Constructive Neural Networks

1. Front Matter

   PDF

2. Constructive Neural Network Algorithms for Feedforward Architectures Suitable for Classification Tasks

   • Maria do Carmo Nicoletti, João R. Bertini Jr., David Elizondo, Leonardo Franco, José M. Jerez

   Pages 1-23

3. Efficient Constructive Techniques for Training Switching Neural Networks

   • Enrico Ferrari, Marco Muselli

   Pages 25-48

4. Constructive Neural Network Algorithms That Solve Highly Non-separable Problems

   • Marek Grochowski, Włodzisław Duch

   Pages 49-70

5. On Constructing Threshold Networks for Pattern Classification

   • Martin Anthony

   Pages 71-82

6. Self-Optimizing Neural Network 3

   • Adrian Horzyk

   Pages 83-101

7. M-CLANN: Multiclass Concept Lattice-Based Artificial Neural Network

   • Engelbert Mephu Nguifo, Norbert Tsopze, Gilbert Tindo

   Pages 103-121

8. Constructive Morphological Neural Networks: Some Theoretical Aspects and Experimental Results in Classification

   • Peter Sussner, Estevão Laureano Esmi

   Pages 123-144

9. A Feedforward Constructive Neural Network Algorithm for Multiclass Tasks Based on Linear Separability

   • João Roberto Bertini Jr., Maria do Carmo Nicoletti

   Pages 145-169

10. Analysis and Testing of the m-Class RDP Neural Network

    • David A. Elizondo, Juan M. Ortiz-de-Lazcano-Lobato, Ralph Birkenhead

    Pages 171-192

11. Active Learning Using a Constructive Neural Network Algorithm

    • José L. Subirats, Leonardo Franco, Ignacio Molina, José M. Jerez

    Pages 193-206

12. Incorporating Expert Advice into Reinforcement Learning Using Constructive Neural Networks

    • Robert Ollington, Peter Vamplew, John Swanson

    Pages 207-224

13. A Constructive Neural Network for Evolving a Machine Controller in Real-Time

    • Andreas Huemer, David Elizondo, Mario Gongora

    Pages 225-242

14. Avoiding Prototype Proliferation in Incremental Vector Quantization of Large Heterogeneous Datasets

    • Héctor F. Satizábal, Andres Pérez-Uribe, Marco Tomassini

    Pages 243-260

15. Tuning Parameters in Fuzzy Growing Hierarchical Self-Organizing Networks

    • Miguel Arturo Barreto-Sanz, Andrés Pérez-Uribe, Carlos-Andres Peña-Reyes, Marco Tomassini

    Pages 261-279

16. Self-Organizing Neural Grove: Efficient Multiple Classifier System with Pruned Self-Generating Neural Trees

    • Hirotaka Inoue

    Pages 281-291

17. Back Matter

    PDF

This book presents a collection of invited works that consider constructive methods for neural networks, taken primarily from papers presented at a special th session held during the 18 International Conference on Artificial Neural Networks (ICANN 2008) in September 2008 in Prague, Czech Republic. The book is devoted to constructive neural networks and other incremental learning algorithms that constitute an alternative to the standard method of finding a correct neural architecture by trial-and-error. These algorithms provide an incremental way of building neural networks with reduced topologies for classification problems. Furthermore, these techniques produce not only the multilayer topologies but the value of the connecting synaptic weights that are determined automatically by the constructing algorithm, avoiding the risk of becoming trapped in local minima as might occur when using gradient descent algorithms such as the popular back-propagation. In most cases the convergence of the constructing algorithms is guaranteed by the method used. Constructive methods for building neural networks can potentially create more compact and robust models which are easily implemented in hardware and used for embedded systems. Thus a growing amount of current research in neural networks is oriented towards this important topic. The purpose of this book is to gather together some of the leading investigators and research groups in this growing area, and to provide an overview of the most recent advances in the techniques being developed for constructive neural networks and their applications.

• Constructive Algorithms
• algorithm
• algorithms
• artificial neural network
• calculus
• computational intelligence
• control
• fuzzy
• intelligence
• learning
• learning algorithm
• neural network
• neural networks
• reinforcement learning
• training

• Dept. of Computer Science, University of Malaga , Málaga, Spain

  Leonardo Franco, José M. Jerez

• Centre for Computational Intelligence, School of Computing, De Montfort University, The Gateway , Leicester, UK

  David A. Elizondo

Policies and ethics