Intelligent Control Based On Flexible Neural Networks
Mohammad Teshnehlab, Keigo Watanabe, M. TeshnehlabBooks.org participates in affiliate programs including Bookshop.org and the Amazon Services LLC Associates Program. We may earn a commission from qualifying purchases made through links on this page, at no additional cost to you.
Synopsis
The use of flexible sigmoid functions makes artificial neural networks more versatile. This volume determines learning algorithms for sigmoid functions in several different learning modes using flexible structures of neural networks with new derivation algorithms.
The book is aimed at electrical, electronic, and mechanical control and systems engineers concerned with intelligent control who wish to explore neural network approaches. Here, for readers who are unfamiliar with neural network computing, is a concise introduction to the main existing types of flexible neural networks. This book will be a valuable aid to new research in which high abilities in artificial neural networks in intelligent control design and development can be achieved.
Booknews
Determines learning algorithms for sigmoid functions in several different learning modes using flexible structures of neural networks with new derivation algorithms. Introduces fundamentals of neural networks and the main types of flexible neural networks, then details self-tuning PID control, self-tuning computed torque control, development of an inverse dynamics model, and self-organizing flexible neural networks. Includes chapter summaries and examples. For electrical, electronic, and mechanical control and systems engineers concerned with intelligent control. Lacks a subject index. The authors teach electrical and mechanical engineering at K. N. Toosi University, Iran, and Saga University, Japan. Annotation c. Book News, Inc., Portland, OR (booknews.com)