Artificial neural networks, or simply called neural networks, refer to the
various mathematical models of human brain functions such as perception,
computation and memory. It is a fascinating scientific challenge of our time to
understand how the human brain works. Modeling neural networks facilitates
us in investigating the information processing occurred in brain in a
mathematical or computational manner. On this manifold, the complexity
and capability of modeled neural networks rely on our present understanding
of biological neural systems. On the other hand, neural networks provide
efficient computation methods in making intelligent machines in multidisciplinary
fields, e.g., computational intelligence, robotics and computer vision.
In the past two decades, research in neural networks has witnessed a great
deal of accomplishments in the areas of theoretical analysis, mathematical
modeling and engineering application. This book does not intend to cover all
the advances in all aspects, and for it is formidable even in attempting to do
so. Significant efforts are devoted to present the recent discoveries that the
authors have made mainly in feedforward neural networks, recurrent networks
and bio-inspired recurrent network studies. The covered topics include learning
algorithm, neuro-dynamics analysis, optimization and sensory information
processing, etc. In writing, the authors especially hope the book to be helpful
for the readers getting familiar with general methodologies of research in the
neural network areas, and to inspire new ideas in the concerned topics.
We received significant support and assistance from the Department of
Electrical and Computer Engineering, and we are especially grateful to the
colleagues in the Control & Simulation Lab and Zhang Yi’s CI lab, where
many simulation experiments and meaningful work were carried out.