Neural Networks and Learning Machines

Neural Networks and Learning Machines

Third Edition

Simon Haykin

McMaster University, Canada

This third edition of a classic book presents a comprehensive treatment of neural networks and learning machines. These two pillars that are closely related. The book has been revised extensively to provide an up-to-date treatment of a subject that is continually growing in importance. Distinctive features of the book include:

• On-line learning algorithms rooted in stochastic gradient descent; small-scale and large-scale learning problems.

• Kernel methods, including support vector machines, and the representer theorem.

• Information-theoretic learning models, including copulas, independent components analysis (ICA), coherent ICA, and information bottleneck.

• Stochastic dynamic programming, including approximate and neurodynamic procedures.

• Sequential state-estimation algorithms, including Kalman and particle filters.

• Recurrent neural networks trained using sequential-state estimation algorithms.

• Insightful computer-oriented experiments.

Just as importantly, the book is written in a readable style that is Simon Haykin’s hallmark.

This book presents the first comprehensive treatment of neural networks from an engineering perspective. Thorough, well-organized, and completely up-to-date, it examines all the important aspects of this emerging technology.