Read more
Conventional model-based data processing methods are computationally expensive and require experts' knowledge for the modelling of a system. Neural networks are a model-free, adaptive, parallel-processing solution. This textbook provides a powerful and universal paradigm for information processing; it reviews the most popular neural-network methods and their associated techniques.
Each chapter has a systematic survey of each neural-network model. Computational intelligence topics like fuzzy logic and genetic algorithms (tools for neural-network learning) are introduced. Array signal processing problems are used to show the applications of each model.
This is an ideal textbook for graduate students and researchers; as well as introducing the basics, the exhaustive list of references included will aid their future research. It is also a valuable reference for scientists and practitioners working in pattern recognition, signal processing, speech and image processing, data analysis and A.I.
List of contents
Fundamentals of Machine Learning and Softcomputing.- Multilayer Perceptrons.- Hopfield Networks and Boltzmann Machines.- Competitive Learning and Clustering.- Radial Basis Function Networks.- Principal Component Analysis Networks.- Fuzzy Logic and Neurofuzzy Systems.- Evolutionary Algorithms and Evolving Neural Networks.- Discussion and Outlook.
About the author
Ke-Lin Du is currently the Chief Scientist at Enjoyor Inc., China. He is also an Affiliate Associate Professor in Department of Electrical and Computer Engineering at Concordia University, Canada. Prior to joining Enjoyor Inc. in 2012, he held positions with Huawei Technologies, the China Academy of Telecommunication Technology, the Chinese University of Hong Kong, the Hong Kong University of Science and Technology, and Concordia University. He has published two books and over 50 papers, and filed over 15 patents. His current research interests include signal processing, neural networks, intelligent systems, and wireless communications. He is a Senior Member of the IEEE.M.N.S. Swamy is currently a Research Professor and holder of the Concordia Tier I Research Chair Signal Processing in the Department of Electrical and Computer Engineering, Concordia University, where he was Dean of the Faculty of Engineering and Computer Science from 1977 to 1993 and the founding Chair of the EE department. He has published extensively in the areas of circuits, systems and signal processing, and co-authored five books. Professor Swamy is a Fellow of the IEEE, IET (UK) and EIC (Canada), and has received many IEEE-CAS awards, including the Guillemin-Cauer award in 1986, as well as the Education Award and the Golden Jubilee Medal, both in 2000.§
Summary
Conventional model-based data processing methods are computationally expensive and require experts’ knowledge for the modelling of a system. Neural networks are a model-free, adaptive, parallel-processing solution. This textbook provides a powerful and universal paradigm for information processing; it reviews the most popular neural-network methods and their associated techniques.
Each chapter has a systematic survey of each neural-network model. Computational intelligence topics like fuzzy logic and genetic algorithms (tools for neural-network learning) are introduced. Array signal processing problems are used to show the applications of each model.
This is an ideal textbook for graduate students and researchers; as well as introducing the basics, the exhaustive list of references included will aid their future research. It is also a valuable reference for scientists and practitioners working in pattern recognition, signal processing, speech and image processing, data analysis and A.I.
