Sample records for NEURONALE NETZWERKE (neural networks)
from WorldWideScience.org

Sample records 1 - 20 shown. Select sample records:



3

Training neural networks with heterogeneous data

Drakopoulos, J. A.; Abdulkader, A.; International Neural Networks Society
2005-01-01

German National Library of Science and Technology (GetInfo) (German)

5

Time series forecasting by evolving artificial neural networks using “Shuffle”, cross-validation and ensembles

Peralta, Juan; Gutiérrez, Germán; Sanchis, Araceli

Accurate time series forecasting are important for several business, research, and application of engineering systems. Evolutionary Neural Networks are particularly appealing because of their ability to design, in an automatic way, a model (an Artificial Neural Network) for an unspecified nonlinear ...

DRIVER (German)

6

Time series forecasting by evolving artificial neural networks using genetic algorithms and differential evolution

Peralta, Juan; Li, Xiaodong; Gutiérrez, Germán; Sanchis, Araceli

Accurate time series forecasting are important for displaying the manner in which the past continues to affect the future and for planning our day to-day activities. In recent years, a large literature has evolved on the use of evolving artificial neural networks (EANNs) in many forecasting applicat...

DRIVER (German)

7

Time series forecasting by evolving artificial neural networks using genetic algorithms and differential evolution

Peralta, Juan; Li, Xiaodong; Gutiérrez, Germán; Sanchis, Araceli

Accurate time series forecasting are important for displaying the manner in which the past continues to affect the future and for planning our day to-day activities. In recent years, a large literature has evolved on the use of evolving artificial neural networks (EANNs) in many forecasting applicat...

DRIVER (German)

15

Studying the capacity of grammatical encoding to generate FNN architectures

Gutiérrez, Germán; García-Jiménez, Beatriz; Molina, José M.; Sanchis, Araceli

Many methods to codify Artificial Neural Networks have been developed to avoid the defects of direct encoding schema, improving the search into the solution’s space. A method to estimate how the search space is covered and how are the movements along search process applying genetic operators is need...

DRIVER (German)

16

Studying the capacity of cellular encoding to generate feedforward neural network topologies

Gutiérrez, Germán; Galván, Inés M.; Molina, José M.; Sanchis, Araceli

Proceeding of: IEEE International Joint Conference on Neural Networks, IJCNN 2004, Budapest, 25-29 July 2004 | Many methods to codify artificial neural networks have been developed to avoid the disadvantages of direct encoding schema, improving the search into the solution's space. A method to analy...

DRIVER (German)

17

Specialized ensemble of classifiers for traffic sign recognition

Sesmero, M. P.; Alonso-Weber, J. M.; Gutiérrez, Germán; Ledezma, Agapito; Sanchis, Araceli

Several complex problems have to be solved in order to build Advanced Driving Assistance Systems. Among them, an important problem is the detection and classification of traffic signs, which can appear at any position within a captured image. This paper describes a system that employs independent mo...

DRIVER (German)

19

Some neural networks compute, others don’t

Piccinini, G.; International Neural Networks Society; IEEE Computational Intelligence Society
2008-01-01

German National Library of Science and Technology (GetInfo) (German)

20

Shuffle design to improve time series forecasting accuracy

Peralta, Juan; Gutiérrez, Germán; Sanchis, Araceli

In this work new improvements from a previous approach of an Automatic Design of Artificial Neural Networks applied to forecast time series is tackled. The automatic process to design Artificial Neural Networks is carried out by a Genetic Algorithm. These improvements, in order to get an accurate fo...

DRIVER (German)

29

Proceedings of the International Workshop on Applications of Neural Networks to Telecommunications

International Workshop on Applications of Neural Networks to Telecommunications < 2, 1995, Stockholm>
1995-01-01

German National Library of Science and Technology (GetInfo) (German)

38

Non-Direct Encoding Method Based on Cellular Automata to Design Neural Network Architectures

Gutiérrez, Germán; Sanchis, Araceli; Isasi, Pedro; Molina, José M.; Galván, Inés M.

