents a review in multimodal ocular disease diagnosis and monitoring based on machine learning approaches. In the first section, the technical issues related to the different machine learning approaches will be present. Machine learning techniques are used to automatically recognize complex patterns in a given dataset. These techniques allows creating homogeneous groups (unsupervised learning), or creating a classifier predicting group membership of new cases (supervised learning), when a group label is available for each case. To ensure a good performance of the machine learning techniques in a given dataset, all possible sources of bias should be removed or minimized. For that, the representativeness of the input dataset for the true population should be confirmed, the noise should be removed, the missing data should be treated and the data dimensionally (i.e., the number of parameters/features and the number of cases in the dataset) should be adjusted. The application of machine learning techniques in ocular disease diagnosis and monitoring will be presented and discussed in the second section of this manuscript. To show the clinical benefits of machine learning in clinical vision sciences, several examples will be presented in glaucoma, age-related macular degeneration

  17. e-Learning for Lifelong Learning in Denmark

    DEFF Research Database (Denmark)

    Buhl, Mie; Andreasen, Lars Birch

    2010-01-01

    The chapter on 'e-Learning for Lifelong Learning in Denmark' is part of an international White Paper, focusing on educational systems, describing status and characteristics and highlighting specific cases of e-learning and of lifelong learning....

  18. Unsupervised Word Mapping Using Structural Similarities in Monolingual Embeddings

    OpenAIRE

    Aldarmaki, Hanan; Mohan, Mahesh; Diab, Mona

    2017-01-01

    Most existing methods for automatic bilingual dictionary induction rely on prior alignments between the source and target languages, such as parallel corpora or seed dictionaries. For many language pairs, such supervised alignments are not readily available. We propose an unsupervised approach for learning a bilingual dictionary for a pair of languages given their independently-learned monolingual word embeddings. The proposed method exploits local and global structures in monolingual vector ...

  19. Bilingual Lexical Interactions in an Unsupervised Neural Network Model

    Science.gov (United States)

    Zhao, Xiaowei; Li, Ping

    2010-01-01

    In this paper we present an unsupervised neural network model of bilingual lexical development and interaction. We focus on how the representational structures of the bilingual lexicons can emerge, develop, and interact with each other as a function of the learning history. The results show that: (1) distinct representations for the two lexicons…

  20. Towards Stable Adversarial Feature Learning for LiDAR based Loop Closure Detection

    OpenAIRE

    Xu, Lingyun; Yin, Peng; Luo, Haibo; Liu, Yunhui; Han, Jianda

    2017-01-01

    Stable feature extraction is the key for the Loop closure detection (LCD) task in the simultaneously localization and mapping (SLAM) framework. In our paper, the feature extraction is operated by using a generative adversarial networks (GANs) based unsupervised learning. GANs are powerful generative models, however, GANs based adversarial learning suffers from training instability. We find that the data-code joint distribution in the adversarial learning is a more complex manifold than in the...

  1. Lessons Learned

    International Nuclear Information System (INIS)

    Dougan, A.D.; Blair, S.

    2006-01-01

    LLNL turned in 5 Declaration Line Items (DLI's) in 2006. Of these, one was declared completed. We made some changes to streamline our process from 2005, used less money, time and fewer team members. This report is a description of what changes we made in 2006 and what we learned. Many of our core review team had changed from last year, including our Laboratory Director, the Facility safety and security representatives, our Division Leader, and the OPSEC Committee Chair. We were able to hand out an AP Manual to some of them, and briefed all newcomers to the AP process. We first went to the OPSEC Committee and explained what the Additional Protocol process would be for 2006 and solicited their help in locating declarable projects. We utilized the 'three questions' from the AP meeting last year. LLNL has no single place to locate all projects at the laboratory. We talked to Resource Managers and key Managers in the Energy and Environment Directorate and in the Nonproliferation Homeland and International Security Directorate to find applicable projects. We also talked to the Principal Investigators who had projects last year. We reviewed a list of CRADA's and LDRD projects given to us by the Laboratory Site Office. Talking to the PI's proved difficult because of vacation or travel schedules. We were never able to locate one PI in town. Fortunately, collateral information allowed us to screen out his project. We had no problems in downloading new versions of the DWA and DDA. It was helpful for both Steve Blair and Arden Dougan to have write privileges. During the time we were working on the project, we had to tag-team the work to allow for travel and vacation schedules. We had some difficulty locating an 'activities block' in the software. This was mentioned as something we needed to fix from our 2005 declaration. Evidently the Activities Block has been removed from the current version of the software. We also had trouble finding the DLI Detail Report, which we included

  2. Alternatively Constrained Dictionary Learning For Image Superresolution.

    Science.gov (United States)

    Lu, Xiaoqiang; Yuan, Yuan; Yan, Pingkun

    2014-03-01

    Dictionaries are crucial in sparse coding-based algorithm for image superresolution. Sparse coding is a typical unsupervised learning method to study the relationship between the patches of high-and low-resolution images. However, most of the sparse coding methods for image superresolution fail to simultaneously consider the geometrical structure of the dictionary and the corresponding coefficients, which may result in noticeable superresolution reconstruction artifacts. In other words, when a low-resolution image and its corresponding high-resolution image are represented in their feature spaces, the two sets of dictionaries and the obtained coefficients have intrinsic links, which has not yet been well studied. Motivated by the development on nonlocal self-similarity and manifold learning, a novel sparse coding method is reported to preserve the geometrical structure of the dictionary and the sparse coefficients of the data. Moreover, the proposed method can preserve the incoherence of dictionary entries and provide the sparse coefficients and learned dictionary from a new perspective, which have both reconstruction and discrimination properties to enhance the learning performance. Furthermore, to utilize the model of the proposed method more effectively for single-image superresolution, this paper also proposes a novel dictionary-pair learning method, which is named as two-stage dictionary training. Extensive experiments are carried out on a large set of images comparing with other popular algorithms for the same purpose, and the results clearly demonstrate the effectiveness of the proposed sparse representation model and the corresponding dictionary learning algorithm.

  3. Stealth Learning: Unexpected Learning Opportunities through Games

    Science.gov (United States)

    Sharp, Laura A.

    2012-01-01

    Educators across the country struggle to create engaging, motivating learning environments for their Net Gen students. These learners expect instant gratification that traditional lectures do not provide. This leaves educators searching for innovative ways to engage students in order to encourage learning. One solution is for educators to use…

  4. From E-learning to Blended Learning

    DEFF Research Database (Denmark)

    Hansen, Line Skov; Hansen, Ole

    2013-01-01

    . The project uses a ?capacity building strategy where new practice and skills are built through pedagogical interventions mostly designed as courses based on blended learning with a dialogue oriented and practice related team-work as an important part. Through this work the team learns how to use a specific...

  5. Generative Learning: Adults Learning within Ambiguity

    Science.gov (United States)

    Nicolaides, Aliki

    2015-01-01

    This study explored the extent to which ambiguity can serve as a catalyst for adult learning. The purpose of this study is to understand learning that is generated when encountering ambiguity agitated by the complexity of liquid modernity. "Ambiguity," in this study, describes an encounter with an appearance of reality that is at first…

  6. LEARNING HOW TO LEARN A LANGUAGE

    CERN Multimedia

    Language Training; Tel. 73127; Andrée Fontbonne; Tel. 72844

    2001-01-01

    This bilingual seminar is for anyone who would like to develop learning strategies and skills for learning a foreign language. Languages: French and English. Length: 3 days, 7 hours per day. Dates: 4, 5, 6 March 2002. Price: 460 CHF per person (for a group of 8 people). If you are interested, please enrol through our Web pages: http://cern.ch/Training

  7. LEARNING HOW TO LEARN A LANGUAGE

    CERN Multimedia

    Language Training; Tel. 73127; Andrée Fontbonne; Tel. 72844

    2001-01-01

    This bilingual seminar is for anyone who would like to develop learning strategies and skills for learning a foreign language. Languages: French and English. Length: 3 days, 7 hours per day. Dates: 5, 6, 7 November 2001. Price: 460 CHF per person (for a group of 8 people). If you are interested, please enrol through our Web pages: http://cern.ch/Training

  8. Constructivist learning theories and complex learning environments

    NARCIS (Netherlands)

    R-J. Simons; Dr. S. Bolhuis

    2004-01-01

    Learning theories broadly characterised as constructivist, agree on the importance to learning of the environment, but differ on what exactly it is that constitutes this importance. Accordingly, they also differ on the educational consequences to be drawn from the theoretical perspective. Cognitive

  9. Transformative Learning: Personal Empowerment in Learning Mathematics

    Science.gov (United States)

    Hassi, Marja-Liisa; Laursen, Sandra L.

    2015-01-01

    This article introduces the concept of personal empowerment as a form of transformative learning. It focuses on commonly ignored but enhancing elements of mathematics learning and argues that crucial personal resources can be essentially promoted by high engagement in mathematical problem solving, inquiry, and collaboration. This personal…

  10. Facilitating "Organisational Learning" in a "Learning Institution"

    Science.gov (United States)

    Lawler, Alan; Sillitoe, James

    2013-01-01

    The term "organisational learning" was popularised by Peter Senge in "The Fifth Discipline", his seminal book from 1990. Since then, the term has become widely accepted among those interested in organisational learning and change management. However, partly due to the somewhat ambiguous situation which arises in a university…

  11. Cooperative Learning as a Democratic Learning Method

    Science.gov (United States)

    Erbil, Deniz Gökçe; Kocabas, Ayfer

    2018-01-01

    In this study, the effects of applying the cooperative learning method on the students' attitude toward democracy in an elementary 3rd-grade life studies course was examined. Over the course of 8 weeks, the cooperative learning method was applied with an experimental group, and traditional methods of teaching life studies in 2009, which was still…

  12. Learning about Allergies

    Science.gov (United States)

    ... Videos for Educators Search English Español Learning About Allergies KidsHealth / For Kids / Learning About Allergies What's in ... in the spring. Why Do Some Kids Get Allergies? People may be born with a genetic (say: ...

  13. Pervasive Learning Environments

    DEFF Research Database (Denmark)

    Hundebøl, Jesper; Helms, Niels Henrik

    in schools. The other is moreover related to work based learning in that it foresees a community of practitioners accessing, sharing and adding to knowledge and learning objects held within a pervasive business intelligence system. Limitations and needed developments of these and other systems are discussed......Abstract: The potentials of pervasive communication in learning within industry and education are right know being explored through different R&D projects. This paper outlines the background for and the possible learning potentials in what we describe as pervasive learning environments (PLE). PLE......'s differ from virtual learning environments (VLE) primarily because in PLE's the learning content is very much related to the actual context in which the learner finds himself. Two local (Denmark) cases illustrate various aspects of pervasive learning. One is the eBag, a pervasive digital portfolio used...

  14. Learning by Doing.

    Science.gov (United States)

    Schettler, Joel

    2002-01-01

    Suggests that, as people become the key differentiation of competitive advantage, companies are turning to experiential learning programs to foster work force collaboration and cooperation. Discusses the history of experiential learning and its application in the workplace. (JOW)

  15. Learning Networks Distributed Environment

    NARCIS (Netherlands)

    Martens, Harrie; Vogten, Hubert; Koper, Rob; Tattersall, Colin; Van Rosmalen, Peter; Sloep, Peter; Van Bruggen, Jan; Spoelstra, Howard

    2005-01-01

    Learning Networks Distributed Environment is a prototype of an architecture that allows the sharing and modification of learning materials through a number of transport protocols. The prototype implements a p2p protcol using JXTA.

