Self-Adapting Intelligent Neural Systems Using Evolutionary Techniques

Self-Adapting Intelligent Neural Systems Using Evolutionary Techniques

Daniel Manrique (Universidad Politecnica de Madrid, Spain), Juan Rios (Universidad Politecnica de Madrid, Spain) and Alfonso Rodriguez-Paton (Universidad Politecnica de Madrid, Spain)
Copyright: © 2006 |Pages: 22
DOI: 10.4018/978-1-59140-902-1.ch005
OnDemand PDF Download:


This chapter describes genetic algorithm-based evolutionary techniques for automatically constructing intelligent neural systems. These techniques can be used to build and train multilayer perceptrons with the simplest architecture. These neural networks are usually designed using binary-coded genetic algorithms. The authors show how the basic architectures codification method, which uses an algebra-based codification, employs a shorter string length and voids illegal architectures in the search space. The networks are trained using real number codification. The morphological crossover operator is presented and compared to other important real-coded crossover operators. The purpose is to understand that the combination of all these techniques results in an evolutionary system, which self-adaptively constructs intelligent neural systems to solve a problem given as a set of training patterns. To do so, the evolutionary system is applied in laboratory tests and to a real-world problem: breast cancer diagnosis.

Complete Chapter List

Search this Book:
Table of Contents
Alejandro Pazos
Chapter 1
Ana B. Porto, Alejandro Pazos
This chapter presents a study that incorporates into the connectionist systems new elements that emulate cells of the glial system. More concretely... Sample PDF
Neuroglial Behaviour in Computer Science
Chapter 2
Eduardo D. Martin, Alfonso Araque
Artificial neural networks are a neurobiologically inspired paradigm that emulates the functioning of the brain. They are based on neuronal... Sample PDF
Astrocytes and the Biological Neural Networks
Chapter 3
Paulo Cortez, Miguel Rocha, José Neves
This chapter presents a hybrid evolutionary computation/neural network combination for time series prediction. Neural networks are innate candidates... Sample PDF
Time Series Forecasting by Evolutionary Neural Networks
Chapter 4
Julián Dorado, Nieves Pedreira, Mónica Miguelez
This chapter presents the use of Artificial Neural Networks (ANN) and Evolutionary Computation (EC) techniques to solve real-world problems... Sample PDF
Development of ANN with Adaptive Connections by CE
Chapter 5
Daniel Manrique, Juan Rios, Alfonso Rodriguez-Paton
This chapter describes genetic algorithm-based evolutionary techniques for automatically constructing intelligent neural systems. These techniques... Sample PDF
Self-Adapting Intelligent Neural Systems Using Evolutionary Techniques
Chapter 6
Daniel Rivero, Miguel Varela, Javier Pereira
A technique is described in this chapter that makes it possible to extract the knowledge held by previously trained artificial neural networks. This... Sample PDF
Using Genetic Programming to Extract Knowledge from Artificial Neural Networks
Chapter 7
Marcos G. Pose, Alberto C. Carollo, José M.A. Garda, Mari P. Gomez-Carracedo
This chapter shows several approaches to determine how the most relevant subset of variables can perform a classification task. It will permit the... Sample PDF
Several Approaches to Variable Selection by Means of Genetic Algorithms
Chapter 8
Juan R. Rabunal, Juan Puertas
This chapter proposes an application of two techniques of artificial intelligence in a civil engineering area: the artificial neural networks (ANN)... Sample PDF
Hybrid System with Artificial Neural Networks and Evolutionary Computation in Civil Engineering
Chapter 9
Belén Gonzalez, M. Isabel Martinez, Diego Carro
This chapter displays an example of application of the ANN in civil engineering. Concretely, it is applied to the prediction of the consistency of... Sample PDF
Prediction of the Consistency of Concrete by Means of the Use of Artificial Neural Networks
Chapter 10
J. Sethuraman
Soft computing is popularly referred to as a collection of methodologies that work synergistically and provide flexible information processing... Sample PDF
Soft Computing Approach for Bond Rating Prediction
Chapter 11
Robert Perkins, Anthony Brabazon
The practical application of MLPs can be time-consuming due to the requirement for substantial modeler intervention in order to select appropriate... Sample PDF
Predicting Credit Ratings with a GA-MLP Hybrid
Chapter 12
Music and Neural Networks  (pages 239-264)
Giuseppe Buzzanca
This chapter pertains to the research in the field of music and artificial neural networks. The first attempts to codify human musical cognition... Sample PDF
Music and Neural Networks
Chapter 13
Alfonso Iglesias, Bernardino Arcay, José M. Cotos
This chapter explains the foundations of a new support system for fisheries, based on connectionist techniques, digital image treatment, and fuzzy... Sample PDF
Connectionist Systems for Fishing Prediction
Chapter 14
Kun-Chang Lee, Tae-Young Paik
Cost managers working in manufacturing firms have suffered from the difficulty of determining an optimal cost control strategy. Though the concept... Sample PDF
A Neural Network Approach to Cost Minimizatin in a Production Scheduling Setting
Chapter 15
Tarun Bhaskar, Narasimha Kamath B.
Intrusion detection system (IDS) is now becoming an integral part of the network security infrastructure. Data mining tools are widely used for... Sample PDF
Intrusion Detection Using Modern Techniques: Integration of Genetic Algorithms and Rough Set with Neural Networks
Chapter 16
Alejandra Rodriguez, Carlos Dafonte, Bernardino Arcay, Iciar Carricajo, Minia Manteiga
This chapter describes a hybrid approach to the unattended classification of low-resolution optical spectra of stars. The classification of stars in... Sample PDF
Cooperative AI Techniques for Stellar Spectra Classification: A Hybrid Strategy
About the Authors