Neural Networks- A Classroom Approach

Part I: Traces of History and a Neuroscience Briefer 1
Chapter 1: The Brain Metaphor
Chapter 2: Lessons from Neuroscience
Part II: Feedforward Neural Networks and Supervised Learning
Chapter 3: Artificial Neurons, Neural Networks and Architectures
Chapter 4: Geometry of Binary Threshold Neurons and Their Networks
Chapter 5: Supervised Learning I: Perceptrons and LMS
Chapter 6: Supervised Learning II: Backpropagation and Beyond
Chapter 7: Neural Networks: A Statistical Pattern Recognition Perspective
Chapter 8: Statistical Learning Theory, Support Vector Machines and Radial Basis Function Networks
Part III: Recurrent Neurodynamical Systems and Unsupervised Learning
Chapter 9: Dynamical Systems Review
Chapter 10: Attractor Neural Networks
Chapter 11: Adaptive Resonance Theory
Chapter 12: Towards the Self-organizing Feature Map
Part IV: Contemporary Topics
Chapter 13: Fuzzy Sets and Fuzzy Systems
Chapter 14: Evolutionary Algorithms
Chapter 15: Soft Computing Goes Hybrid
Chapter 16: Frontiers of Research: Spiking and Quantum Neural Networks

This revised edition of Neural Networks is an up-to-date exposition of the subject andcontinues to provide an understanding of the underlying geometry of foundation neuralnetwork models while stressing on heuristic explanations of theoretical results. Thehighlight of this book is its easy-to-read format and a balanced mix of both theory andpractice, without compromising on the requisite mathematical rigor. Professor Kumar,in this book, has successfully maintained excellent pictorial description integrated withthe concepts and interesting pedagogy to render sound learning.