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.

Cellular Genetic Algorithms defines a new class of optimization algorithms based on the concepts of structured populations and Genetic Algorithms (GAs). The authors explain and demonstrate the validity of these cellular genetic algorithms throughout the book. This class of genetic algorithms is shown to produce impressive results on a whole range of domains, including complex problems that are epistatic, multi-modal, deceptive, discrete, continuous, multi-objective, and random in nature. The focus of this book is twofold. On the one hand, the authors present new algorithmic models and extensions to the basic class of Cellular GAs in order to tackle complex problems more efficiently. On the other hand, practical real world tasks are successfully faced by applying Cellular GA methodologies to produce workable solutions of real-world applications. These methods can include local search (memetic algorithms), cooperation, parallelism, multi-objective, estimations of distributions, and self-adaptive ideas to extend their applicability.

The methods are benchmarked against well-known metaheuristics like Genetic Algorithms, Tabu Search, heterogeneous GAs, Estimation of Distribution Algorithms, etc. Also, a publicly available software tool is offered to reduce the learning curve in applying these techniques. The three final chapters will use the classic problem of “vehicle routing” and the hot topics of “ad-hoc mobile networks” and “DNA genome sequencing” to clearly illustrate and demonstrate the power and utility of these algorithms.

Here, a team of international experts brings together core ideas for solving complex problems in optimization across a wide variety of real-world settings, including computer science, engineering, transportation, telecommunications, and bioinformatics.

Part One—covers methodologies for complex problem solving including genetic programming, neural networks, genetic algorithms, hybrid evolutionary algorithms, and more.

Part Two—delves into applications including DNA sequencing and reconstruction, location of antennae in telecommunication networks, metaheuristics, FPGAs, problems arising in telecommunication networks, image processing, time series prediction, and more.

All chapters contain examples that illustrate the applications themselves as well as the actual performance of the algorithms.?Optimization Techniques for Solving Complex Problems is a valuable resource for practitioners and researchers who work with optimization in real-world settings.

The 16 papers presented in this volume were carefully reviewed and selected from 21 submissions. The topics covered include studies and tools to improve road traffic, energy consumption, logistics, frameworks to provide new services and take decisions in a holistic way, driving assistance, electric vehicles, public transport, and surveys on smart city concepts.

The fourth installment of the ECC was jointly organized by the University of Málaga, Spain; the VŠB - Technical University of Ostrava, Czech Republic; and Fujian University of Technology, Fuzhou, China. The conference took place in Málaga, Spain on October 9–11, 2017.

"Parallel Evolutionary Computation" focuses on the aspects related to the parallelization of evolutionary computations, such as parallel genetic operators, parallel fitness evaluation, distributed genetic algorithms, and parallel hardware implementations, as well as on their impact on several applications.The book is divided into four parts. The first part deals with a clear software-like and algorithmic vision on parallel evolutionary optimizations. The second part is about hardware implementations of genetic algorithms, a valuable topic which is hard to find in the present literature. The third part treats the problem of distributed evolutionary computation and presents three interesting applications wherein parallel EC new ideas are featured. Finally, the last part deals with the up-to-date field of parallel particle swarm optimization to illustrate the intrinsic similarities and potential extensions to techniques in this domain. The book offers a wide spectrum of sample works developed in leading research throughout the world about parallel implementations of efficient techniques at the heart of computational intelligence. It will be useful both for beginners and experienced researchers in the field of computational intelligence.

This book is the result of several years of research trying to better characterize parallel genetic algorithms (pGAs) as a powerful tool for optimization, search, and learning. Readers can learn how to solve complex tasks by reducing their high computational times. Dealing with two scientific fields (parallelism and GAs) is always difficult, and the book seeks at gracefully introducing from basic concepts to advanced topics.

The presentation is structured in three parts. The first one is targeted to the algorithms themselves, discussing their components, the physical parallelism, and best practices in using and evaluating them. A second part deals with the theory for pGAs, with an eye on theory-to-practice issues. A final third part offers a very wide study of pGAs as practical problem solvers, addressing domains such as natural language processing, circuits design, scheduling, and genomics.

This volume will be helpful both for researchers and practitioners. The first part shows pGAs to either beginners and mature researchers looking for a unified view of the two fields: GAs and parallelism. The second part partially solves (and also opens) new investigation lines in theory of pGAs. The third part can be accessed independently for readers interested in applications. The result is an excellent source of information on the state of the art and future developments in parallel GAs.

This book is an updated effort in summarizing the trending topics and new hot research lines in solving dynamic problems using metaheuristics. An analysis of the present state in solving complex problems quickly draws a clear picture: problems that change in time, having noise and uncertainties in their definition are becomingvery important. The tools to face these problems are still to be built, since existing techniques are either slow or inefficient in tracking the many global optima that those problems are presenting to the solver technique.

Thus, this book is devoted to include several of the most important advances in solving dynamic problems. Metaheuristics are the more popular tools to this end, and then we can find in the book how to best use genetic algorithms, particle swarm, ant colonies, immune systems, variable neighborhood search, and many other bioinspiredtechniques. Also, neural network solutions are considered in this book.

Both, theory and practice have been addressed in the chapters of the book. Mathematical background and methodological tools in solving this new class of problems and applications are included. From the applications point of view, not just academic benchmarks are dealt with, but also real world applications in logistics and bioinformaticsare discussed here. The book then covers theory and practice, as well as discrete versus continuous dynamic optimization, in the aim of creating a fresh and comprehensive volume. This book is targeted to either beginners and experienced practitioners in dynamic  optimization, since we took care of devising the chapters in a way that a wide audience could profit from its contents. We hope to offer a single source for up-to-date information in dynamic optimization, an inspiring and attractive new research domain that appeared in these last years and is here to stay.

