Artificial Neural Nets and Genetic Algorithms

1. Front Matter

   Pages I-XIII

   PDF

2. Plenary Talks and Tutorials

   1. What Can a Neural Network Do without Scaling Activation Function?

      • Yoshifusa Ito

      Pages 1-6

   2. Ratio Scales are Critical for Modeling Neural Synthesis in the Brain

      • Thomas L. Saaty

      Pages 7-15

   3. Hypermatrix of the Brain

      • Thomas L. Saaty

      Pages 16-21

   4. The Computational Capabilities of Neural Networks

      • Jiří Šíma

      Pages 22-26

3. Neural Networks — Theory

   1. Activation Functions

      • N. C. Steele, C. R. Reeves, E. I. Gaura

      Pages 27-30

   2. A Simulation of Spiking Neurons by Sigmoid Neurons

      • Vladimír Kvasnička

      Pages 31-34

   3. Tightness of Upper Bounds on Rates of Neural-Network Approximation

      • Věra Kůrková, Marcello Sanguineti

      Pages 35-38

   4. Incremental Function Approximation Based on Gram-Schmidt Orthonormalisation Process

      • Bartlomiej Beliczynski

      Pages 39-42

   5. Wavelet Based Smoothing in Time Series Prediction with Neural Networks

      • Uroš Lotrič, Andrej Dobnikar

      Pages 43-46

   6. Fitting Densities and Hazard Functions with Neural Networks

      • Colin Reeves, Charles Johnston

      Pages 47-50

   7. Optimization of Expensive Functions by Surrogates Created from Neural Network Ensembles

      • Jiří Pospíchal

      Pages 51-54

   8. Local-Global Neural Networks for Interpolation

      • Carlos E. Pedreira, Luiz Carlos Pedroza, Mayte Fariñas

      Pages 55-58

   9. Improving the Competency of Classifiers through Data Generation

      • Herna L. Viktor, Iryna Skrypnik

      Pages 59-62

   10. Graded Rescaling in Hopfield Networks

       • Xinchuan Zeng, Tony R. Martinez

       Pages 63-66

   11. Principles of Associative Computation

       • Andrzej Wichert, Birgit Lonsinger-Miller

       Pages 67-69

   12. An Experimental Assessment of the Performance of Several Associative Memory Models

       • S. P. Turvey, S. P. Hunt, N. Davey, R. J. Frank

       Pages 70-73

   13. Recall Time in Densely Encoded Hopfield Network: Results from KFS Theory and Computer Simulation

       • A. A. Frolov, D. Husek, P. Combe, V. Snášel

       Pages 74-77

   14. On-Line Identification and Rule Extraction of Finite State Automata with Recurrent Neural Networks

       • Ivan Gabrijel, Andrej Dobnikar

       Pages 78-81

   15. Using Decision Surface Mapping in the Automatic Recognition of Images

       • Colin Reeves, Gurdeep Singh Billan

       Pages 82-85

The first ICANNGA conference, devoted to biologically inspired computational paradigms, Neural Net­ works and Genetic Algorithms, was held in Innsbruck, Austria, in 1993. The meeting attracted researchers from all over Europe and further afield, who decided that this particular blend of topics should form a theme for a series of biennial conferences. The second meeting, held in Ales, France, in 1995, carried on the tradition set in Innsbruck of a relaxed and stimulating environment for the. exchange of ideas. The series has continued in Norwich, UK, in 1997, and Portoroz, Slovenia, in 1999. The Institute of Computer Science, Czech Academy of Sciences, is pleased to host the fifth conference in Prague. We have chosen the Liechtenstein palace under the Prague Castle as the conference site to enhance the traditionally good atmosphere of the meeting. There is an inspirational genius loci of the historical center of the city, where four hundred years ago a fruitful combination of theoretical and empirical method, through the collaboration of Johannes Kepler and Tycho de Brahe, led to the discovery of the laws of planetary orbits.

• Analysis
• Hub
• Pattern Recognition
• Routing
• algorithms
• artificial intelligence
• complexity
• data mining
• fuzzy logic
• image analysis
• modeling
• optimization
• proving
• simulation

• Institute of Computer Science, Czech Republic

  Věra Kůrková, Roman Neruda

• Institute of Information Theory and Automation, Academy of Sciences of the Czech Republic, Prague, Czech Republic

  Miroslav Kárný

• Division of Mathematics, School of Mathematical and Information Sciences Coventry University, Coventry, UK

  Nigel C. Steele

Policies and ethics