  16. Learning about Proteins

    Science.gov (United States)

    ... Fitness Diseases & Conditions Infections Drugs & Alcohol School & Jobs Sports Expert Answers (Q&A) Staying Safe Videos for Educators Search English Español Learning About Proteins KidsHealth / For Kids / Learning About Proteins What's in ...

  17. Learning in Practice

    DEFF Research Database (Denmark)

    Helth, Poula

    on theories of aesthetic performance and transformative learning, and on empirical studies through interventive methods within action research and ethnography. Transformative learning in my study has been developed based on aesthetic performance addressing leaders’ learning in practice. This kind of learning......The thesis presents the essence of my study of how leaders transform their practice through aesthetic performance. The background of the study is leaders' need for learning in and through practice, as an alternative to learning in classrooms and to leadership education programs. The study is based...... happens when leaders become aware of the potential for transformation of their leadership practice when they experiment with aesthetic performance integrated in a learning process. The greatest impact in relation to organisational transformation is, when leaders base their learning on a collective...

  18. MOOC Blended learning ontwikkelen

    NARCIS (Netherlands)

    Verjans, Steven

    2015-01-01

    Presentatie over het ontwerpen van leeractiviteiten (learning design) tijdens de zesde live sessie van de MOOC Blended learning ontwikkelen. Met gebruikmaking van presentatiematerialen van Diana Laurillard, Grainne Conole, Helen Beetham, Jos Fransen, Pieter Swager, Helen Keegan, Corinne Weisgerber.

  19. Social Structures for Learning

    NARCIS (Netherlands)

    I.M. Bogenrieder (Irma); B. Nooteboom (Bart)

    2001-01-01

    textabstractThis article investigates what learning groups there are in organizations, other than the familiar 'communities of practice'. It first develops an interdisciplinary theoretical framework for identifying, categorizing and understanding learning groups. For this, it employs a

  20. Learning about Carbohydrates

    Science.gov (United States)

    ... Videos for Educators Search English Español Learning About Carbohydrates KidsHealth / For Kids / Learning About Carbohydrates Print en ... source of energy for the body. What Are Carbohydrates? There are two major types of carbohydrates (or ...

  1. Preventing Learned Helplessness.

    Science.gov (United States)

    Hoy, Cheri

    1986-01-01

    To prevent learned helplessness in learning disabled students, teachers can share responsibilities with the students, train students to reinforce themselves for effort and self control, and introduce opportunities for changing counterproductive attitudes. (CL)

  2. Teaming up for learning

    NARCIS (Netherlands)

    Fransen, Jos

    2012-01-01

    Fransen, J. (2012). Teaming up for learning: Team effectiveness in collaborative learning in higher education (Doctoral dissertation). November, 16, 2012, Open University in the Netherlands (CELSTEC), Heerlen, The Netherlands.

  3. Teachability in Computational Learning

    OpenAIRE

    Shinohara, Ayumi; Miyano, Satoru

    1990-01-01

    This paper considers computationai learning from the viewpoint of teaching. We introduce a notion of teachability with which we establish a relationship between the learnability and teachability. We also discuss the complexity issues of a teacher in relation to learning.

  4. The sign learning theory

    African Journals Online (AJOL)

    KING OF DAWN

    The sign learning theory also holds secrets that could be exploited in accomplishing motor tasks. ... Introduction ... In his classic work: Cognitive Map in Rats and Men (1948),Tolman talked about five groups of experiments viz: latent learning ...

  5. Efficient Learning Design

    DEFF Research Database (Denmark)

    Godsk, Mikkel

    This paper presents the current approach to implementing educational technology with learning design at the Faculty of Science and Technology, Aarhus University, by introducing the concept of ‘efficient learning design’. The underlying hypothesis is that implementing learning design is more than...... engaging educators in the design process and developing teaching and learning, it is a shift in educational practice that potentially requires a stakeholder analysis and ultimately a business model for the deployment. What is most important is to balance the institutional, educator, and student...... perspectives and to consider all these in conjunction in order to obtain a sustainable, efficient learning design. The approach to deploying learning design in terms of the concept of efficient learning design, the catalyst for educational development, i.e. the learning design model and how it is being used...

  6. Pervasive Learning Environments

    DEFF Research Database (Denmark)

    Helms, Niels Henrik; Hundebøl, Jesper

    2006-01-01

    The potentials of pervasive communication in learning within industry and education are right know being explored through different R&D projects. This paper outlines the background for and the possible learning potentials in what we describe as pervasive learning environments (PLE). PLE's differ...... from virtual learning environments (VLE) primarily because in PLE's the learning content is very much related to the actual context in which the learner finds himself. Two local (Denmark) cases illustrate various aspects of pervasive learning. One is the eBag, a pervasive digital portfolio used...... in schools. The other is moreover related to work based learning in that it foresees a community of practitioners accessing, sharing and adding to knowledge and learning objects held within a pervasive business intelligence system. Limitations and needed developments of these and other systems are discussed...

  7. Learning Design Tools

    NARCIS (Netherlands)

    Griffiths, David; Blat, Josep; Garcia, Rocío; Vogten, Hubert; Kwong, KL

    2005-01-01

    Griffiths, D., Blat, J., Garcia, R., Vogten, H. & Kwong, KL. (2005). Learning Design Tools. In: Koper, R. & Tattersall, C., Learning Design: A Handbook on Modelling and Delivering Networked Education and Training (pp. 109-136). Berlin-Heidelberg: Springer Verlag.

  8. Genetic Science Learning Center

    Science.gov (United States)

    Genetic Science Learning Center Making science and health easy for everyone to understand Home News Our Team What We Do ... Collaboration Conferences Current Projects Publications Contact The Genetic Science Learning Center at The University of Utah is a ...

  9. Mobile Informal Learning

    NARCIS (Netherlands)

    Glahn, Christian; Börner, Dirk

    2010-01-01

    Glahn, C., & Börner, D. (2009). Mobile Informal Learning. Presented at Mobile Learning in Context Symposium at the Open University of the Netherlands. September, 11, 2009, Heerlen, The Netherlands: Open University of the Netherlands.

  10. Making Learning Meaningful.

    Science.gov (United States)

    Odom, A. Louis; Kelly, Paul V.

    1998-01-01

    Discusses two theories of cognitive development, Ausubel's theory of verbal learning and Piaget's development theory. Illustrates that both concept mapping and the learning cycle are rooted in these two theories. (DDR)

  11. New learning : three ways to learn in a new balance

    NARCIS (Netherlands)

    Simons, P.R.J.

    2000-01-01

    Because people are learning all the time, we need criteria that can help us distinguish between better and worse kinds of learning. Organizations and societies as well as the psychology of learning ask for new learning outcomes, new learning processes and new forms of instruction. New learning

  12. Learning about Learning: A Conundrum and a Possible Resolution

    Science.gov (United States)

    Barnett, Ronald

    2011-01-01

    What is it to learn in the modern world? We can identify four "learning epochs" through which our understanding of learning has passed: a metaphysical view; an empirical view; an experiential view; and, currently, a "learning-amid-contestation" view. In this last and current view, learning has its place in a world in which, the more one learns,…

  13. Effects of Cooperative E-Learning on Learning Outcomes

    Science.gov (United States)

    Yeh, Shang-Pao; Fu, Hsin-Wei

    2014-01-01

    This study aims to discuss the effects of E-Learning and cooperative learning on learning outcomes. E-Learning covers the dimensions of Interpersonal communication, abundant resources, Dynamic instruction, and Learning community; and, cooperative learning contains three dimensions of Cooperative motive, Social interaction, and Cognition…

  14. Learning, Play, and Your Newborn

    Science.gov (United States)

    ... Staying Safe Videos for Educators Search English Español Learning, Play, and Your Newborn KidsHealth / For Parents / Learning, ... Some Other Ideas Print What Is My Newborn Learning? Play is the chief way that infants learn ...

  15. Unsupervised clustering with spiking neurons by sparse temporal coding and multi-layer RBF networks

    NARCIS (Netherlands)

    S.M. Bohte (Sander); J.A. La Poutré (Han); J.N. Kok (Joost)

    2000-01-01

    textabstractWe demonstrate that spiking neural networks encoding information in spike times are capable of computing and learning clusters from realistic data. We show how a spiking neural network based on spike-time coding and Hebbian learning can successfully perform unsupervised clustering on

  16. Supervised and unsupervised condition monitoring of non-stationary acoustic emission signals

    DEFF Research Database (Denmark)

    Sigurdsson, Sigurdur; Pontoppidan, Niels Henrik; Larsen, Jan

    2005-01-01

    condition changes across load changes. In this paper we approach this load interpolation problem with supervised and unsupervised learning, i.e. model with normal and fault examples and normal examples only, respectively. We apply non-linear methods for the learning of engine condition changes. Both...

  17. Supervised Learning for Dynamical System Learning.

    Science.gov (United States)

    Hefny, Ahmed; Downey, Carlton; Gordon, Geoffrey J

    2015-01-01

    Recently there has been substantial interest in spectral methods for learning dynamical systems. These methods are popular since they often offer a good tradeoff between computational and statistical efficiency. Unfortunately, they can be difficult to use and extend in practice: e.g., they can make it difficult to incorporate prior information such as sparsity or structure. To address this problem, we present a new view of dynamical system learning: we show how to learn dynamical systems by solving a sequence of ordinary supervised learning problems, thereby allowing users to incorporate prior knowledge via standard techniques such as L 1 regularization. Many existing spectral methods are special cases of this new framework, using linear regression as the supervised learner. We demonstrate the effectiveness of our framework by showing examples where nonlinear regression or lasso let us learn better state representations than plain linear regression does; the correctness of these instances follows directly from our general analysis.

  18. Immersive Learning Technologies

    Science.gov (United States)

    2009-08-20

    Immersive Learning Technologies Mr. Peter Smith Lead, ADL Immersive Learning Team 08/20/2009 Report Documentation Page Form ApprovedOMB No. 0704...to 00-00-2009 4. TITLE AND SUBTITLE Immersive Learning Technologies 5a. CONTRACT NUMBER 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR...unclassified c. THIS PAGE unclassified Standard Form 298 (Rev. 8-98) Prescribed by ANSI Std Z39-18 Why Immersive Learning Technologies

  19. Learning a Second Language

    OpenAIRE

    Murphy, Caroline; Hermann, Charlotte; Andersen, Signe Hvalsøe; Grigalauskyte, Simona; Tolsgaard, Mads; Holmegaard, Thorbjørn; Hajaya, Zaedo Musa

    2013-01-01

    This study examines the concept of second language learning in Denmark with focus on how second language learners negotiate their identities in relation to language learning and integration. By investigating three language learners’ acquisition of Danish through key theories on the field of second language learning, focus is centred on the subjects’ lived experiences of the learning process within their everyday lives and in the classroom. Through interviews and observations it can be conclud...

  20. Social Structures for Learning

    OpenAIRE

    Bogenrieder, I.M.; Nooteboom, B.