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.

Cellular Genetic Algorithms defines a new class of optimization algorithms based on the concepts of structured populations and Genetic Algorithms (GAs). The authors explain and demonstrate the validity of these cellular genetic algorithms throughout the book. This class of genetic algorithms is shown to produce impressive results on a whole range of domains, including complex problems that are epistatic, multi-modal, deceptive, discrete, continuous, multi-objective, and random in nature. The focus of this book is twofold. On the one hand, the authors present new algorithmic models and extensions to the basic class of Cellular GAs in order to tackle complex problems more efficiently. On the other hand, practical real world tasks are successfully faced by applying Cellular GA methodologies to produce workable solutions of real-world applications. These methods can include local search (memetic algorithms), cooperation, parallelism, multi-objective, estimations of distributions, and self-adaptive ideas to extend their applicability.

The methods are benchmarked against well-known metaheuristics like Genetic Algorithms, Tabu Search, heterogeneous GAs, Estimation of Distribution Algorithms, etc. Also, a publicly available software tool is offered to reduce the learning curve in applying these techniques. The three final chapters will use the classic problem of “vehicle routing” and the hot topics of “ad-hoc mobile networks” and “DNA genome sequencing” to clearly illustrate and demonstrate the power and utility of these algorithms.

Here, a team of international experts brings together core ideas for solving complex problems in optimization across a wide variety of real-world settings, including computer science, engineering, transportation, telecommunications, and bioinformatics.

Part One—covers methodologies for complex problem solving including genetic programming, neural networks, genetic algorithms, hybrid evolutionary algorithms, and more.

Part Two—delves into applications including DNA sequencing and reconstruction, location of antennae in telecommunication networks, metaheuristics, FPGAs, problems arising in telecommunication networks, image processing, time series prediction, and more.

All chapters contain examples that illustrate the applications themselves as well as the actual performance of the algorithms.?Optimization Techniques for Solving Complex Problems is a valuable resource for practitioners and researchers who work with optimization in real-world settings.

The 16 papers presented in this volume were carefully reviewed and selected from 21 submissions. The topics covered include studies and tools to improve road traffic, energy consumption, logistics, frameworks to provide new services and take decisions in a holistic way, driving assistance, electric vehicles, public transport, and surveys on smart city concepts.

The fourth installment of the ECC was jointly organized by the University of Málaga, Spain; the VŠB - Technical University of Ostrava, Czech Republic; and Fujian University of Technology, Fuzhou, China. The conference took place in Málaga, Spain on October 9–11, 2017.

"Parallel Evolutionary Computation" focuses on the aspects related to the parallelization of evolutionary computations, such as parallel genetic operators, parallel fitness evaluation, distributed genetic algorithms, and parallel hardware implementations, as well as on their impact on several applications.The book is divided into four parts. The first part deals with a clear software-like and algorithmic vision on parallel evolutionary optimizations. The second part is about hardware implementations of genetic algorithms, a valuable topic which is hard to find in the present literature. The third part treats the problem of distributed evolutionary computation and presents three interesting applications wherein parallel EC new ideas are featured. Finally, the last part deals with the up-to-date field of parallel particle swarm optimization to illustrate the intrinsic similarities and potential extensions to techniques in this domain. The book offers a wide spectrum of sample works developed in leading research throughout the world about parallel implementations of efficient techniques at the heart of computational intelligence. It will be useful both for beginners and experienced researchers in the field of computational intelligence.

This book is the result of several years of research trying to better characterize parallel genetic algorithms (pGAs) as a powerful tool for optimization, search, and learning. Readers can learn how to solve complex tasks by reducing their high computational times. Dealing with two scientific fields (parallelism and GAs) is always difficult, and the book seeks at gracefully introducing from basic concepts to advanced topics.

The presentation is structured in three parts. The first one is targeted to the algorithms themselves, discussing their components, the physical parallelism, and best practices in using and evaluating them. A second part deals with the theory for pGAs, with an eye on theory-to-practice issues. A final third part offers a very wide study of pGAs as practical problem solvers, addressing domains such as natural language processing, circuits design, scheduling, and genomics.

This volume will be helpful both for researchers and practitioners. The first part shows pGAs to either beginners and mature researchers looking for a unified view of the two fields: GAs and parallelism. The second part partially solves (and also opens) new investigation lines in theory of pGAs. The third part can be accessed independently for readers interested in applications. The result is an excellent source of information on the state of the art and future developments in parallel GAs.

This book is an updated effort in summarizing the trending topics and new hot research lines in solving dynamic problems using metaheuristics. An analysis of the present state in solving complex problems quickly draws a clear picture: problems that change in time, having noise and uncertainties in their definition are becomingvery important. The tools to face these problems are still to be built, since existing techniques are either slow or inefficient in tracking the many global optima that those problems are presenting to the solver technique.

Thus, this book is devoted to include several of the most important advances in solving dynamic problems. Metaheuristics are the more popular tools to this end, and then we can find in the book how to best use genetic algorithms, particle swarm, ant colonies, immune systems, variable neighborhood search, and many other bioinspiredtechniques. Also, neural network solutions are considered in this book.

Both, theory and practice have been addressed in the chapters of the book. Mathematical background and methodological tools in solving this new class of problems and applications are included. From the applications point of view, not just academic benchmarks are dealt with, but also real world applications in logistics and bioinformaticsare discussed here. The book then covers theory and practice, as well as discrete versus continuous dynamic optimization, in the aim of creating a fresh and comprehensive volume. This book is targeted to either beginners and experienced practitioners in dynamic  optimization, since we took care of devising the chapters in a way that a wide audience could profit from its contents. We hope to offer a single source for up-to-date information in dynamic optimization, an inspiring and attractive new research domain that appeared in these last years and is here to stay.