| Soft Computing and AI:Fundamentals and Applications | |
| Authors: Dilip Kumar Pratihar | ISBN:
978-81-8487-799-1 |
About the book This textbook has been revised and renamed as Soft Computing and AI: Fundamentals and Applications – earlier published as Soft Computing: Fundamentals and Applications, begins with an introduction to Soft Computing, a family of many members, namely Genetic Algorithms (GAs), Fuzzy Logic (FL), Neural Networks (NNs), etc., including AI tools. To realize the need for a non-traditional and nature-inspired optimization tool like GA, one chapter is devoted to explain the principle of traditional optimization. The working cycle of a GA is explained in depth along with the mechanisms of some specialized GAs with appropriate examples. Working principles of non-traditional optimization tools like Simulated Annealing (SA), Particle Swarm Optimization (PSO) and Bonobo Optimization (BO) algorithm are discussed. Multi-objective optimization is covered, where the working principles of a few approaches are explained. Fuzzy sets are introduced before explaining the principle of fuzzy reasoning and clustering. The fundamentals of NNs are presented, prior to the discussion on various forms of NN including Deep Learning Neural Network (DLNN). The combined techniques, such as GA-FL, GA-NN, NN-FL and GA-FL-NN are then explained, and the last chapter deals with the applications of soft computing and AI tools in two different fields of research. This book fulfils the requirements of a large number of readers belonging to various disciplines of engineering and general sciences. The algorithms are discussed with a number of solved numerical examples. It will be a valuable book for the undergraduate and postgraduate students, researchers, scientists and practicing engineers and others. | |
Key Features |
|
Table of content Dedication / Preface / Introduction / Optimization and Some Traditional Methods / Introduction to Genetic Algorithms / Some Specialized Genetic Algorithms / Overview of Other Non-Traditional Optimization Methods / Multi-Objective Optimization / Introduction to Fuzzy Sets / Fuzzy Reasoning and Clustering / Fundamentals of Neural Networks / Some Examples of Neural Networks / Reinforcement Learning and Deep Learning Neural Networks / Combined Genetic Algorithms: Fuzzy Logic / Combined Genetic Algorithms: Neural Networks / Combined Neural Networks: Fuzzy Logic / Applications of Soft Computing and AI Tools Audience Undergraduate and Graduate Students, Professionals & Researchers | |
 | |