    2001-01-01

    textabstractThis article investigates what learning groups there are in organizations, other than the familiar 'communities of practice'. It first develops an interdisciplinary theoretical framework for identifying, categorizing and understanding learning groups. For this, it employs a constructivist, interactionist theory of knowledge and learning. It employs elements of transaction cost theory and of social theory of trust. Transaction cost economics neglects learning and trust, but element...

  1. Pervasive e-learning

    DEFF Research Database (Denmark)

    Hundebøl, Jesper; Helms, Niels Henrik

    2009-01-01

    This article falls within planning, production and delivery of innovative learning resources. The establishment of pervasive learning environments is based on the successful combination and re-configuration of inter-connected sets of learning objects, databases and data-streams. The text presents...... a definition of Pervasive Learning Environments and discusses the pedagogical potentials and challenges in developing such environments with emphasis on context, new didactics, content and affordances....

  2. Evolving to organizational learning.

    Science.gov (United States)

    Bechtold, B L

    2000-02-01

    To transform in stride with the business changes, organizations need to think of development as "organizational learning" rather than "training." Companies need to manage learning as a strategic competitive advantage for current and future business rather than as a perk for individuals. To position themselves for success in a dynamic business environment, companies need to reframe their concept of learning and development to a mindset of organizational learning.

  3. LEADING THE LEARNING ORGANIZATION

    OpenAIRE

    Sapna Rijal

    2009-01-01

    Researchers have identified leadership as being one of the most important factors that influence the development of learning organization. They suggest that creating a collective vision of the future, empowering and developing employees so that they are better able to handle environmental challenges, modeling learning behavior and creating a learning environment, are crucial skills for leaders of learning organization. These roles are suitable to a transformational leader. Despite the potenti...

  4. Social learning in fish

    OpenAIRE

    Atton, Nicola

    2010-01-01

    Social learning is known to be a common phenomenon in fish, which they utilise under many different contexts, including foraging, mate-choice and migration. Here I review the literature on social learning in fish and present two studies. The first examines the ability of threespined sticklebacks to use social learning in the enhancement of food preferences. The second study examines the ability of both threespined sticklebacks and ninespined sticklebacks to use social learning in the avoidanc...

  5. Learning from prescribing errors

    OpenAIRE

    Dean, B

    2002-01-01

    

 The importance of learning from medical error has recently received increasing emphasis. This paper focuses on prescribing errors and argues that, while learning from prescribing errors is a laudable goal, there are currently barriers that can prevent this occurring. Learning from errors can take place on an individual level, at a team level, and across an organisation. Barriers to learning from prescribing errors include the non-discovery of many prescribing errors, lack of feedback to th...

  6. Microsoft Azure machine learning

    CERN Document Server

    Mund, Sumit

    2015-01-01

    The book is intended for those who want to learn how to use Azure Machine Learning. Perhaps you already know a bit about Machine Learning, but have never used ML Studio in Azure; or perhaps you are an absolute newbie. In either case, this book will get you up-and-running quickly.

  7. My Teaching Learning Philosophy

    Science.gov (United States)

    Punjani, Neelam Saleem

    2014-01-01

    The heart of teaching learning philosophy is the concept of nurturing students and teaching them in a way that creates passion and enthusiasm in them for a lifelong learning. According to Duke (1990) education is a practice of artful action where teaching learning process is considered as design and knowledge is considered as colours. Teaching…

  8. Enhancing learning with technology

    NARCIS (Netherlands)

    Specht, Marcus; Klemke, Roland

    2013-01-01

    Specht, M., & Klemke, R. (2013, 26-27 September). Enhancing Learning with Technology. In D. Milosevic (Ed.), Proceedings of the fourth international conference on eLearning (eLearning 2013) (pp. 37-45). Belgrade Metropolitan University, Belgrade, Serbia. http://econference.metropolitan.ac.rs/

  9. Deep Learning Policy Quantization

    NARCIS (Netherlands)

    van de Wolfshaar, Jos; Wiering, Marco; Schomaker, Lambertus

    2018-01-01

    We introduce a novel type of actor-critic approach for deep reinforcement learning which is based on learning vector quantization. We replace the softmax operator of the policy with a more general and more flexible operator that is similar to the robust soft learning vector quantization algorithm.

  10. Games for Learning

    Science.gov (United States)

    Gee, James Paul

    2013-01-01

    Today there is a great deal of interest in and a lot of hype about using video games in schools. Video games are a new silver bullet. Games can create good learning because they teach in powerful ways. The theory behind game-based learning is not really new, but a traditional and well-tested approach to deep and effective learning, often…

  11. Learning Probabilistic Decision Graphs

    DEFF Research Database (Denmark)

    Jaeger, Manfred; Dalgaard, Jens; Silander, Tomi

    2004-01-01

    efficient representations than Bayesian networks. In this paper we present an algorithm for learning PDGs from data. First experiments show that the algorithm is capable of learning optimal PDG representations in some cases, and that the computational efficiency of PDG models learned from real-life data...

  12. A learning space Odyssey

    NARCIS (Netherlands)

    Beckers, Ronald

    2016-01-01

    This dissertation addresses the alignment of learning space with higher education learning and teaching. Significant changes in higher education the past decades, such as increased information and communication technology (ICT) and new learning theories have resulted in the dilemma whether higher

  13. Learning in Organization

    Science.gov (United States)

    Palos, Ramona; Veres Stancovici, Vesna

    2016-01-01

    Purpose: This study aims at identifying the presence of the dimensions of learning capabilities and the characteristics of a learning organization within two companies in the field of services, as well as identifying the relationships between their learning capability and the organizational culture. Design/methodology/approach: This has been a…

  14. Learning Outcomes Report

    NARCIS (Netherlands)

    Stoyanov, Slavi; Spoelstra, Howard; Burgoyne, Louise; O’Tuathaigh, Colm

    2018-01-01

    Aim of the study The learning outcomes study, conducted as part of WP3 of the BioApp project, has as objectives: (a) generating a comprehensive list of the learning outcomes; (b) reaching an agreement on the scope and priority of the learning outcomes, and (c) making suggestions for the further

  15. Action Learning in China

    Science.gov (United States)

    Marquardt, Michael J.

    2015-01-01

    Action learning was introduced into China less than 20 years ago, but has rapidly become a valuable tool for organizations seeking to solve problems, develop their leaders, and become learning organizations. This article provides an historical overview of action learning in China, its cultural underpinnings, and five case studies. It concludes…

  16. Invited Reaction: Influences of Formal Learning, Personal Learning Orientation, and Supportive Learning Environment on Informal Learning

    Science.gov (United States)

    Cseh, Maria; Manikoth, Nisha N.

    2011-01-01

    As the authors of the preceding article (Choi and Jacobs, 2011) have noted, the workplace learning literature shows evidence of the complementary and integrated nature of formal and informal learning in the development of employee competencies. The importance of supportive learning environments in the workplace and of employees' personal learning…

  17. KARATE WITH CONSTRUCTIVE LEARNING

    Directory of Open Access Journals (Sweden)

    Srikrishna Karanam

    2012-02-01

    Full Text Available Any conventional learning process involves the traditional hierarchy of garnering of information and then recall gathered information. Constructive learning is an important research area having wide impact on teaching methods in education, learning theories, and plays a major role in many education reform movements. It is observed that constructive learning advocates the interconnection between emotions and learning. Human teachers identify the emotions of students with varying degrees of accuracy and can improve the learning rate of the students by motivating them. In learning with computers, computers also should be given the capability to recognize emotions so as to optimize the learning process. Image Processing is a very popular tool used in the process of establishing the theory of Constructive Learning. In this paper we use the Optical Flow computation in image sequences to analyze the accuracy of the moves of a karate player. We have used the Lucas-Kanade method for computing the optical flow in image sequences. A database consisting of optical flow images by a group of persons learning karate is formed and the learning rates are analyzed in order to main constructive learning. The contours of flow images are compared with the standard images and the error graphs are plotted. Analysis of the emotion of the amateur karate player is made by observing the error plots.

  18. Repurposing learning object components

    NARCIS (Netherlands)

    Verbert, K.; Jovanovic, J.; Gasevic, D.; Duval, E.; Meersman, R.

    2005-01-01

    This paper presents an ontology-based framework for repurposing learning object components. Unlike the usual practice where learning object components are assembled manually, the proposed framework enables on-the-fly access and repurposing of learning object components. The framework supports two

  19. Canadian Chefs' Workplace Learning

    Science.gov (United States)

    Cormier-MacBurnie, Paulette; Doyle, Wendy; Mombourquette, Peter; Young, Jeffrey D.

    2015-01-01

    Purpose: This paper aims to examine the formal and informal workplace learning of professional chefs. In particular, it considers chefs' learning strategies and outcomes as well as the barriers to and facilitators of their workplace learning. Design/methodology/approach: The methodology is based on in-depth, face-to-face, semi-structured…

  20. Learning: An Evolutionary Analysis

    Science.gov (United States)

    Swann, Joanna

    2009-01-01

    This paper draws on the philosophy of Karl Popper to present a descriptive evolutionary epistemology that offers philosophical solutions to the following related problems: "What happens when learning takes place?" and "What happens in human learning?" It provides a detailed analysis of how learning takes place without any direct transfer of…

  1. Guided Learning at Work.

    Science.gov (United States)

    Billett, Stephen

    2000-01-01

    Guided learning (questioning, diagrams/analogies, modeling, coaching) was studied through critical incident interviews in five workplaces. Participation in everyday work activities was the most effective contributor to workplace learning. Organizational readiness and the efficacy of guided learning in resolving novel tasks were also important. (SK)

  2. Adult Learning Assumptions

    Science.gov (United States)

    Baskas, Richard S.

    2011-01-01

    The purpose of this study is to examine Knowles' theory of andragogy and his six assumptions of how adults learn while providing evidence to support two of his assumptions based on the theory of andragogy. As no single theory explains how adults learn, it can best be assumed that adults learn through the accumulation of formal and informal…

  3. Learning analytics dashboard applications

    NARCIS (Netherlands)

    Verbert, K.; Duval, E.; Klerkx, J.; Govaerts, S.; Santos, J.L.

    2013-01-01

    This article introduces learning analytics dashboards that visualize learning traces for learners and teachers. We present a conceptual framework that helps to analyze learning analytics applications for these kinds of users. We then present our own work in this area and compare with 15 related

  4. Innovazione nel mobile learning

    Directory of Open Access Journals (Sweden)

    Immaculada Arnedillo-Sànchez

    2008-01-01

    Full Text Available Descrizione, da una prospettiva europea, dell’innovazione nel settore del mobile learning e l’utilizzabilita’ del mobile learning in contesti educativi. Vengono illustrate i principali progetti europei di m-learning e si esamina le prospettive pedagogiche e teoriche relative al campo.

