Artificial Neural Networks - ICANN 2006

1. Front Matter

   PDF

2. Feature Selection and Dimension Reduction for Regression (Special Session)

   1. Dimensionality Reduction Based on ICA for Regression Problems

      • Nojun Kwak, Chunghoon Kim

      Pages 1-10

   2. A Functional Approach to Variable Selection in Spectrometric Problems

      • Fabrice Rossi, Damien François, Vincent Wertz, Michel Verleysen

      Pages 11-20

   3. The Bayes-Optimal Feature Extraction Procedure for Pattern Recognition Using Genetic Algorithm

      • Marek Kurzynski, Edward Puchala, Aleksander Rewak

      Pages 21-30

   4. Speeding Up the Wrapper Feature Subset Selection in Regression by Mutual Information Relevance and Redundancy Analysis

      • Gert Van Dijck, Marc M. Van Hulle

      Pages 31-40

   5. Effective Input Variable Selection for Function Approximation

      • L. J. Herrera, H. Pomares, I. Rojas, M. Verleysen, A. Guilén

      Pages 41-50

   6. Comparative Investigation on Dimension Reduction and Regression in Three Layer Feed-Forward Neural Network

      • Lei Shi, Lei Xu

      Pages 51-60

3. Learning Algorithms (I)

   1. On-Line Learning with Structural Adaptation in a Network of Spiking Neurons for Visual Pattern Recognition

      • Simei Gomes Wysoski, Lubica Benuskova, Nikola Kasabov

      Pages 61-70

   2. Learning Long Term Dependencies with Recurrent Neural Networks

      • Anton Maximilian Schäfer, Steffen Udluft, Hans Georg Zimmermann

      Pages 71-80

   3. Adaptive On-Line Neural Network Retraining for Real Life Multimodal Emotion Recognition

      • Spiros Ioannou, Loic Kessous, George Caridakis, Kostas Karpouzis, Vered Aharonson, Stefanos Kollias

      Pages 81-92

   4. Time Window Width Influence on Dynamic BPTT(h) Learning Algorithm Performances: Experimental Study

      • V. Scesa, P. Henaff, F. B. Ouezdou, F. Namoun

      Pages 93-102

   5. Framework for the Interactive Learning of Artificial Neural Networks

      • Matúš Užák, Rudolf Jakša

      Pages 103-112

   6. Analytic Equivalence of Bayes a Posteriori Distributions

      • Takeshi Matsuda, Sumio Watanabe

      Pages 113-121

4. Learning Algorithms (II)

   1. Neural Network Architecture Selection: Size Depends on Function Complexity

      • Iván Gómez, Leonardo Franco, José L. Subirats, José M. Jerez

      Pages 122-129

   2. Competitive Repetition-suppression (CoRe) Learning

      • Davide Bacciu, Antonina Starita

      Pages 130-139

   3. Real-Time Construction of Neural Networks

      • Kang Li, Jian Xun Peng, Minrui Fei

      Pages 140-149

   4. MaxMinOver Regression: A Simple Incremental Approach for Support Vector Function Approximation

      • Daniel Schneegaß, Kai Labusch, Thomas Martinetz

      Pages 150-158

   5. A Variational Formulation for the Multilayer Perceptron

      • Roberto Lopez, Eugenio Oñate

      Pages 159-168

5. Advances in Neural Network Learning Methods (Special Session)

   1. Natural Conjugate Gradient Training of Multilayer Perceptrons

      • Ana González, José R. Dorronsoro

      Pages 169-177

   2. Building Ensembles of Neural Networks with Class-Switching

      • Gonzalo Martínez-Muñoz, Aitor Sánchez-Martínez, Daniel Hernández-Lobato, Alberto Suárez

      Pages 178-187

This book includes the proceedings of the International Conference on Artificial Neural Networks (ICANN 2006) held on September 10-14, 2006 in Athens, Greece, with tutorials being presented on September 10, the main conference taking place during September 11-13 and accompanying workshops on perception, cognition and interaction held on September 14, 2006. The ICANN conference is organized annually by the European Neural Network Society in cooperation with the International Neural Network Society, the Japanese Neural Network Society and the IEEE Computational Intelligence Society. It is the premier European event covering all topics concerned with neural networks and related areas. The ICANN series of conferences was initiated in 1991 and soon became the major European gathering for experts in these fields. In 2006 the ICANN Conference was organized by the Intelligent Systems Laboratory and the Image, Video and Multimedia Systems Laboratory of the National Technical University of Athens in Athens, Greece. From 475 papers submitted to the conference, the International Program Committee selected, following a thorough peer-review process, 208 papers for publication and presentation to 21 regular and 10 special sessions. The quality of the papers received was in general very high; as a consequence, it was not possible to accept and include in the conference program many papers of good quality.

• Neuroscience
• algorithm
• algorithms
• bioinformatics
• complex system
• image processing
• learning
• machine learning
• multimedia
• organization
• robot
• robotics
• semantic web

• School of Electrical and Computer Engineering, Image, Video and Multimedia Systems Laboratory, National Technical University of Athens, Zographou, Greece

  Stefanos D. Kollias

• Department of Electrical and Computer Engineering, National Technical University of Athens, Zographou, Greece

  Andreas Stafylopatis

• Department of Informatics, Nicolaus Copernicus University, Toruń, Poland

  Włodzisław Duch

• Adaptive Informatics Research Centre, Helsinki University of Technology, HUT, Finland

  Erkki Oja

Policies and ethics