The Handbook on Computer Learning and Intelligence is a second edition which aims to be a one-stop-shop for the various aspects of the broad research area of computer learning and intelligence. This field of research evolved so much in the last five years that it necessitates this new edition of the earlier Handbook on Computational Intelligence. This two-volume handbook is divided into five parts. Volume 1 covers Explainable AI and Supervised Learning. Volume 2 covers three parts: Deep Learning, Intelligent Control, and Evolutionary Computation. The chapters detail the theory, methodology and applications of computer learning and intelligence, and are authored by some of the leading experts in the respective areas. The fifteen core chapters of the previous edition have been written and significantly refreshed by the same authors. Parts of the handbook have evolved to keep pace with the latest developments in computational intelligence in the areas that span across Machine Learning and Artificial Intelligence. The Handbook remains dedicated to applications and engineering-orientated aspects of these areas over abstract theories.
Previously published as Handbook of Computational Intelligence, this two-volume handbook consists of 26 chapters that detail the theory, methodology, and applications of computer learning and intelligence, particularly explainable artificial intelligence, supervised learning, deep learning, intelligent control, and evolutionary computation. It covers the fundamentals of fuzzy sets theory, granular computing, evolving fuzzy and neuro-fuzzy systems, fuzzy classifiers, kernel models and support vector machines, evolving connectionist systems for adaptive learning and knowledge discovery, fault detection and diagnoses based on a long short-term memory neural network applied to a level control pilot plant, ensemble learning, fuzzy model-based control, reinforcement learning with applications in automation control and game theory, nature-inspired optimal tuning of fuzzy controllers, evolutionary computation, algorithmic bias, collective intelligence and metaheuristic algorithms inspired by animals, and fuzzy dynamic parameter adaptation. This edition has mostly rewritten and new chapters, including new chapters on incremental fuzzy machine learning for online classification of emotions in games, causal reasoning, supervised learning using spiking neural networks, conversational agents, deep learning, deep neural networks, a multistream deep rule-based ensemble system for aerial image scene classification, indirect self-evolving fuzzy control approaches and their application, and evaluating inter-task similarity for multifactorial evolutionary algorithms from different perspectives. Chapters are by researchers and scientists from around the world. Annotation ©2022 Ringgold, Inc., Portland, OR (protoview.com)