  5. Under Threes' Mathematical Learning

    Science.gov (United States)

    Franzén, Karin

    2015-01-01

    The article focuses on mathematics for toddlers in preschool, with the aim of challenging a strong learning discourse that mainly focuses on cognitive learning. By devoting more attention to other perspectives on learning, the hope is to better promote children's early mathematical development. Sweden is one of few countries to have a curriculum…

  6. Learning from Errors

    Science.gov (United States)

    Metcalfe, Janet

    2017-01-01

    Although error avoidance during learning appears to be the rule in American classrooms, laboratory studies suggest that it may be a counterproductive strategy, at least for neurologically typical students. Experimental investigations indicate that errorful learning followed by corrective feedback is beneficial to learning. Interestingly, the…

  7. Learning from Errors

    OpenAIRE

    Martínez-Legaz, Juan Enrique; Soubeyran, Antoine

    2003-01-01

    We present a model of learning in which agents learn from errors. If an action turns out to be an error, the agent rejects not only that action but also neighboring actions. We find that, keeping memory of his errors, under mild assumptions an acceptable solution is asymptotically reached. Moreover, one can take advantage of big errors for a faster learning.

  8. Learning from Failed Decisions

    Science.gov (United States)

    Nutt, Paul C.

    2010-01-01

    The consequences and dilemmas posed by learning issues for decision making are discussed. Learning requires both awareness of barriers and a coping strategy. The motives to hold back information essential for learning stem from perverse incentives, obscure outcomes, and the hindsight bias. There is little awareness of perverse incentives that…

  9. E-Learning Agents

    Science.gov (United States)

    Gregg, Dawn G.

    2007-01-01

    Purpose: The purpose of this paper is to illustrate the advantages of using intelligent agents to facilitate the location and customization of appropriate e-learning resources and to foster collaboration in e-learning environments. Design/methodology/approach: This paper proposes an e-learning environment that can be used to provide customized…

  10. How People Learn in an Asynchronous Online Learning Environment: The Relationships between Graduate Students' Learning Strategies and Learning Satisfaction

    Science.gov (United States)

    Choi, Beomkyu

    2016-01-01

    The purpose of this study was to examine the relationships between learners' learning strategies and learning satisfaction in an asynchronous online learning environment. In an attempt to shed some light on how people learn in an online learning environment, one hundred and sixteen graduate students who were taking online learning courses…

  11. A Flow of Entrepreneurial Learning Elements in Experiential Learning Settings

    DEFF Research Database (Denmark)

    Ramsgaard, Michael Breum; Christensen, Marie Ernst

    This paper explored the concept of learning in an experiential learning setting and whether the learning process can be understood as a flow of learning factors influencing the outcome. If many constituting factors lead to the development of learning outcomes, there might need to be developed...... that are a part of experiential learning settings and curriculum development....... a differentiated approach to facilitate experiential learning. Subsequently the paper investigated how facilitators of learning processes can design a learning space where the boundary of what is expected from the learner is challenged. In other words the aim was to explore the transformative learning processes...

  12. Advanced Machine Learning for Classification, Regression, and Generation in Jet Physics

    CERN Multimedia

    CERN. Geneva

    2017-01-01

    There is a deep connection between machine learning and jet physics - after all, jets are defined by unsupervised learning algorithms. Jet physics has been a driving force for studying modern machine learning in high energy physics. Domain specific challenges require new techniques to make full use of the algorithms. A key focus is on understanding how and what the algorithms learn. Modern machine learning techniques for jet physics are demonstrated for classification, regression, and generation. In addition to providing powerful baseline performance, we show how to train complex models directly on data and to generate sparse stacked images with non-uniform granularity.

  13. Learning in context

    DEFF Research Database (Denmark)

    Keiding, Tina Bering

    2007-01-01

    This article offers a re-description of the concept of learning context. Drawing on Niklas Luhmann and Gregory Bateson it suggests an alternative to situated, social learning and activity theory. The conclusion is that learning context designates an individual's reconstruction of the environment...... through contingent handling of differences and that the individual emerge as learning through the actual construction. Selection of differences is influenced by the learner's actual knowledge, the nature of the environment and the current horizon of meaning in which the current adaptive perspective...... becomes a significant factor. The re-description contributes to didaktik  through renewed understandings of participants' background in teaching and learning....

  14. Political learning among youth

    DEFF Research Database (Denmark)

    Solhaug, Trond; Kristensen, Niels Nørgaard

    2014-01-01

    This article focuses on students’ first political learning and explores the research question, what dynamic patterns of political learning can be explored among a selection of young, diverse Danish students’ first political interests? The authors use theories of learning in their analytical......, but are active constructors of their political life. Their emotions and social environment are highly important for their political orientation. It is recommended that further research focus on dynamic learning and on arenas for political learning rather than on “single agent studies.” Recommendations...

  15. Quantum machine learning.

    Science.gov (United States)

    Biamonte, Jacob; Wittek, Peter; Pancotti, Nicola; Rebentrost, Patrick; Wiebe, Nathan; Lloyd, Seth

    2017-09-13

    Fuelled by increasing computer power and algorithmic advances, machine learning techniques have become powerful tools for finding patterns in data. Quantum systems produce atypical patterns that classical systems are thought not to produce efficiently, so it is reasonable to postulate that quantum computers may outperform classical computers on machine learning tasks. The field of quantum machine learning explores how to devise and implement quantum software that could enable machine learning that is faster than that of classical computers. Recent work has produced quantum algorithms that could act as the building blocks of machine learning programs, but the hardware and software challenges are still considerable.

  16. Rethinking expansive learning

    DEFF Research Database (Denmark)

    Kolbæk, Ditte; Lundh Snis, Ulrika

    Abstract: This paper analyses an online community of master’s students taking a course in ICT and organisational learning. The students initiated and facilitated an educational design for organisational learning called Proactive Review in the organisation where they are employed. By using an online...... discussion forum on Google groups, they created new ways of reflecting and learning. We used netnography to select qualitative postings from the online community and expansive learning concepts for data analysis. The findings show how students changed practices of organisational learning...

  17. Machine learning with R

    CERN Document Server

    Lantz, Brett

    2013-01-01

    Written as a tutorial to explore and understand the power of R for machine learning. This practical guide that covers all of the need to know topics in a very systematic way. For each machine learning approach, each step in the process is detailed, from preparing the data for analysis to evaluating the results. These steps will build the knowledge you need to apply them to your own data science tasks.Intended for those who want to learn how to use R's machine learning capabilities and gain insight from your data. Perhaps you already know a bit about machine learning, but have never used R; or

  18. A Case Study on Sepsis Using PubMed and Deep Learning for Ontology Learning.

    Science.gov (United States)

    Arguello Casteleiro, Mercedes; Maseda Fernandez, Diego; Demetriou, George; Read, Warren; Fernandez Prieto, Maria Jesus; Des Diz, Julio; Nenadic, Goran; Keane, John; Stevens, Robert

    2017-01-01

    We investigate the application of distributional semantics models for facilitating unsupervised extraction of biomedical terms from unannotated corpora. Term extraction is used as the first step of an ontology learning process that aims to (semi-)automatic annotation of biomedical concepts and relations from more than 300K PubMed titles and abstracts. We experimented with both traditional distributional semantics methods such as Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA) as well as the neural language models CBOW and Skip-gram from Deep Learning. The evaluation conducted concentrates on sepsis, a major life-threatening condition, and shows that Deep Learning models outperform LSA and LDA with much higher precision.

  19. Learning Analytics for Supporting Seamless Language Learning Using E-Book with Ubiquitous Learning System

    Science.gov (United States)

    Mouri, Kousuke; Uosaki, Noriko; Ogata, Hiroaki

    2018-01-01

    Seamless learning has been recognized as an effective learning approach across various dimensions including formal and informal learning contexts, individual and social learning, and physical world and cyberspace. With the emergence of seamless learning, the majority of the current research focuses on realizing a seamless learning environment at…

  20. FLIPPED LEARNING: PRACTICAL ASPECTS

    Directory of Open Access Journals (Sweden)

    Olena Kuzminska

    2016-03-01

    Full Text Available The article is devoted to issues of implementation of the flipped learning technology in the practice of higher education institutions. The article defines the principles of technology and a model of the educational process, it notes the need to establish an information support system. The article defines online platforms and resources; it describes recommendations for the design of electronic training courses and organization of the students in the process of implementing the proposed model, as well as tools for assessing its effectiveness. The article provides a description of flipped learning implementation scenario and formulates suggestions regarding the use of this model as a mechanism to improve the efficiency of the learning process in the ICT-rich environment of high school: use of learning management systems (LMS and personal learning environments (PLE of participants in a learning process. The article provides an example of implementation of the flipped learning model as a part of the Information Technologies course in the National University of Life and Environmental Sciences of Ukraine (NULES. The article gives examples of tasks, resources and services, results of students’ research activity, as well as an example of the personal learning network, established in the course of implementation of the flipped learning model and elements of digital student portfolios. It presents the results of the monitoring of learning activities and students’ feedback. The author describes cautions against the mass introduction of the flipped learning model without monitoring of readiness of the participants of the educational process for its implementation

  1. Learning and memory

    Directory of Open Access Journals (Sweden)

    P. A. J. Ryke

    1989-03-01

    Full Text Available Under various circumstances and in different species the outward expression of learning varies considerably, and this has led to the classification of different categories of learning. Just as there is no generally agreed on definition of learning, there is no one system of classification. Types of learning commonly recognized are: Habituation, sensitization, classical conditioning, operant conditioning, trial and error, taste aversion, latent learning, cultural learning, imprinting, insight learning, learning-set learning and instinct. The term memory must include at least two separate processes. It must involve, on the one hand, that of learning something and on the other, at some later date, recalling that thing. What lies between the learning and (he remembering must be some permanent record — a memory trace — within the brain. Memory exists in at least two forms: memory for very recent events (short-term which is relatively labile and easily disruptable; and long-term memory, which is much more stable. Not everything that gets into short-term memory becomes fixed in the long-term store; a filtering mechanism selects things that might be important and discards the rest.

  2. Approximate kernel competitive learning.

    Science.gov (United States)

    Wu, Jian-Sheng; Zheng, Wei-Shi; Lai, Jian-Huang

    2015-03-01

    Kernel competitive learning has been successfully used to achieve robust clustering. However, kernel competitive learning (KCL) is not scalable for large scale data processing, because (1) it has to calculate and store the full kernel matrix that is too large to be calculated and kept in the memory and (2) it cannot be computed in parallel. In this paper we develop a framework of approximate kernel competitive learning for processing large scale dataset. The proposed framework consists of two parts. First, it derives an approximate kernel competitive learning (AKCL), which learns kernel competitive learning in a subspace via sampling. We provide solid theoretical analysis on why the proposed approximation modelling would work for kernel competitive learning, and furthermore, we show that the computational complexity of AKCL is largely reduced. Second, we propose a pseudo-parallelled approximate kernel competitive learning (PAKCL) based on a set-based kernel competitive learning strategy, which overcomes the obstacle of using parallel programming in kernel competitive learning and significantly accelerates the approximate kernel competitive learning for large scale clustering. The empirical evaluation on publicly available datasets shows that the proposed AKCL and PAKCL can perform comparably as KCL, with a large reduction on computational cost. Also, the proposed methods achieve more effective clustering performance in terms of clustering precision against related approximate clustering approaches. Copyright © 2014 Elsevier Ltd. All rights reserved.

  3. Motion Learning Based on Bayesian Program Learning

    Directory of Open Access Journals (Sweden)

    Cheng Meng-Zhen

    2017-01-01

    Full Text Available The concept of virtual human has been highly anticipated since the 1980s. By using computer technology, Human motion simulation could generate authentic visual effect, which could cheat human eyes visually. Bayesian Program Learning train one or few motion data, generate new motion data by decomposing and combining. And the generated motion will be more realistic and natural than the traditional one.In this paper, Motion learning based on Bayesian program learning allows us to quickly generate new motion data, reduce workload, improve work efficiency, reduce the cost of motion capture, and improve the reusability of data.

