Artificial Neural Networks - ICANN 2008

1. Front Matter

   PDF

2. Mathematical Theory of Neurocomputing

   1. Dimension Reduction for Mixtures of Exponential Families

      • Shotaro Akaho

      Pages 1-10

   2. Several Enhancements to Hermite-Based Approximation of One-Variable Functions

      • Bartlomiej Beliczynski, Bernardete Ribeiro

      Pages 11-20

   3. Multi-category Bayesian Decision by Neural Networks

      • Yoshifusa Ito, Cidambi Srinivasan, Hiroyuki Izumi

      Pages 21-30

   4. Estimates of Network Complexity and Integral Representations

      • Paul C. Kainen, Věra Kůrková

      Pages 31-40

   5. Reliability of Cross-Validation for SVMs in High-Dimensional, Low Sample Size Scenarios

      • Sascha Klement, Amir Madany Mamlouk, Thomas Martinetz

      Pages 41-50

   6. Generalization of Concave and Convex Decomposition in Kikuchi Free Energy

      • Yu Nishiyama, Sumio Watanabe

      Pages 51-60

   7. Analysis of Chaotic Dynamics Using Measures of the Complex Network Theory

      • Yutaka Shimada, Takayuki Kimura, Tohru Ikeguchi

      Pages 61-70

   8. Global Dynamics of Finite Cellular Automata

      • Martin Schüle, Thomas Ott, Ruedi Stoop

      Pages 71-78

3. Learning Algorithms

   1. Semi-supervised Learning of Tree-Structured RBF Networks Using Co-training

      • Mohamed F. Abdel Hady, Friedhelm Schwenker, Günther Palm

      Pages 79-88

   2. A New Type of ART2 Architecture and Application to Color Image Segmentation

      • Jiaoyan Ai, Brian Funt, Lilong Shi

      Pages 89-98

   3. BICA: A Boolean Indepenedent Component Analysis Approach

      • Bruno Apolloni, Simone Bassis, Andrea Brega

      Pages 99-108

   4. Improving the Learning Speed in 2-Layered LSTM Network by Estimating the Configuration of Hidden Units and Optimizing Weights Initialization

      • Débora C. Corrêa, Alexandre L. M. Levada, José H. Saito

      Pages 109-118

   5. Manifold Construction Using the Multilayer Perceptron

      • Wei-Chen Cheng, Cheng-Yuan Liou

      Pages 119-127

   6. Improving Performance of a Binary Classifier by Training Set Selection

      • Cezary Dendek, Jacek Mańdziuk

      Pages 128-135

   7. An Overcomplete ICA Algorithm by InfoMax and InfoMin

      • Yoshitatsu Matsuda, Kazunori Yamaguchi

      Pages 136-144

   8. OP-ELM: Theory, Experiments and a Toolbox

      • Yoan Miche, Antti Sorjamaa, Amaury Lendasse

      Pages 145-154

   9. Robust Nonparametric Probability Density Estimation by Soft Clustering

      • Ezequiel López-Rubio, Juan Miguel Ortiz-de-Lazcano-Lobato, Domingo López-Rodríguez, María del Carmen Vargas-Gonzalez

      Pages 155-164

   10. Natural Conjugate Gradient on Complex Flag Manifolds for Complex Independent Subspace Analysis

       • Yasunori Nishimori, Shotaro Akaho, Mark D. Plumbley

       Pages 165-174

   11. Quadratically Constrained Quadratic Programming for Subspace Selection in Kernel Regression Estimation

       • Marco Signoretto, Kristiaan Pelckmans, Johan A. K. Suykens

       Pages 175-184

This two volume set LNCS 5163 and LNCS 5164 constitutes the refereed proceedings of the 18th International Conference on Artificial Neural Networks, ICANN 2008, held in Prague Czech Republic, in September 2008. The 200 revised full papers presented were carefully reviewed and selected from more than 300 submissions. The first volume contains papers on mathematical theory of neurocomputing, learning algorithms, kernel methods, statistical learning and ensemble techniques, support vector machines, reinforcement learning, evolutionary computing, hybrid systems, self-organization, control and robotics, signal and time series processing and image processing.

• Support Vector Machine
• algorithmic learning
• algorithms
• artificial intelligence
• bayesian statistics
• behavior
• bioinspired computing
• classification
• cognitive systems
• complexity
• data mining
• evolutionary systems
• face r
• fuzzy logic
• fuzzy system

Policies and ethics