Architecture design is a fundamental step in the successful application of Feed forward Neural Networks. In most cases a large number of neural networks architectures suitable to solve a problem exist and the architecture design is, unfortunately, still a human expert’s job. It depends heavily on th...

DRIVER (German)

39

New Neural Network Methods for Forecasting Regional Employment: An Analysis of German Labour Markets

Patuelli, Roberto; Reggiani, Aura; Nijkamp, Peter; Blien, Uwe

In this paper, a set of neural network (NN) models is developed to compute short-term forecasts of regional employment patterns in Germany. NNs are modern statistical tools based on learning algorithms that are able to process large amounts of data. NNs are enjoying increasing interest in several fi...

DRIVER (German)

40

Neural networks in the framework of granular computing

Pedrycz, W.; Polish Neural Networks Council; IEEE Neural Networks Council
2000-01-01

German National Library of Science and Technology (GetInfo) (German)

41

Neural networks in financial engineering : proceedings of the Third International Conference on Neural Networks in the Capital Markets, London, England, 11 - 13 October 95

London Business School; California Institute of Technology < Pasadena, Calif.>; International Conference on Neural Networks in the Capital Markets < 3, 1995, London>
1996-01-01

German National Library of Science and Technology (GetInfo) (German)

42

Neural networks for signal processing II : proceedings of the 1992 IEEE-SP workshop, second in a series of workshops ; [held on August 31 - September 2 at Hotel Marienlyst, Helsingoer, Denmark]

Workshop on Neural Networks for Signal Processing < 2, 1992, Helsingør>; Signal Processing Society / Neural Networks Technical Committee; Danish Computational Neural Network Center < Lyngby-Tårbaek>
1992-01-01

German National Library of Science and Technology (GetInfo) (German)

43

Neural networks for signal processing II : proceedings of the 1992 IEEE-SP workshop, second in a series of workshops ; [held on August 31 - September 2 at Hotel Marienlyst, Helsingoer, Denmark]

Workshop on Neural Networks for Signal Processing < 2, 1992, Helsingør>; Signal Processing Society / Neural Networks Technical Committee; Danish Computational Neural Network Center < Lyngby-Tårbaek>
1992-01-01

German National Library of Science and Technology (GetInfo) (German)

49

Neural Networks Applied to Direct Marketing

Ter Heide, R. P.; Dutch Foundation for Neural Networks(SNN)
1995-01-01

German National Library of Science and Technology (GetInfo) (German)

56

Learning and adaptivity for connectionist models and neural networks: Proceedings Working Group "Connectionism", Magdeburg, Germany, September 29, 1999

Paaß, G.

This report contains the talks accepted for the meeting of the working group "connectionism" of the German Society of Computer Science (GI) on September 29th, 1999 in Magdeburg. It takes place in conjunction with the GI-Workshop-Days "Learning, Knowledge Discovery, and Adaptivity". The meeting is de...

DRIVER (German)

63

Generative capacities of cellular automata codification for evolution of NN codification

Gutiérrez, Germán; Galván, Inés M.; Sanchis, Araceli; Molina, José M.

Proceeding of: International Conference on Artificial Neural Networks. ICANN 2002, Madrid, Spain, August 28-30, 2002 | Automatic methods for designing artificial neural nets are desired to avoid the laborious and erratically human expert’s job. Evolutionary computation has been used as a search tech...

DRIVER (German)

67

Forecasting of Meteorologic Data by Artificial Neural Networks

Cigizoglu, K.; Polish Neural Networks Society; Technical University of Czestochowa
2003-01-01

German National Library of Science and Technology (GetInfo) (German)

68

First IEE International Conference on Artificial Neural Networks, 16-18 October 1989

International Conference on Artificial Neural Networks < Institution of Electrical Engineers, 1, 1989, London>; Institution of Electrical Engineers / Electronics Division
1989-01-01

German National Library of Science and Technology (GetInfo) (German)

70

Fault detection in discrete event based distributed systems by forecasting message sequences with neural networks

Langer, F.; Eilers, D.; Knorr, R.