  4. Blended Learning or E-learning?

    OpenAIRE

    Tayebinik, Maryam; Puteh, Marlia

    2013-01-01

    ICT or Information and Communication Technology has pervaded the fields of education.In recent years the term e-learning has emerged as a result of the integration of ICT in the education fields. Following the application this technology into teaching, some pitfalls have been identified and this have led to the Blended learning phenomenon.However the preference on this new method has been debated quite extensively.The aim of this paper is to investigate the advantages of blended learning over...

  5. Evaluation and Policy Learning

    DEFF Research Database (Denmark)

    Borrás, Susana; Højlund, Steven

    2015-01-01

    This article examines how evaluation induces policy learning – a question largely neglected by the scholarly literature on evaluation and policy learning. Following a learner's perspective, the article attempts to ascertain who the learners are, and what, and how, learners actually learn from...... evaluations. In so doing, it focuses on what different types of learners actually learn within the context of the evaluation framework (the set of administrative structures defining the evaluation goals and process). Taking the empirical case of three EU programme evaluations, the patterns of policy learning...... emanating from them are examined. The findings are that only two types of actors involved in the evaluation are actually learning (programme units and external evaluators), that learners learn different things (programme overview, small-scale programme adjustments, policy change and evaluation methods...

  6. Semantic Learning Service Personalized

    Directory of Open Access Journals (Sweden)

    Yibo Chen

    2012-02-01

    Full Text Available To provide users with more suitable and personalized service, personalization is widely used in various fields. Current e-Learning systems search for learning resources using information search technology, based on the keywords that selected or inputted by the user. Due to lack of semantic analysis for keywords and exploring the user contexts, the system cannot provide a good learning experiment. In this paper, we defined the concept and characteristic of the personalized learning service, and proposed a semantic learning service personalized framework. Moreover, we made full use of semantic technology, using ontologies to represent the learning contents and user profile, mining and utilizing the friendship and membership of the social relationship to construct the user social relationship profile, and improved the collaboration filtering algorithm to recommend personalized learning resources for users. The results of the empirical evaluation show that the approach is effectiveness in augmenting recommendation.

  7. Infant Statistical Learning

    Science.gov (United States)

    Saffran, Jenny R.; Kirkham, Natasha Z.

    2017-01-01

    Perception involves making sense of a dynamic, multimodal environment. In the absence of mechanisms capable of exploiting the statistical patterns in the natural world, infants would face an insurmountable computational problem. Infant statistical learning mechanisms facilitate the detection of structure. These abilities allow the infant to compute across elements in their environmental input, extracting patterns for further processing and subsequent learning. In this selective review, we summarize findings that show that statistical learning is both a broad and flexible mechanism (supporting learning from different modalities across many different content areas) and input specific (shifting computations depending on the type of input and goal of learning). We suggest that statistical learning not only provides a framework for studying language development and object knowledge in constrained laboratory settings, but also allows researchers to tackle real-world problems, such as multilingualism, the role of ever-changing learning environments, and differential developmental trajectories. PMID:28793812

  8. Exploitative Learning by Exporting

    DEFF Research Database (Denmark)

    Golovko, Elena; Lopes Bento, Cindy; Sofka, Wolfgang

    Decisions on entering foreign markets are among the most challenging but also potentially rewarding strategy choices managers can make. In this study, we examine the effect of export entry on the firm investment decisions in two activities associated with learning about new technologies...... and learning about new markets ? R&D investments and marketing investments, in search of novel insights into the content and process underlying learning by exporting. We draw from organizational learning theory for predicting changes in both R&D and marketing investment patterns that accompany firm entry......, it is predominantly the marketing-related investment decisions associated with starting to export that lead to increases in firm productivity. We conclude that learning-by-exporting might be more properly characterized as ?learning about and exploiting new markets? rather than ?learning about new technologies...

  9. Learning as Negotiating Identities

    DEFF Research Database (Denmark)

    Jørgensen, Kenneth Mølbjerg; Keller, Hanne Dauer

    The paper explores the contribution of Communities of Practice (COP) to Human Resource Development (HRD). Learning as negotiating identities captures the contribution of COP to HRD. In COP the development of practice happens through negotiation of meaning. The learning process also involves modes...... of belonging constitutive of our identities. We suggest that COP makes a significant contribution by linking learning and identification. This means that learning becomes much less instrumental and much more linked to fundamental questions of being. We argue that the COP-framework links learning with the issue...... of time - caught in the notion of trajectories of learning - that integrate past, present and future. Working with the learners' notion of time is significant because it is here that new learning possibilities become visible and meaningful for individuals. Further, we argue that the concept of identity...

  10. Lessons learned bulletin

    International Nuclear Information System (INIS)

    1994-05-01

    During the past four years, the Department of Energy -- Savannah River Operations Office and the Westinghouse Savannah River Company (WSRC) Environmental Restoration (ER) Program completed various activities ranging from waste site investigations to closure and post closure projects. Critiques for lessons learned regarding project activities are performed at the completion of each project milestone, and this critique interval allows for frequent recognition of lessons learned. In addition to project related lessons learned, ER also performs lessons learned critiques. T'he Savannah River Site (SRS) also obtains lessons learned information from general industry, commercial nuclear industry, naval nuclear programs, and other DOE sites within the complex. Procedures are approved to administer the lessons learned program, and a database is available to catalog applicable lessons learned regarding environmental remediation, restoration, and administrative activities. ER will continue to use this database as a source of information available to SRS personnel

  11. Learning Methods for Dynamic Topic Modeling in Automated Behavior Analysis.

    Science.gov (United States)

    Isupova, Olga; Kuzin, Danil; Mihaylova, Lyudmila

    2017-09-27

    Semisupervised and unsupervised systems provide operators with invaluable support and can tremendously reduce the operators' load. In the light of the necessity to process large volumes of video data and provide autonomous decisions, this paper proposes new learning algorithms for activity analysis in video. The activities and behaviors are described by a dynamic topic model. Two novel learning algorithms based on the expectation maximization approach and variational Bayes inference are proposed. Theoretical derivations of the posterior estimates of model parameters are given. The designed learning algorithms are compared with the Gibbs sampling inference scheme introduced earlier in the literature. A detailed comparison of the learning algorithms is presented on real video data. We also propose an anomaly localization procedure, elegantly embedded in the topic modeling framework. It is shown that the developed learning algorithms can achieve 95% success rate. The proposed framework can be applied to a number of areas, including transportation systems, security, and surveillance.

  12. Is mobile learning a substitute for electronic learning?

    OpenAIRE

    Sitthiworachart, Jirarat; Joy, Mike

    2008-01-01

    Mobile learning is widely regarded as the next generation of learning technologies, and refers to the use of mobile devices in education to enhance learning activities. The increasing use of mobile devices has encouraged research into the capabilities of mobile learning systems. Many questions arise about mobile learning, such as whether mobile learning can be a substitute for electronic learning, what the potential benefits and problems of utilizing mobile devices in education are, and what ...

  13. Emergent learning and learning ecologies in Web 2.0

    OpenAIRE

    Williams, Roy; Karousou, Regina; Mackness, J.

    2011-01-01

    This paper describes emergent learning and situates it within learning networks and systems and the broader learning ecology of Web 2.0. It describes the nature of emergence and emergent learning and the conditions that enable emergent, self-organised learning to occur and to flourish. Specifically, it explores whether emergent learning can be validated and self-correcting and whether it is possible to link or integrate emergent and prescribed learning. It draws on complexity theory, commu...

  14. Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines

    Science.gov (United States)

    Neftci, Emre O.; Pedroni, Bruno U.; Joshi, Siddharth; Al-Shedivat, Maruan; Cauwenberghs, Gert

    2016-01-01

    Recent studies have shown that synaptic unreliability is a robust and sufficient mechanism for inducing the stochasticity observed in cortex. Here, we introduce Synaptic Sampling Machines (S2Ms), a class of neural network models that uses synaptic stochasticity as a means to Monte Carlo sampling and unsupervised learning. Similar to the original formulation of Boltzmann machines, these models can be viewed as a stochastic counterpart of Hopfield networks, but where stochasticity is induced by a random mask over the connections. Synaptic stochasticity plays the dual role of an efficient mechanism for sampling, and a regularizer during learning akin to DropConnect. A local synaptic plasticity rule implementing an event-driven form of contrastive divergence enables the learning of generative models in an on-line fashion. S2Ms perform equally well using discrete-timed artificial units (as in Hopfield networks) or continuous-timed leaky integrate and fire neurons. The learned representations are remarkably sparse and robust to reductions in bit precision and synapse pruning: removal of more than 75% of the weakest connections followed by cursory re-learning causes a negligible performance loss on benchmark classification tasks. The spiking neuron-based S2Ms outperform existing spike-based unsupervised learners, while potentially offering substantial advantages in terms of power and complexity, and are thus promising models for on-line learning in brain-inspired hardware. PMID:27445650

  15. Workplaces as Transformative Learning Spaces

    DEFF Research Database (Denmark)

    Maslo, Elina

    2010-01-01

    some other examples on “successful learning” from the formal, informal and non-formal learning environments, trying to prove those criteria. This presentation provides a view on to new examples on transformative learning spaces we discovered doing research on Workplace Learning in Latvia as a part......Abstract to the Vietnam Forum on Lifelong Learning: Building a Learning Society Hanoi, 7-8 December 2010 Network 2: Competence development as Workplace Learning Title of proposal: Workplaces as Transformative Learning Spaces Author: Elina Maslo, dr. paed., University of Latvia, elina@latnet.lv Key...... words: learning, lifelong learning, adult learning, workplace learning, transformative learning spaces During many years of research on lifelong foreign language learning with very different groups of learners, we found some criteria, which make learning process successful. Since then we tried to find...

  16. Flexible learning intinerary vs. linear learning itinerary

    OpenAIRE

    Martín San José, Juan Fernando; Juan Lizandra, María Carmen; Gil Gómez, Jose Antonio; Rando, Noemí

    2014-01-01

    The latest video game and entertainment technology and other technologies are facilitating the development of new and powerful e-Learning systems. In this paper, we present a computer-based game for learning about five historical ages. The objective of the game is to reinforce the events that mark the transition from one historical age to another and the order of the historical ages. Our game incorporates natural human-computer interaction based on video game technology, Frontal Projection, a...

