
As an Amazon Associate and affiliate partner, Menrva Books earns from qualifying purchases. Learn more
This publication describes examples of applications of neural networks in modelling, prediction and control. Topics covered include identification of general linear and nonlinear processes, forecasting of river levels, stock market prices, currency exchange rates, and control of a time-delayed plant and a two-joint robot. The neural network types considered are the multilayer perceptron (MLP), the Elman and Jordan networks, the Group-Method-of-Data-Handling (GMDH), the cerebellar-model-articulation-controller (CMAC) networks and neuromorphic fuzzy logic systems. The algorithms presented are the standard backpropagation (BP) algorithm, the Widrow-Hoff learning, dynamic BP and evolutionary learning. Full listings of computer programs written in C for neural-network-based system identification and prediction to facilitate practical experimentation with neural network techniques are included.
This publication explores the practical applications of neural networks across various domains, focusing on modeling, prediction, and control. The author, Duc Truong Pham, details how neural networks can be employed for identifying linear and nonlinear processes, forecasting financial markets and environmental data, and controlling complex systems like robots and time-delayed plants. The book examines a range of neural network architectures, including MLPs, Elman and Jordan networks, GMDH, CMAC, and neuromorphic fuzzy logic systems, alongside various learning algorithms such as backpropagation, Widrow-Hoff, dynamic BP, and evolutionary learning. To aid practical implementation, the text includes full C program listings for system identification and prediction.
The book is presented as a technical guide for practitioners and researchers interested in applying neural networks. Its focus on practical examples and inclusion of source code suggests an aim to facilitate hands-on experimentation and implementation. The detailed coverage of various network types and learning algorithms indicates a comprehensive approach to the subject matter. The publication date suggests it offers foundational knowledge within the field of neural networks as understood in the mid-1990s.
Page Count:
242
Publication Date:
1995-01-01
ISBN-10:
1447132467
ISBN-13:
9781447132462
No comments yet. Be the first to share your thoughts!