In reliable systems fault detection is essential for ensuring the correct behavior. Todays automotive electronical systems consists of 30 to 80 electronic control units which provide up to 2.500 atomic functions. Because of the growing dependencies between the different functionality, very complex i...

DRIVER (German)

77

Evolutionary genetic algorithms in a constraint satisfaction problem: Puzzle Eternity II

Muñoz, Jorge; Gutiérrez, Germán; Sanchis, Araceli

This paper evaluates a genetic algorithm and a multiobjective evolutionary algorithm in a constraint satisfaction problem (CSP). The problem that has been chosen is the Eternity II puzzle (E2), an edge-matching puzzle. The objective is to analyze the results and the convergence of both algorithms in...

DRIVER (German)

78

Evolutionary cellular configurations for designing feed-forward neural networks architectures

Gutiérrez, Germán; Isasi, Pedro; Molina, José M.; Sanchis, Araceli; Galván, Inés M.

Proceeding of: 6th International Work-Conference on Artificial and Natural Neural Networks, IWANN 2001 Granada, Spain, June 13–15, 2001 | In the recent years, the interest to develop automatic methods to determine appropriate architectures of feed-forward neural networks has increased. Most of the m...

DRIVER (German)

79
85

Design of artificial neural networks based on genetic algorithms to forecast time series

Peralta, Juan; Gutiérrez, Germán; Sanchis, Araceli

In this work an initial approach to design Artificial Neural Networks to forecast time series is tackle, and the automatic process to design is carried out by a Genetic Algorithm. A key issue for these kinds of approaches is what information is included in the chromosome that represents an Artificia...

DRIVER (German)

86

Design of artificial neural networks based on genetic algorithms to forecast time series

Peralta, Juan; Gutiérrez, Germán; Sanchis, Araceli

In this work an initial approach to design Artificial Neural Networks to forecast time series is tackle, and the automatic process to design is carried out by a Genetic Algorithm. A key issue for these kinds of approaches is what information is included in the chromosome that represents an Artificia...

DRIVER (German)

93

Computation, Cognition and Neural Networks

Van der Velde, F.; Dutch Foundation for Neural Networks (SNN)
1995-01-01

German National Library of Science and Technology (GetInfo) (German)

95

COGANN-92 : International Workshop on Combinations of Genetic Algorithms and Neural Networks, June 6, 1992, Baltimore, Maryland ; [proceedings]

International Workshop on Combinations of Genetic Algorithms & Neural Networks < 1992, Baltimore, Md.>; Institute of Electrical and Electronics Engineers / Neural Networks Council; International Society for Genetic Algorithms
1992-01-01

German National Library of Science and Technology (GetInfo) (German)

99

Artificial neural networks in pattern recognition : Second IAPR Workshop, ANNPR 2006, Ulm, Germany, August 31 - September 2, 2006 ; proceedings

Workshop on Artificial Neural Networks in Pattern Recognition < 2, 2006, Ulm>; International Association for Pattern Recognition / Technical Committee on Neural Networks and Computational Intelligence
2006-01-01

German National Library of Science and Technology (GetInfo) (German)

109

ADANN: Automatic Design of Artificial Neural Networks

Peralta, Juan; Gutiérrez, Germán; Sanchis, Araceli

In this work an improvement of an initial approach to design Artificial Neural Networks to forecast Time Series is tackled, and the automatic process to design Artificial Neural Networks is carried out by a Genetic Algorithm. A key issue for these kinds of approaches is what information is included ...

DRIVER (German)

118

Ernst, Bernhard

Die Maßnahmen zur Förderung der Windenergie in Deutschland haben wichtige Anstöße zur technologischen Weiterentwicklung geliefert und die Grundlagen für den enormen Anlagenzubau geschaffen. Die installierte Windleistung hat heute eine beachtliche Größenordnung erreicht und ein weiteres Wachstum in ä...

DRIVER (German)

119

1993 the First New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, November 24 - 26, 1993, Dunedin, New Zealand : proceedings

International Two-Stream Conference on Artificial Neural Networks and Expert Systems < 1, 1993, Dunedin, New Zealand>; New Zealand Computer Society
1993-01-01

German National Library of Science and Technology (GetInfo) (German)