  17. LEARNING HOW TO LEARN A LANGUAGE

    CERN Multimedia

    Language Training; Tel. 73127; Andrée Fontbonne; Tel. 72844

    2001-01-01

    This bilingual seminar is for anyone who would like to develop learning strategies and skills for learning a foreign language. Languages: French and English. Length: 3 days, 7 hours per day. Dates: 7, 8, 9 March 2001. Price: 462 CHF per person (for a group of 8 people). If you are interested, please enrol through our Web pages: http://training.web.cern.ch/Training/LANG/lang0_F.html

  18. LEARNING HOW TO LEARN A LANGUAGE

    CERN Multimedia

    Moniek Laurent

    2002-01-01

    This bilingual seminar is for anyone who would like to develop learning strategies and skills for learning a foreign language. Languages: French and English. Length: 3 days, 7 hours per day. Dates: 4, 5, 6 March 2002. Price: 460 CHF per person (for a group of 8 people). If you are interested, please enrol through our Web pages: http://cern.ch/Training   Language Training Moniek Laurent Tel. 78582 moniek.laurent@cern.ch

  19. LEARNING HOW TO LEARN A LANGUAGE

    CERN Multimedia

    Formation en Langues; Andrée Fontbonne - Tél. 72844; Language Training; Françoise Benz - Tel. 73127; Andrée Fontbonne - Tel. 72844

    2000-01-01

    This bilingual seminar is for anyone who would like to develop learning strategies and skills for learning a foreign language. It is particularly recommended for those wishing to sign up for a 3-month self-study session in the Resource Centre. Languages: French and English. Length: 5 hours a day for one week. Dates: 27 November to December 2000. Price: 490 CHF per person (for a group of 8 people). If you are interested, please enrol through our Web pages.

  20. Learning to practice: Practicing to learn

    OpenAIRE

    McBride, F.

    2005-01-01

    There is clearly a lack of consensus regarding the terminology used to describe the APStraciJ eXp 0jtatjon of knowledge in an organisational context. The theory of knowledge exploitation is bound up in various concepts, the most familiar being Organisational Learning, Knowledge Management and the Learning Organisation. This report is an enquiry into the applicability of these concepts to the design led architectural practice. Implicit within this study is a suggestion that the firm can be suc...

  1. CULTURAL VARIATIONS IN LEARNING AND LEARNING STYLES

    Directory of Open Access Journals (Sweden)

    Pegah OMIDVAR,, Putra University, MALAYSIA

    2012-08-01

    Full Text Available The need for cross-cultural understanding of the relationship between culture and learning style is becoming increasingly important because of the changing cultural mix of classrooms and society at large. The research done regarding the two variables is mostly quantitative. This review summarizes results of the existing research on cultural variations in learning styles. Limitations of the existing studies are discussed and some suggestion for future research is proposed.

  2. Learning from neural control.

    Science.gov (United States)

    Wang, Cong; Hill, David J

    2006-01-01

    One of the amazing successes of biological systems is their ability to "learn by doing" and so adapt to their environment. In this paper, first, a deterministic learning mechanism is presented, by which an appropriately designed adaptive neural controller is capable of learning closed-loop system dynamics during tracking control to a periodic reference orbit. Among various neural network (NN) architectures, the localized radial basis function (RBF) network is employed. A property of persistence of excitation (PE) for RBF networks is established, and a partial PE condition of closed-loop signals, i.e., the PE condition of a regression subvector constructed out of the RBFs along a periodic state trajectory, is proven to be satisfied. Accurate NN approximation for closed-loop system dynamics is achieved in a local region along the periodic state trajectory, and a learning ability is implemented during a closed-loop feedback control process. Second, based on the deterministic learning mechanism, a neural learning control scheme is proposed which can effectively recall and reuse the learned knowledge to achieve closed-loop stability and improved control performance. The significance of this paper is that the presented deterministic learning mechanism and the neural learning control scheme provide elementary components toward the development of a biologically-plausible learning and control methodology. Simulation studies are included to demonstrate the effectiveness of the approach.

  3. Theoretical Foundations of Active Learning

    Science.gov (United States)

    2009-05-01

    I study the informational complexity of active learning in a statistical learning theory framework. Specifically, I derive bounds on the rates of...convergence achievable by active learning , under various noise models and under general conditions on the hypothesis class. I also study the theoretical...advantages of active learning over passive learning, and develop procedures for transforming passive learning algorithms into active learning algorithms

  4. The Army Learning Organisation Workshop

    Science.gov (United States)

    2013-06-01

    learning • Sharing information • Learning resulting in purposeful action • Creating environments that promote learning • Technology and resources...individual and collective learning • Exploiting and investing in technology to facilitate learning (i.e. blended and E- learning ) • Lifelong or...opportunities provided by training and education programs. More significantly, participants noted the multi-layered nature of informal and formal learning

  5. Featurized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic Inference

    OpenAIRE

    Bao, Ruying; Liang, Sihang; Wang, Qingcan

    2018-01-01

    Deep neural networks have been demonstrated to be vulnerable to adversarial attacks, where small perturbations are intentionally added to the original inputs to fool the classifier. In this paper, we propose a defense method, Featurized Bidirectional Generative Adversarial Networks (FBGAN), to capture the semantic features of the input and filter the non-semantic perturbation. FBGAN is pre-trained on the clean dataset in an unsupervised manner, adversarially learning a bidirectional mapping b...

  6. Risk assessment of atmospheric emissions using machine learning

    OpenAIRE

    Cervone, G.; Franzese, P.; Ezber, Y.; Boybeyi, Z.

    2008-01-01

    Supervised and unsupervised machine learning algorithms are used to perform statistical and logical analysis of several transport and dispersion model runs which simulate emissions from a fixed source under different atmospheric conditions.

    First, a clustering algorithm is used to automatically group the results of different transport and dispersion simulations according to specific cloud characteristics. Then, a symbolic classification algorithm is employed to find compl...

  7. Active Learning Through Discussion in E-Learning

    OpenAIRE

    Daru Wahyuningsih

    2016-01-01

    Active learning is generally made by a lecturer in learning face to face. In the face to face learning, lecturer can implement a variety of teaching methods to make students actively involved in learning. This is different from learning that is actuating in e-learning. The main characteristic of e-learning is learning that can take place anytime and anywhere. Special strategies are needed so that lecturer can make students play an active role in the course of e-learning. Research in order to ...

  8. Accuracy of latent-variable estimation in Bayesian semi-supervised learning.

    Science.gov (United States)

    Yamazaki, Keisuke

    2015-09-01

    Hierarchical probabilistic models, such as Gaussian mixture models, are widely used for unsupervised learning tasks. These models consist of observable and latent variables, which represent the observable data and the underlying data-generation process, respectively. Unsupervised learning tasks, such as cluster analysis, are regarded as estimations of latent variables based on the observable ones. The estimation of latent variables in semi-supervised learning, where some labels are observed, will be more precise than that in unsupervised, and one of the concerns is to clarify the effect of the labeled data. However, there has not been sufficient theoretical analysis of the accuracy of the estimation of latent variables. In a previous study, a distribution-based error function was formulated, and its asymptotic form was calculated for unsupervised learning with generative models. It has been shown that, for the estimation of latent variables, the Bayes method is more accurate than the maximum-likelihood method. The present paper reveals the asymptotic forms of the error function in Bayesian semi-supervised learning for both discriminative and generative models. The results show that the generative model, which uses all of the given data, performs better when the model is well specified. Copyright © 2015 Elsevier Ltd. All rights reserved.

  9. Zero Learning: Case explorations of barriers to organizational learning

    DEFF Research Database (Denmark)

    Jørgensen, Frances; S., Jacob

    2003-01-01

    that the existence of learning barriers may not only inhibit on-going learning process, but also lead to a negative cycle of non-learning in the organization. The implications of a "zero learning" cycle caused by learning barriers are discussed and insights are provided as to how barriers may be resolved so...

  10. Seamless Language Learning: Second Language Learning with Social Media

    Science.gov (United States)

    Wong, Lung-Hsiang; Chai, Ching Sing; Aw, Guat Poh

    2017-01-01

    This conceptual paper describes a language learning model that applies social media to foster contextualized and connected language learning in communities. The model emphasizes weaving together different forms of language learning activities that take place in different learning contexts to achieve seamless language learning. it promotes social…

  11. Learning "While" Working: Success Stories on Workplace Learning in Europe

    Science.gov (United States)

    Lardinois, Rocio

    2011-01-01

    Cedefop's report "Learning while working: success stories on workplace learning in Europe" presents an overview of key trends in adult learning in the workplace. It takes stock of previous research carried out by Cedefop between 2003 and 2010 on key topics for adult learning: governance and the learning regions; social partner roles in…

  12. Can Social Learning Increase Learning Speed, Performance or Both?

    NARCIS (Netherlands)

    Heinerman, J.V.; Stork, J.; Rebolledo Coy, M.A.; Hubert, J.G.; Eiben, A.E.; Bartz-Beielstein, Thomas; Haasdijk, Evert

    2017-01-01

    Social learning enables multiple robots to share learned experiences while completing a task. The literature offers contradicting examples of its benefits; robots trained with social learning reach a higher performance, an increased learning speed, or both, compared to their individual learning

  13. Toward a Social Approach to Learning in Community Service Learning

    Science.gov (United States)

    Cooks, Leda; Scharrer, Erica; Paredes, Mari Castaneda

    2004-01-01

    The authors describe a social approach to learning in community service learning that extends the contributions of three theoretical bodies of scholarship on learning: social constructionism, critical pedagogy, and community service learning. Building on the assumptions about learning described in each of these areas, engagement, identity, and…

  14. Deep learning: Using machine learning to study biological vision

    OpenAIRE

    Majaj, Najib; Pelli, Denis

    2017-01-01

    Today most vision-science presentations mention machine learning. Many neuroscientists use machine learning to decode neural responses. Many perception scientists try to understand recognition by living organisms. To them, machine learning offers a reference of attainable performance based on learned stimuli. This brief overview of the use of machine learning in biological vision touches on its strengths, weaknesses, milestones, controversies, and current directions.

  15. 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.

  16. Blended learning in anatomy

    DEFF Research Database (Denmark)

    Østergaard, Gert Værge; Brogner, Heidi Marie

    behind DBR is that new knowledge is generated through processes that simultaneously develop, test and improve a design, in this case, an educational design (1) The main principles used in the project is blended learning and flipped learning (2). …"I definitely learn best in practice, but the theory...... in working with the assignments in the classroom."... External assesor, observer and interviewer Based on the different evaluations, the conclusion are that the blended learning approach combined with the ‘flipped classroom’ is a very good way to learn and apply the anatomy, both for the students......The aim of the project was to bridge the gap between theory and practice by working more collaboratively, both peer-to-peer and between student and lecturer. Furthermore the aim was to create active learning environments. The methodology of the project is Design-Based Research (DBR). The idea...

  17. Cultural dimensions of learning

    Science.gov (United States)

    Eyford, Glen A.

    1990-06-01

    How, what, when and where we learn is frequently discussed, as are content versus process, or right brain versus left brain learning. What is usually missing is the cultural dimension. This is not an easy concept to define, but various aspects can be identified. The World Decade for Cultural Development emphasizes the need for a counterbalance to a quantitative, economic approach. In the last century poets also warned against brutalizing materialism, and Sorokin and others have described culture more recently in terms of cohesive basic values expressed through aesthetics and institutions. Bloom's taxonomy incorporates the category of affective learning, which internalizes values. If cultural learning goes beyond knowledge acquisition, perhaps the surest way of understanding the cultural dimension of learning is to examine the aesthetic experience. This can use myths, metaphors and symbols, and to teach and learn by using these can help to unlock the human potential for vision and creativity.

