Automatic Generation Of Neural Network Architecture Using Evolutionary Computation

This book describes the application of evolutionary computation in the automatic generation of a neural network architecture. The architecture has a significant influence on the performance of the neural network. It is the usual practice to use trial and error to find a suitable neural network architecture for a given problem. The process of trial and error is not only time-consuming but may not generate an optimal network. The use of evolutionary computation is a step towards automation in neural network architecture generation.An overview of the field of evolutionary computation is presented, together with the biological background from which the field was inspired. The most commonly used approaches to a mathematical foundation of the field of genetic algorithms are given, as well as an overview of the hybridization between evolutionary computation and neural networks. Experiments on the implementation of automatic neural network generation using genetic programming and one using genetic algorithms are described, and the efficacy of genetic algorithms as a learning algorithm for a feedforward neural network is also investigated.

This book delivers the state of the art in deep learning (DL) methods hybridized with evolutionary computation (EC). Over the last decade, DL has dramatically reformed many domains: computer vision, speech recognition, healthcare, and automatic game playing, to mention only a few. All DL models, using different architectures and algorithms, utilize multiple processing layers for extracting a hierarchy of abstractions of data. Their remarkable successes notwithstanding, these powerful models are facing many challenges, and this book presents the collaborative efforts by researchers in EC to solve some of the problems in DL. EC comprises optimization techniques that are useful when problems are complex or poorly understood, or insufficient information about the problem domain is available. This family of algorithms has proven effective in solving problems with challenging characteristics such as non-convexity, non-linearity, noise, and irregularity, which dampen the performance of most classic optimization schemes. Furthermore, EC has been extensively and successfully applied in artificial neural network (ANN) research —from parameter estimation to structure optimization. Consequently, EC researchers are enthusiastic about applying their arsenal for the design and optimization of deep neural networks (DNN). This book brings together the recent progress in DL research where the focus is particularly on three sub-domains that integrate EC with DL: (1) EC for hyper-parameter optimization in DNN; (2) EC for DNN architecture design; and (3) Deep neuroevolution. The book also presents interesting applications of DL with EC in real-world problems, e.g., malware classification and object detection. Additionally, it covers recent applications of EC in DL, e.g. generative adversarial networks (GAN) training and adversarial attacks. The book aims to prompt and facilitate the research in DL with EC both in theory and in practice.

Evolutionary computing paradigms offer robust and powerful adaptive search mechanisms for system design. This book’s thirteen chapters cover a wide area of topics in evolutionary computing and applications, including an introduction to evolutionary computing in system design; evolutionary neuro-fuzzy systems; and evolution of fuzzy controllers. The book will be useful to researchers in intelligent systems with interest in evolutionary computing, as well as application engineers and system designers.

Computational Intelligence: Synergies of Fuzzy Logic, NeuralNetworks and Evolutionary Computing presents an introduction tosome of the cutting edge technological paradigms under the umbrellaof computational intelligence. Computational intelligence schemesare investigated with the development of a suitable framework forfuzzy logic, neural networks and evolutionary computing,neuro-fuzzy systems, evolutionary-fuzzy systems and evolutionaryneural systems. Applications to linear and non-linear systems arediscussed with examples. Key features: Covers all the aspects of fuzzy, neural and evolutionaryapproaches with worked out examples, MATLAB® exercises andapplications in each chapter Presents the synergies of technologies of computationalintelligence such as evolutionary fuzzy neural fuzzy andevolutionary neural systems Considers real world problems in the domain of systemsmodelling, control and optimization Contains a foreword written by Lotfi Zadeh Computational Intelligence: Synergies of Fuzzy Logic, NeuralNetworks and Evolutionary Computing is an ideal text for finalyear undergraduate, postgraduate and research students inelectrical, control, computer, industrial and manufacturingengineering.

This book contains state-of-the-art contributions in the field of evolutionary and deterministic methods for design, optimization and control in engineering and sciences. Specialists have written each of the 34 chapters as extended versions of selected papers presented at the International Conference on Evolutionary and Deterministic Methods for Design, Optimization and Control with Applications to Industrial and Societal Problems (EUROGEN 2013). The conference was one of the Thematic Conferences of the European Community on Computational Methods in Applied Sciences (ECCOMAS). Topics treated in the various chapters are classified in the following sections: theoretical and numerical methods and tools for optimization (theoretical methods and tools; numerical methods and tools) and engineering design and societal applications (turbo machinery; structures, materials and civil engineering; aeronautics and astronautics; societal applications; electrical and electronics applications), focused particularly on intelligent systems for multidisciplinary design optimization (mdo) problems based on multi-hybridized software, adjoint-based and one-shot methods, uncertainty quantification and optimization, multidisciplinary design optimization, applications of game theory to industrial optimization problems, applications in structural and civil engineering optimum design and surrogate models based optimization methods in aerodynamic design.

This proceeding book of Nostradamus conference (http://nostradamus-conference.org) contains accepted papers presented at this event in 2012. Nostradamus conference was held in the one of the biggest and historic city of Ostrava (the Czech Republic, http://www.ostrava.cz/en), in September 2012. Conference topics are focused on classical as well as modern methods for prediction of dynamical systems with applications in science, engineering and economy. Topics are (but not limited to): prediction by classical and novel methods, predictive control, deterministic chaos and its control, complex systems, modelling and prediction of its dynamics and much more.

The refereed proceedings of the Joint International Conference on Artificial Neural Networks and International Conference on Neural Information Processing, ICANN/ICONIP 2003, held in Istanbul, Turkey, in June 2003. The 138 revised full papers were carefully reviewed and selected from 346 submissions. The papers are organized in topical sections on learning algorithms, support vector machine and kernel methods, statistical data analysis, pattern recognition, vision, speech recognition, robotics and control, signal processing, time-series prediction, intelligent systems, neural network hardware, cognitive science, computational neuroscience, context aware systems, complex-valued neural networks, emotion recognition, and applications in bioinformatics.

"Applications of Neural Networks in High Assurance Systems" is the first book directly addressing a key part of neural network technology: methods used to pass the tough verification and validation (V&V) standards required in many safety-critical applications. The book presents what kinds of evaluation methods have been developed across many sectors, and how to pass the tests. A new adaptive structure of V&V is developed in this book, different from the simple six sigma methods usually used for large-scale systems and different from the theorem-based approach used for simplified component subsystems.