Cellular Neural Networks and Visual Computing: Foundations and Applications

Note: Supplemental materials are not guaranteed with Rental or Used book purchases.

ISBN: 9780521652476 | 0521652472
Cover: Hardcover
Copyright: 6/10/2002

Rent

(Recommended)

$107.72

Term

Due

Price

Semester

Dec 13

$119.69

Quarter

Sep 14

$113.70

Short Term

Aug 16

$107.72

*This item is part of an exclusive publisher rental program and requires an additional convenience fee. This fee will be reflected in the shopping cart.
Buy Used

Usually Ships in 2-4 Business Days

$122.01
Buy New

Special Order: 1-2 Weeks

$163.52
eBook

Available Instantly

Online: 1825 Days

Downloadable: Lifetime Access

$111.36

Cellular Nonlinear/Neural Network (CNN) technology is both a revolutionary concept and an experimentally proven new computing paradigm. Analogic cellular computers based on CNNs are set to change the way analog signals are processed. This unique undergraduate level textbook includes many examples and exercises, including CNN simulator and development software accessible via the Internet. It is an ideal introduction to CNNs and analogic cellular computing for students, researchers and engineers from a wide range of disciplines. Leon Chua, co-inventor of the CNN, and Tamàs Roska are both highly respected pioneers in the field.

Acknowledgements

Introduction

(6)

Notation, definitions, and mathematical foundation

(28)

Basic notation and definitions

(7)

Mathematical foundations

(21)

Characteristics and analysis of simple CNN templates

(65)

Two case studies: the EDGE and EDGEGRAY templates

(14)

Three quick steps for sketching the shifted DP plot

(1)

Some other useful templates

(50)

Simulation of the CNN dynamics

100

(15)

Integration of the standard CNN differential equation

100

(1)

Image input

101

(1)

Software simulation

102

(8)

Digital hardware accelerators

110

(1)

Analog CNN implementations

111

(2)

Scaling the signals

113

(1)

Discrete-time CNN (DTCNN)

114

(1)

Binary CNN characterization via Boolean functions

115

(24)

Binary and universal CNN truth table

115

(7)

Boolean and compressed local rules

122

(2)

Optimizing the truth table

124

(15)

Uncoupled CNNs: unified theory and applications

139

(44)

The complete stability phenomenon

139

(1)

Explicit CNN output formula

140

(2)

Proof of completely stable CNN theorem

142

(13)

The primary CNN mosaic

155

(1)

Explicit formula for transient waveform and settling time

156

(5)

Which local Boolean functions are realizable by uncoupled CNNs?

161

(1)

Geometrical interpretations

162

(4)

How to design uncoupled CNNs with prescribed Boolean functions

166

(7)

How to realize non-separable local Boolean functions?

173

(10)

Introduction to the CNN Universal Machine

183

(22)

Global clock and global wire

184

(1)

Set inclusion

184

(4)

Translation of sets and binary images

188

(2)

Opening and closing and implementing any morphological operator

190

(5)

Implementing any prescribed Boolean transition function by not more than 256 templates

195

(3)

Minimizing the number of templates when implementing any possible Boolean transition function

198

(3)

Analog-to-digital array converter

201

(4)

Back to basics: Nonlinear dynamics and complete stability

205

(34)

A glimpse of things to come

205

(1)

An oscillatory CNN with only two cells

205

(5)

A chaotic CNN with only two cells and one sinusoidal input

210

(4)

Symmetric A template implies complete stability

214

(5)

Positive and sign-symmetric A template implies complete stability

219

(5)

Positive and cell-linking A template implies complete stability

224

(7)

Stability of some sign-antisymmetric CNNs

231

(8)

Appendix to Chapter 8

236

(3)

The CNN Universal Machine (CNN-UM)

239

(19)

The architecture

240

(4)

A simple example in more detail

244

(2)

A very simple example on the circuit level

246

(8)

Language, compiler, operating system

254

(4)

Template design tools

258

(9)

Various design techniques

258

(2)

Binary representation, linear separability, and simple decomposition

260

(4)

Template optimization

264

(1)

Template decomposition techniques

265

(2)

CNNs for linear image processing

267

(9)

Linear image processing with B templates is equivalent to spatial convolution with FIR kernels

267

(2)

Spatial frequency characterization

269

(3)

A primer on properties and applications of discrete-space Fourier transform (DSFT)

272

(1)

Linear image processing with A and B templates is equivalent to spatial convolution with IIR kernels

272

(4)

Coupled CNN with linear synaptic weights

276

(14)

Active and inactive cells, dynamic local rules

278

(5)

Binary activation pattern and template format

283

(1)

A simple propagating type example with B/W symmetrical rule

284

(2)

The connectivity problem

286

(4)

Uncoupled standard CNNs with nonlinear synaptic weights

290

(6)

Dynamic equations and DP plot

291

(5)

Standard CNNs with delayed synaptic weights and motion analysis

296

(8)

Dynamic equations

296

(1)

Motion analysis-discrete time and continuous time image acquisition

297

(7)

Visual microprocessors-analog and digital VLSI implementation of the CNN Universal Machine

304

(16)

The analog CNN core

304

(6)

Analogic CNN-UM cell

310

(2)

Emulated digital implementation

312

(1)

The visual microprocessor and its computational infrastructure

313

(5)

Computing power comparison

318

(2)

CNN models in the visual pathway and the ``Bionic Eye''

320

(19)

Receptive field organization, synaptic weights, and cloning template

321

(1)

Some prototype elementary functions and CNN models of the visual pathway

322

(7)

A simple qualitative ``engineering'' model of a vertebrate retina

329

(9)

The ``Bionic Eye'' implemented on a CNN Universal Machine

338

(1)

Notes

339

(9)

Bibliography

348

(13)

Exercises

361

(28)

Appendices

389

(1)

Index

390

Please wait while the item is added to your bag...

FREE SHIPPING

Amazon no longer offers textbook rentals. We do!

Cellular Neural Networks and Visual Computing: Foundations and Applications

Summary

Table of Contents

Supplemental Materials