Apart from research efforts bringing together metaheuristic techniques to train artificial neural networks, this is the first book to achieve this objective. This book provides a unified approach to training ANNs with modern heuristics; moreover, it provides abundant literature demonstrating how these procedures escape local optima and solve problems in very different mathematical scenarios
The procedures and methods in the book are strategies that have demonstrated success in finding solutions of high quality to hard problems in industry, business, and science within reasonable computational time
This book provides successful implementations of metaheuristic methods for neural network training. It is the first book to achieve this objective. Moreover, the basic principles and fundamental ideas given in the book will allow the readers to create successful training methods on their own. Overall, the book's aim is to provide a broad coverage of the concepts, methods, and tools of the important area of ANNs within the realm of continuous optimization.
|
Artificial neural networks (ANNs) offer a general framework for representing non-linear mappings from several input variables to several output variables, and they can be considered as an extension of the many conventional mapping techniques. In addition to many considerations on their biological foundations and their really wide spectrum of applications, constructing appropriate ANNs can be seen as a really hard problem. A distinguished task in building ANNs is the tuning of a set of parameters known as weights. This will be the main focus of the present book. The trained ANNs can be later used in classification (or recognition) problems, where the ANN outputs represent categories, or in prediction (approximation) problems, where the outputs represent continuous variables.
METAHEURISTIC PROCEDURES FOR TRAINING NEURAL NETWORKS provides successful implementations of metaheuristic methods for neural network training. Moreover, the basic principles and fundamental ideas given in the book will allow the readers to create successful training methods on their own. Apart from Chapter 1, in which classical training methods are reviewed for the sake of the book´s completeness, we have classified the chapters in three main categories. The first one is devoted to local search based methods, in which we include Simulated Annealing, Tabu Search, and Variable Neighborhood Search. The second part of the book presents the most effective population based methods, such as Estimation Distribution algorithms, Scatter Search, and Genetic Algorithms. Finally, the third part includes other advanced techniques, such as Ant Colony Optimization, Co-evolutionary methods, GRASP, and Memetic algorithms. All these methods have been shown to work out high quality solutions in a wide range of hard optimization problems. However, the book's objective is engineered to provide a broad coverage of the concepts, methods, and tools of this important area of ANNs within the realm of continuous optimization.
Classical Training Methods.- Local Search Based Methods.- Simulated Annealing.- Tabu Search.- Variable Neighbourhood Search.- Population Based Methods.- Estimation of Distribution Algorithms.- Genetic Algorithms.- Scatter Search.- Other Advanced Methods.- Ant Colony Optimization.- Cooperative Coevolutionary Methods.- Greedy Randomized Adaptive Search Procedures.- Memetic Algorithms.
From the reviews:
"The strength of the book is its clear motivation to bring a new breath from metaheuristics into training of neural networks and integrate both sub-disciplines for the purpose of better exploitation of artificial intelligence approaches. ... The most benefiting reader of this book will perhaps be those who research on modelling data with ANN faced with difficulty of robust mapping with classical training algorithms." (S. Gazioglu, Journal of the Operational Research Society, Vol. 58 (12), 2007)
Metaheuristic Procedures For Training Neural Networks provides successful implementations of metaheuristic methods for neural network training. Moreover, the basic principles and fundamental ideas given in the book will allow the readers to create successful training methods on their own. Apart from Chapter 1, which reviews classical training methods, the chapters are divided into three main categories. The first one is devoted to local search based methods, including Simulated Annealing, Tabu Search, and Variable Neighborhood Search. The second part of the book presents population based methods, such as Estimation Distribution algorithms, Scatter Search, and Genetic Algorithms. The third part covers other advanced techniques, such as Ant Colony Optimization, Co-evolutionary methods, GRASP, and Memetic algorithms. Overall, the book's objective is engineered to provide a broad coverage of the concepts, methods, and tools of this important area of ANNs within the realm of continuous optimization.
From the reviews:
"The strength of the book is its clear motivation to bring a new breath from metaheuristics into training of neural networks and integrate both sub-disciplines for the purpose of better exploitation of artificial intelligence approaches. ... The most benefiting reader of this book will perhaps be those who research on modelling data with ANN faced with difficulty of robust mapping with classical training algorithms." (S. Gazioglu, Journal of the Operational Research Society, Vol. 58 (12), 2007)
Inhaltsverzeichnis
Classical Training Methods.- Local Search Based Methods.- Simulated Annealing.- Tabu Search.- Variable Neighbourhood Search.- Population Based Methods.- Estimation of Distribution Algorithms.- Genetic Algorithms.- Scatter Search.- Other Advanced Methods.- Ant Colony Optimization.- Cooperative Coevolutionary Methods.- Greedy Randomized Adaptive Search Procedures.- Memetic Algorithms.
Klappentext
Metaheuristic Procedures For Training Neural Networks provides successful implementations of metaheuristic methods for neural network training. Moreover, the basic principles and fundamental ideas given in the book will allow the readers to create successful training methods on their own. Apart from Chapter 1, which reviews classical training methods, the chapters are divided into three main categories. The first one is devoted to local search based methods, including Simulated Annealing, Tabu Search, and Variable Neighborhood Search. The second part of the book presents population based methods, such as Estimation Distribution algorithms, Scatter Search, and Genetic Algorithms. The third part covers other advanced techniques, such as Ant Colony Optimization, Co-evolutionary methods, GRASP, and Memetic algorithms. Overall, the book's objective is engineered to provide a broad coverage of the concepts, methods, and tools of this important area of ANNs within the realm of continuous optimization.
Apart from research efforts bringing together metaheuristic techniques to train artificial neural networks, this is the first book to achieve this objective. This book provides a unified approach to training ANNs with modern heuristics; moreover, it provides abundant literature demonstrating how these procedures escape local optima and solve problems in very different mathematical scenarios
The procedures and methods in the book are strategies that have demonstrated success in finding solutions of high quality to hard problems in industry, business, and science within reasonable computational time