  18. Learning through reactions

    DEFF Research Database (Denmark)

    Hasse, Cathrine

    2007-01-01

    Universities can from the student?s point of view be seen as places of learning an explicit curriculum of a particular discipline. From a fieldwork among physicist students at the Niels Bohr Institute in Denmark, I argue that the learning of cultural code-curricula in higher educational...... institutions designate in ambiguous ways. I argue claim that students also have to learn institutional cultural codes, which are not the explicit curricula presented in textbooks, but a socially designated cultural code-curricula learned through everyday interactions at the university institutes. I further...... argue that this code-curriculum is learned through what I shall term indefinite learning processes, which are mainly pre-discursive to the newcomer...

  19. Cultural Learning Redux.

    Science.gov (United States)

    Tomasello, Michael

    2016-05-01

    M. Tomasello, A. Kruger, and H. Ratner (1993) proposed a theory of cultural learning comprising imitative learning, instructed learning, and collaborative learning. Empirical and theoretical advances in the past 20 years suggest modifications to the theory; for example, children do not just imitate but overimitate in order to identify and affiliate with others in their cultural group, children learn from pedagogy not just episodic facts but the generic structure of their cultural worlds, and children collaboratively co-construct with those in their culture normative rules for doing things. In all, human children do not just culturally learn useful instrumental activities and information, they conform to the normative expectations of the cultural group and even contribute themselves to the creation of such normative expectations. © 2016 The Author. Child Development © 2016 Society for Research in Child Development, Inc.

  20. Problem Based Learning

    DEFF Research Database (Denmark)

    de Graaff, Erik; Guerra, Aida

    , the key principles remain the same everywhere. Graaff & Kolmos (2003) identify the main PBL principles as follows: 1. Problem orientation 2. Project organization through teams or group work 3. Participant-directed 4. Experiental learning 5. Activity-based learning 6. Interdisciplinary learning and 7...... model and in general problem based and project based learning. We apply the principle of teach as you preach. The poster aims to outline the visitors’ workshop programme showing the results of some recent evaluations.......Problem-Based Learning (PBL) is an innovative method to organize the learning process in such a way that the students actively engage in finding answers by themselves. During the past 40 years PBL has evolved and diversified resulting in a multitude in variations in models and practices. However...

  1. Deep learning with Python

    CERN Document Server

    Chollet, Francois

    2018-01-01

    DESCRIPTION Deep learning is applicable to a widening range of artificial intelligence problems, such as image classification, speech recognition, text classification, question answering, text-to-speech, and optical character recognition. Deep Learning with Python is structured around a series of practical code examples that illustrate each new concept introduced and demonstrate best practices. By the time you reach the end of this book, you will have become a Keras expert and will be able to apply deep learning in your own projects. KEY FEATURES • Practical code examples • In-depth introduction to Keras • Teaches the difference between Deep Learning and AI ABOUT THE TECHNOLOGY Deep learning is the technology behind photo tagging systems at Facebook and Google, self-driving cars, speech recognition systems on your smartphone, and much more. AUTHOR BIO Francois Chollet is the author of Keras, one of the most widely used libraries for deep learning in Python. He has been working with deep neural ...

  2. Pattern recognition & machine learning

    CERN Document Server

    Anzai, Y

    1992-01-01

    This is the first text to provide a unified and self-contained introduction to visual pattern recognition and machine learning. It is useful as a general introduction to artifical intelligence and knowledge engineering, and no previous knowledge of pattern recognition or machine learning is necessary. Basic for various pattern recognition and machine learning methods. Translated from Japanese, the book also features chapter exercises, keywords, and summaries.

  3. Formalized Informal Learning

    DEFF Research Database (Denmark)

    Levinsen, Karin Tweddell; Sørensen, Birgitte Holm

    2013-01-01

    are examined and the relation between network society competences, learners’ informal learning strategies and ICT in formalized school settings over time is studied. The authors find that aspects of ICT like multimodality, intuitive interaction design and instant feedback invites an informal bricoleur approach....... When integrated into certain designs for teaching and learning, this allows for Formalized Informal Learning and support is found for network society competences building....

  4. Deep learning relevance

    DEFF Research Database (Denmark)

    Lioma, Christina; Larsen, Birger; Petersen, Casper

    2016-01-01

    train a Recurrent Neural Network (RNN) on existing relevant information to that query. We then use the RNN to "deep learn" a single, synthetic, and we assume, relevant document for that query. We design a crowdsourcing experiment to assess how relevant the "deep learned" document is, compared...... to existing relevant documents. Users are shown a query and four wordclouds (of three existing relevant documents and our deep learned synthetic document). The synthetic document is ranked on average most relevant of all....

  5. Professional Learning and Collaboration

    OpenAIRE

    Greer, Janet Agnes

    2012-01-01

    The American education system must utilize collaboration to meet the challenges and demands our culture poses for schools. Deeply rooted processes and structures favor teaching and learning in isolation and hinder the shift to a more collaborative paradigm. Professional learning communities (PLCs) support continuous teacher learning, improved efficacy, and program implementation. The PLC provides the framework for the development and enhancement of teacher collaboration and teacher collaborat...

  6. Introduction to machine learning

    OpenAIRE

    Baştanlar, Yalın; Özuysal, Mustafa

    2014-01-01

    The machine learning field, which can be briefly defined as enabling computers make successful predictions using past experiences, has exhibited an impressive development recently with the help of the rapid increase in the storage capacity and processing power of computers. Together with many other disciplines, machine learning methods have been widely employed in bioinformatics. The difficulties and cost of biological analyses have led to the development of sophisticated machine learning app...

  7. Learning Mathematics through Programming

    DEFF Research Database (Denmark)

    Misfeldt, Morten; Ejsing-Duun, Stine

    2015-01-01

    In this paper we explore the potentials for learning mathematics through programming by a combination of theoretically derived potentials and cases of practical pedagogical work. We propose a model with three interdependent learning potentials as programming which can: (1) help reframe the students...... to mathematics is paramount. Analyzing two cases, we suggest a number of ways in which didactical attention to epistemic mediation can support learning mathematics....

  8. Learning Motivation and Achievements

    Institute of Scientific and Technical Information of China (English)

    冯泽野

    2016-01-01

    It is known to all that motivation is one of the most important elements in EFL learning.This study analyzes the type of English learning motivations and learning achievements within non-English majors’ students (Bilingual program in Highway School and Architecture) in Chang’an University, who has been considered English as the foreign language. This thesis intends to put forward certain strategies in promoting foreign language teaching.

  9. Learning Perforce SCM

    CERN Document Server

    Cowham, Robert

    2013-01-01

    Learning Perforce SCM is written in a friendly and practical style with a focus on getting you started with Perforce efficiently and effectively. The book provides plenty of examples and screenshots to guide you through the process of learning.""Learning Perforce SCM"" is for anyone who wants to know how to adeptly manage software development activities using Perforce. Experience with other version control tools is a plus but is not required.

  10. Budgeted Interactive Learning

    Science.gov (United States)

    2017-06-15

    2, and 3). The selection scheme is implemented and released as an open-source active learning package. They have studied theories for designing...We have studied theories for designing algorithms for interactive learning with batch-like feedback (for 1) and algorithms for online digestion of... necessity on pre-training. The new idea provides layer-wise cost estimation with auxiliary nodes, and is applicable to a wider range of deep learning

  11. Neuromorphic Deep Learning Machines

    OpenAIRE

    Neftci, E; Augustine, C; Paul, S; Detorakis, G

    2017-01-01

    An ongoing challenge in neuromorphic computing is to devise general and computationally efficient models of inference and learning which are compatible with the spatial and temporal constraints of the brain. One increasingly popular and successful approach is to take inspiration from inference and learning algorithms used in deep neural networks. However, the workhorse of deep learning, the gradient descent Back Propagation (BP) rule, often relies on the immediate availability of network-wide...

  12. Learning dialog act processing

    OpenAIRE

    Wermter, Stefan; Löchel, Matthias

    1996-01-01

    In this paper we describe a new approach for learning dialog act processing. In this approach we integrate a symbolic semantic segmentation parser with a learning dialog act network. In order to support the unforeseeable errors and variations of spoken language we have concentrated on robust data-driven learning. This approach already compares favorably with the statistical average plausibility method, produces a segmentation and dialog act assignment for all utterances in a robust manner,...

  13. Lifelong Open and Flexible Learning

    DEFF Research Database (Denmark)

    Bang, Jørgen

    2006-01-01

    and Flexible (LOF) learning embracing characteristics as: open learning, distance learning, e-learning, online learning, open accessibility, multimedia support, virtual mobility, learning communities, dual mode (earn & learn) approaches, and the like.In my presentation I will focus on the EADTU strategies...... for creating a synergy network in e-learning – eventually leading to a European Learning Space that supports virtual mobility of students, staff and courses, adds an e-dimension to the Bologa process and facilitates collaboration between universities and the corporate sector....

  14. Feature Inference Learning and Eyetracking

    Science.gov (United States)

    Rehder, Bob; Colner, Robert M.; Hoffman, Aaron B.

    2009-01-01

    Besides traditional supervised classification learning, people can learn categories by inferring the missing features of category members. It has been proposed that feature inference learning promotes learning a category's internal structure (e.g., its typical features and interfeature correlations) whereas classification promotes the learning of…

  15. Develop a Professional Learning Plan

    Science.gov (United States)

    Journal of Staff Development, 2013

    2013-01-01

    A professional learning plan establishes short-and long-term plans for professional learning and implementation of the learning. Such plans guide individuals, schools, districts, and states in coordinating learning experiences designed to achieve outcomes for educators and students. Professional learning plans focus on the program of educator…

  16. The Organization of Informal Learning

    Science.gov (United States)

    Rogoff, Barbara; Callanan, Maureen; Gutiérrez, Kris D.; Erickson, Frederick

    2016-01-01

    Informal learning is often treated as simply an alternative to formal, didactic instruction. This chapter discusses how the organization of informal learning differs across distinct settings but with important commonalities distinguishing informal learning from formal learning: Informal learning is nondidactic, is embedded in meaningful activity,…

  17. Readiness of Adults to Learn Using E-Learning, M-Learning and T-Learning Technologies

    Science.gov (United States)

    Vilkonis, Rytis; Bakanoviene, Tatjana; Turskiene, Sigita

    2013-01-01

    The article presents results of the empirical research revealing readiness of adults to participate in the lifelong learning process using e-learning, m-learning and t-learning technologies. The research has been carried out in the framework of the international project eBig3 aiming at development a new distance learning platform blending virtual…

  18. Holistic evaluations of learning materials

    DEFF Research Database (Denmark)

    Bundsgaard, Jeppe; Hansen, Thomas Illum

    2011-01-01

    The aim of this paper is to present a holistic framework for evaluating learning materials and designs for learning. A holistic evaluation of learning material comprises investigations of - the potential learning potential, i.e. the affordances and challenges of the learning material...

  19. Formative assessment and learning analytics

    NARCIS (Netherlands)

    Tempelaar, D.T.; Heck, A.; Cuypers, H.; van der Kooij, H.; van de Vrie, E.; Suthers, D.; Verbert, K.; Duval, E.; Ochoa, X.

