Artificial Neural Nets and Genetic Algorithms

1. Front Matter

   Pages i-xvi

   PDF

2. Robotics and Sensors

   1. Obstacle Identification by an Ultrasound Sensor Using Neural Networks

      • D. Diep, A. Johannet, P. Bonnefoy, F. Harroy

      Pages 1-5

   2. A Modular Reinforcement Learning Architecture for Mobile Robot Control

      • R. M. Rylatt, C. A. Czarnecki, T. W. Routen

      Pages 6-10

   3. Timing without Time — An Experiment in Evolutionary Robotics

      • H. H. Lund

      Pages 11-15

   4. Incremental Acquisition of Complex Behaviour by Structured Evolution

      • S. Perkins, G. Hayes

      Pages 16-20

   5. Evolving Neural Controllers for Robot Manipulators

      • R. Salama, R. Owens

      Pages 21-25

   6. Using Genetic Algorithms with Variable-length Individuals for Planning Two-Manipulators Motion

      • J. Riquelme, M. A. Ridao, E. F. Camacho, M. Toro

      Pages 26-30

3. ANN Architectures

   1. Ensembles of Neural Networks for Digital Problems

      • D. Philpot, T. Hendtlass

      Pages 31-34

   2. A Modular Neural Network Architecture with Additional Generalization Abilities for Large Input Vectors

      • A. Schmidt, Z. Bandar

      Pages 35-39

   3. Principal Components Identify MLP Hidden Layer Size for Optimal Generalisation Performance

      • M. Girolami

      Pages 40-43

   4. Bernoulli Mixture Model of Experts for Supervised Pattern Classification

      • N. Elhor, R. Bertrand, D. Hamad

      Pages 44-48

4. Power Systems

   1. Electric Load Forecasting with Genetic Neural Networks

      • F. J. Marín, F. Sandoval

      Pages 49-52

   2. Multiobjective Pressurised Water Reactor Reload Core Design using a Genetic Algorithm

      • G. T. Parks

      Pages 53-57

   3. Using Artificial Neural Networks to Model Non-Linearity in a Complex System

      • P. Weller, A. Thompson, R. Summers

      Pages 58-61

   4. Transit Time Estimation by Artificial Neural Networks

      • T. Tambouratzis, M. Antonopoulos-Domis, M. Marseguerra, E. Padovani

      Pages 62-65

5. Evolware

   1. Evolving Asynchronous and Scalable Non-uniform Cellular Automata

      • M. Sipper, M. Tomassini, M. S. Capcarrere

      Pages 66-70

   2. One-Chip Evolvable Hardware: 1C-EHW

      • H. de Garis

      Pages 71-77

6. Vision

   1. Evolving Low-Level Vision Capabilities with the GENCODER Genetic Programming Environment

      • P. Ziemeck, H. Ritter

      Pages 78-82

   2. NLRFLA: A Supervised Learning Algorithm for the Development of Non-Linear Receptive Fields

      • S. L. Funk, I. Kumazawa, J. M. Kennedy

      Pages 83-87

   3. Fuzzy-tuned Stochastic Scanpaths for AGV Vision

      • I. J. Griffiths, Q. H. Mehdi, N. E. Gough

      Pages 88-92

This is the third in a series of conferences devoted primarily to the theory and applications of artificial neural networks and genetic algorithms. The first such event was held in Innsbruck, Austria, in April 1993, the second in Ales, France, in April 1995. We are pleased to host the 1997 event in the mediaeval city of Norwich, England, and to carryon the fine tradition set by its predecessors of providing a relaxed and stimulating environment for both established and emerging researchers working in these and other, related fields. This series of conferences is unique in recognising the relation between the two main themes of artificial neural networks and genetic algorithms, each having its origin in a natural process fundamental to life on earth, and each now well established as a paradigm fundamental to continuing technological development through the solution of complex, industrial, commercial and financial problems. This is well illustrated in this volume by the numerous applications of both paradigms to new and challenging problems. The third key theme of the series, therefore, is the integration of both technologies, either through the use of the genetic algorithm to construct the most effective network architecture for the problem in hand, or, more recently, the use of neural networks as approximate fitness functions for a genetic algorithm searching for good solutions in an 'incomplete' solution space, i.e. one for which the fitness is not easily established for every possible solution instance.

• algorithms
• artificial neural network
• cognition
• genetic algorithms
• genetic programming
• heuristics
• image processing
• learning
• modeling
• neural networks
• optimization
• reinforcement learning
• robot
• robotics
• scheduling
• complexity

• School of Information Systems, University of East Anglia, Norwich, UK

  George D. Smith

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

  Nigel C. Steele

• Institut für Informatik, Universität Innsbruck, Innsbruck, Austria

  Rudolf F. Albrecht

Policies and ethics