This book details the non-linear synapse neural network (NoSyNN). It also discusses the applications in computationally intensive tasks like graph coloring, ranking, and linear as well as quadratic programming.

This book aims to present a viable alternative to the Hopfield Neural Network (HNN) model for analog computation. It is well known the standard HNN suffers from problems of convergence to local minima, and requirement of a large number of neurons and synaptic weights. Therefore, improved solutions are needed. The non-linear synapse neural network (NoSyNN) is one such possibility and is discussed in detail in this book. This book also discusses the applications in computationally intensive tasks like graph coloring, ranking, and linear as well as quadratic programming. The material in the book is useful to students, researchers and academician working in the area of analog computation.

First dedicated book on non-linear feedback neural networks Contains thorough discussion on transcendental energy function Includes special chapter on Hopfield Network, its applications, and limitations Cadence OrCAD circuit files for all the circuit simulations discussed in the book Useful material for researchers working in the area of analog computation

Autorentext

Dr. Mohammad Samar Ansari is an Assistant Professor of the Department of Electronics Engineering at Aligarh Muslim University, Aligarh, India. Before this he worked at the same university as a Lecturer and Guest Faculty from September 2004. Dr. Ansari also worked with Defense Research Development Organization (DRDO) and Siemens Limited during the years 2001-2003. He obtained PhD in 2012 (thesis title: Neural Circuits for Solving Linear Equations with Extensions for Mathematical Programming), and completed MTech (Electronics Engineering) in 2007 and BTech (Electronics Engineering) in 2001 from the same university. He has published 15 international journal papers and more than 30 international and national conference papers. He is a Life Member of The Institution of Electronics and Telecommunication Engineers (IETE), India.

Inhalt

Introduction.- Background.- Voltage-mode Neural Network for the Solution of Linear Equations.- Mixed-mode Neural Circuit for Solving Linear Equations.- Non-Linear Feedback Neural Circuits for Linear and Quadratic Programming.- OTA-based Implementations of Mixed-mode Neural Circuits.- Appendix A: Mixed-mode Neural Network for Graph Colouring.- Appendix B: Mixed-mode Neural Network for Ranking.