    2013-01-01

    Learning analytics seeks to enhance the learning process through systematic measurements of learning related data, and informing learners and teachers of the results of these measurements, so as to support the control of the learning process. Learning analytics has various sources of information,

  20. Researching workplace learning

    DEFF Research Database (Denmark)

    Jørgensen, Christian Helms; Warring, Niels

    2007-01-01

    This article presents a theoretical and methodological framework for understanding and researching learning in the workplace. The workplace is viewed in a societal context and the learner is viewed as more than an employee in order to understand the learning process in relation to the learner......'s life history.Moreover we will explain the need to establish a 'double view' by examining learning in the workplace both as an objective and as a subjective reality. The article is mainly theoretical, but can also be of interest to practitioners who wish to understand learning in the workplace both...

  1. Recommender Systems for Learning

    CERN Document Server

    Manouselis, Nikos; Verbert, Katrien; Duval, Erik

    2013-01-01

    Technology enhanced learning (TEL) aims to design, develop and test sociotechnical innovations that will support and enhance learning practices of both individuals and organisations. It is therefore an application domain that generally covers technologies that support all forms of teaching and learning activities. Since information retrieval (in terms of searching for relevant learning resources to support teachers or learners) is a pivotal activity in TEL, the deployment of recommender systems has attracted increased interest. This brief attempts to provide an introduction to recommender systems for TEL settings, as well as to highlight their particularities compared to recommender systems for other application domains.

  2. Learning efficient correlated equilibria

    KAUST Repository

    Borowski, Holly P.; Marden, Jason R.; Shamma, Jeff S.

    2014-01-01

    The majority of distributed learning literature focuses on convergence to Nash equilibria. Correlated equilibria, on the other hand, can often characterize more efficient collective behavior than even the best Nash equilibrium. However, there are no existing distributed learning algorithms that converge to specific correlated equilibria. In this paper, we provide one such algorithm which guarantees that the agents' collective joint strategy will constitute an efficient correlated equilibrium with high probability. The key to attaining efficient correlated behavior through distributed learning involves incorporating a common random signal into the learning environment.

  3. Learning and Communicative Rationality

    DEFF Research Database (Denmark)

    Rasmussen, Palle

    The paper is an attempt to outline Habermas' contributions to a theory of learning. Such contributions are found in his work on individual learning and socialization, the constitution and reproduction of lifeworlds, the character of social evolution, the processes of public delibearation...... and democracy and the idea and role of universities. A "theory of learning" is not taken in a very formalised sense, rather the idea is to identify themes where Habermas' theoretical framework provide the opportunity for locating important aspects of learning in modern society....

  4. Strengths-based Learning

    DEFF Research Database (Denmark)

    Ledertoug, Mette Marie

    -being. The Ph.D.-project in Strength-based learning took place in a Danish school with 750 pupils age 6-16 and a similar school was functioning as a control group. The presentation will focus on both the aware-explore-apply processes and the practical implications for the schools involved, and on measurable......Strength-based learning - Children͛s Character Strengths as Means to their Learning Potential͛ is a Ph.D.-project aiming to create a strength-based mindset in school settings and at the same time introducing strength-based interventions as specific tools to improve both learning and well...

  5. The interprofessional learning experience

    DEFF Research Database (Denmark)

    Jakobsen, Flemming; Morcke, Anne Mette; Hansen, Torben Baek

    2017-01-01

    in a safe and challenging learning environment. The shift to the outpatient setting was strongly and practically supported by the management. This study indicates that student learning can be shifted to the outpatient clinic setting if there is supportive management and dedicated supervisors who establish...... a challenging yet safe interprofessional learning environment....... who worked in an interprofessional outpatient orthopaedic clinic from March 2015 to January 2016. The interviews were transcribed and analysed using systematic text condensation. The students’ self-reported learning experience in this outpatient clinic was characterised by direct patient contact...

  6. Perspectives on ontology learning

    CERN Document Server

    Lehmann, J

    2014-01-01

    Perspectives on Ontology Learning brings together researchers and practitioners from different communities − natural language processing, machine learning, and the semantic web − in order to give an interdisciplinary overview of recent advances in ontology learning.Starting with a comprehensive introduction to the theoretical foundations of ontology learning methods, the edited volume presents the state-of-the-start in automated knowledge acquisition and maintenance. It outlines future challenges in this area with a special focus on technologies suitable for pushing the boundaries beyond the c

  7. Learning efficient correlated equilibria

    KAUST Repository

    Borowski, Holly P.

    2014-12-15

    The majority of distributed learning literature focuses on convergence to Nash equilibria. Correlated equilibria, on the other hand, can often characterize more efficient collective behavior than even the best Nash equilibrium. However, there are no existing distributed learning algorithms that converge to specific correlated equilibria. In this paper, we provide one such algorithm which guarantees that the agents\\' collective joint strategy will constitute an efficient correlated equilibrium with high probability. The key to attaining efficient correlated behavior through distributed learning involves incorporating a common random signal into the learning environment.

  8. Editorial: Advanced learning technologies

    Directory of Open Access Journals (Sweden)

    Yu-Ju Lan

    2012-03-01

    Full Text Available Recent rapid development of advanced information technology brings high expectations of its potential to improvement and innovations in learning. This special issue is devoted to using some of the emerging technologies issues related to the topic of education and knowledge sharing, involving several cutting edge research outcomes from recent advancement of learning technologies. Advanced learning technologies are the composition of various related technologies and concepts such as mobile technologies and social media towards learner centered learning. This editorial note provides an overview of relevant issues discussed in this special issue.

  9. Machine Learning for Hackers

    CERN Document Server

    Conway, Drew

    2012-01-01

    If you're an experienced programmer interested in crunching data, this book will get you started with machine learning-a toolkit of algorithms that enables computers to train themselves to automate useful tasks. Authors Drew Conway and John Myles White help you understand machine learning and statistics tools through a series of hands-on case studies, instead of a traditional math-heavy presentation. Each chapter focuses on a specific problem in machine learning, such as classification, prediction, optimization, and recommendation. Using the R programming language, you'll learn how to analyz

  10. Learning in Ressource Mangement

    DEFF Research Database (Denmark)

    Hoffmann, Birgitte; Agger, Annika

    2005-01-01

    This paper explores the roles of NGOs as intermediaries in societal learning processes. The key question is how NGOs facilitate learning in the water sector, and the paper explores the notion of critical friends to grasp their dual position as both partner in the development and critical...... strategies and finally in relation to changes of the water management discourse. Developing the notion ‘critical friend’ the paper discusses how the NGO facilitates learning processes. Traditional approaches to learning are often based on the ‘petrol station pedagogy’ in which knowledge figuratively ‘are...

  11. Georgia - Improved Learning Environment

    Data.gov (United States)

    Millennium Challenge Corporation — The school rehabilitation activity seeks to decrease student and teacher absenteeism, increase students’ time on task, and, ultimately, improve learning and labor...

  12. What is Social Learning?

    Directory of Open Access Journals (Sweden)

    Mark S. Reed

    2010-12-01

    between individual and wider social learning. Many unsubstantiated claims for social learning exist, and there is frequently confusion between the concept itself and its potential outcomes. This lack of conceptual clarity has limited our capacity to assess whether social learning has occurred, and if so, what kind of learning has taken place, to what extent, between whom, when, and how. This response attempts to provide greater clarity on the conceptual basis for social learning. We argue that to be considered social learning, a process must: (1 demonstrate that a change in understanding has taken place in the individuals involved; (2 demonstrate that this change goes beyond the individual and becomes situated within wider social units or communities of practice; and (3 occur through social interactions and processes between actors within a social network. A clearer picture of what we mean by social learning could enhance our ability to critically evaluate outcomes and better understand the processes through which social learning occurs. In this way, it may be possible to better facilitate the desired outcomes of social learning processes.

  13. Revisiting Boltzmann learning: parameter estimation in Markov random fields

    DEFF Research Database (Denmark)

    Hansen, Lars Kai; Andersen, Lars Nonboe; Kjems, Ulrik

    1996-01-01

    This article presents a generalization of the Boltzmann machine that allows us to use the learning rule for a much wider class of maximum likelihood and maximum a posteriori problems, including both supervised and unsupervised learning. Furthermore, the approach allows us to discuss regularization...... and generalization in the context of Boltzmann machines. We provide an illustrative example concerning parameter estimation in an inhomogeneous Markov field. The regularized adaptation produces a parameter set that closely resembles the “teacher” parameters, hence, will produce segmentations that closely reproduce...

  14. Advances in independent component analysis and learning machines

    CERN Document Server

    Bingham, Ella; Laaksonen, Jorma; Lampinen, Jouko

    2015-01-01

    In honour of Professor Erkki Oja, one of the pioneers of Independent Component Analysis (ICA), this book reviews key advances in the theory and application of ICA, as well as its influence on signal processing, pattern recognition, machine learning, and data mining. Examples of topics which have developed from the advances of ICA, which are covered in the book are: A unifying probabilistic model for PCA and ICA Optimization methods for matrix decompositions Insights into the FastICA algorithmUnsupervised deep learning Machine vision and image retrieval A review of developments in the t

  15. Learner Managed Learning: Managing To Learn or Learning To Manage?

    Science.gov (United States)

    Harrison, Roger

    2000-01-01

    In the discourse of learner self-management, learners must take responsibility for learning and are offered the possibility of individual autonomy and control. A critical perspective reveals that environmental constraints inhibit the success of technical-rational self-management techniques. An alternative view is the entrepreneurial self, a…

  16. Learning about Learning: Action Learning in Times of Organisational Change

    Science.gov (United States)

    Hill, Robyn

    2009-01-01

    This paper explores the conduct and outcomes of an action learning activity during a period of intense organisational change in a medium-sized vocational education and training organisation in Victoria, Australia. This organisation was the subject of significant change due to government-driven and statewide amalgamation, downsizing and sector…

  17. Organizational learning viewed from a social learning perspective

    DEFF Research Database (Denmark)

    Elkjær, Bente; Brandi, Ulrik

    2011-01-01

    This chapter reviews the literature on organizational learning through the lens of a social learning perspective. We start with an individual learning perspective, before moving on to a social learning perspective with a particular focus upon pragmatism. The literature review covers the following...... four issues: the content of learning, the process of learning, the relation between individual and organization, and the concept of organization. An important separator between individual and social learning perspectives is the different emphasis on learning as acquisition of skills and knowledge......, versus learning as encompassing development of identities and socialization to organizational work and life. A pragmatist social learning perspective emphasizes both learning as acquisition through experience and inquiry, and learning as development of identities and socialization through individuals...

  18. Learned-Helplessness Theory: Implications for Research in Learning Disabilities.

    Science.gov (United States)

    Canino, Frank J.

    1981-01-01

    The application of learned helplessness theory to achievement is discussed within the context of implications for research in learning disabilities. Finally, the similarities between helpless children and learning disabled students in terms of problems solving and attention are discussed. (Author)

  19. Challenges of Implementing Mobile Learning in Distance Learning ...

    African Journals Online (AJOL)

    Challenges of Implementing Mobile Learning in Distance Learning in Tanzania. ... A sample of 450 students were interviewed by using both questionnaire and ... the biggest advantage of M-learning technology- when used, is that it can be ...

  20. Involvement in Learning Revisited: Lessons We Have Learned.

    Science.gov (United States)

    Astin, Alexander W.

    1996-01-01

    Discusses interconnections between the following two national reports: (1) Involvement in Learning; and (2) The Student Learning Imperative. Reviews recent research on student development in order to demonstrate how student affairs professionals can use this information to enhance learning. (SNR)