Artificial Neural Nets And Genetic Algorithms

This book introduces readers to the fundamentals of artificial neural networks, with a special emphasis on evolutionary algorithms. At first, the book offers a literature review of several well-regarded evolutionary algorithms, including particle swarm and ant colony optimization, genetic algorithms and biogeography-based optimization. It then proposes evolutionary version of several types of neural networks such as feed forward neural networks, radial basis function networks, as well as recurrent neural networks and multi-later perceptron. Most of the challenges that have to be addressed when training artificial neural networks using evolutionary algorithms are discussed in detail. The book also demonstrates the application of the proposed algorithms for several purposes such as classification, clustering, approximation, and prediction problems. It provides a tutorial on how to design, adapt, and evaluate artificial neural networks as well, and includes source codes for most of the proposed techniques as supplementary materials.

The 2003 edition of ICANNGA marks a milestone in this conference series, because it is the tenth year of its existence. The series began in 1993 with the inaugural conference at Innsbruck in Austria. At that first conference, the organisers decided to organise a similar scientific meeting every two years. As a result, conferences were organised at Ales in France (1995), Norwich in England (1997), Portoroz in Slovenia (1999) and Prague in the Czech Republic (2001). It is a great honour that the conference is taking place in France for the second time. Each edition of ICANNGA has been special and had its own character. Not only that, participants have been able to sample the life and local culture in five different European coun tries. Originally limited to neural networks and genetic algorithms the conference has broadened its outlook over the past ten years and now includes papers on soft computing and artificial intelligence in general. This is one of the reasons why the reader will find papers on fuzzy logic and various other topics not directly related to neural networks or genetic algorithms included in these proceedings. We have, however, kept the same name, "International Conference on Artificial Neural Networks and Genetic Algorithms". All of the papers were sorted into one of six principal categories: neural network theory, neural network applications, genetic algorithm and evolutionary computation theory, genetic algorithm and evolutionary computation applications, fuzzy and soft computing theory, fuzzy and soft computing applications.

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.

Artificial neural networks and genetic algorithms both are areas of research which have their origins in mathematical models constructed in order to gain understanding of important natural processes. By focussing on the process models rather than the processes themselves, significant new computational techniques have evolved which have found application in a large number of diverse fields. This diversity is reflected in the topics which are subjects of the contributions to this volume. There are contributions reporting successful applications of the technology to the solution of industrial/commercial problems. This may well reflect the maturity of the technology, notably in the sense that 'real' users of modelling/prediction techniques are prepared to accept neural networks as a valid paradigm. Theoretical issues also receive attention, notably in connection with the radial basis function neural network. Contributions in the field of genetic algorithms reflect the wide range of current applications, including, for example, portfolio selection, filter design, frequency assignment, tuning of nonlinear PID controllers. These techniques are also used extensively for combinatorial optimisation problems.

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.

Artificial neural networks and genetic algorithms both are areas of research which have their origins in mathematical models constructed in order to gain understanding of important natural processes. By focussing on the process models rather than the processes themselves, significant new computational techniques have evolved which have found application in a large number of diverse fields. This diversity is reflected in the topics which are the subjects of contributions to this volume. There are contributions reporting theoretical developments in the design of neural networks, and in the management of their learning. In a number of contributions, applications to speech recognition tasks, control of industrial processes as well as to credit scoring, and so on, are reflected. Regarding genetic algorithms, several methodological papers consider how genetic algorithms can be improved using an experimental approach, as well as by hybridizing with other useful techniques such as tabu search. The closely related area of classifier systems also receives a significant amount of coverage, aiming at better ways for their implementation. Further, while there are many contributions which explore ways in which genetic algorithms can be applied to real problems, nearly all involve some understanding of the context in order to apply the genetic algorithm paradigm more successfully. That this can indeed be done is evidenced by the range of applications covered in this volume.

From the contents: Neural networks – theory and applications: NNs (= neural networks) classifier on continuous data domains– quantum associative memory – a new class of neuron-like discrete filters to image processing – modular NNs for improving generalisation properties – presynaptic inhibition modelling for image processing application – NN recognition system for a curvature primal sketch – NN based nonlinear temporal-spatial noise rejection system – relaxation rate for improving Hopfield network – Oja's NN and influence of the learning gain on its dynamics Genetic algorithms – theory and applications: transposition: a biological-inspired mechanism to use with GAs (= genetic algorithms) – GA for decision tree induction – optimising decision classifications using GAs – scheduling tasks with intertask communication onto multiprocessors by GAs – design of robust networks with GA – effect of degenerate coding on GAs – multiple traffic signal control using a GA – evolving musical harmonisation – niched-penalty approach for constraint handling in GAs – GA with dynamic population size – GA with dynamic niche clustering for multimodal function optimisation Soft computing and uncertainty: self-adaptation of evolutionary constructed decision trees by information spreading – evolutionary programming of near optimal NNs

This is the only book to apply neural nets, genetic algorithms, and fuzzy set theory to the fast growing field of machine learning. Placing particular emphasis on neural networks, it explores how to integrate them with other technologies to improve their performance. Examples are included for each system discussed.