Optical Neural Networks

1. Front Matter

   Pages I-XIV

   PDF

2. Background for Optical Neural Networks

   1. Front Matter

      Pages 1-1

      PDF

   2. Introduction

      • Cornelia Denz

      Pages 3-13

   3. The Principles of Neural Networks

      • Cornelia Denz

      Pages 14-70

   4. Basic Concepts of Nonlinear and Photorefractive Optics

      • Cornelia Denz

      Pages 71-112

3. Devices, Components and Subsystems

   1. Front Matter

      Pages 113-113

      PDF

   2. Nonlinear Optical Storage and Interconnection Concepts

      • Cornelia Denz

      Pages 115-215

   3. Nonlinear Thresholding

      • Cornelia Denz

      Pages 216-243

   4. Further Computing Elements

      • Cornelia Denz

      Pages 244-296

4. Concepts, Architectures and Complex Systems

   1. Front Matter

      Pages 297-297

      PDF

   2. Associative Memories

      • Cornelia Denz

      Pages 299-333

   3. Optical Realizations of Perceptron-like Neural Networks

      • Cornelia Denz

      Pages 334-349

   4. Optical Realizations of Multilayer Perceptrons

      • Cornelia Denz

      Pages 350-376

   5. Optical Realizations of Self-Organizing Neural Networks

      • Cornelia Denz

      Pages 377-392

   6. Optical Realizations of Hopfield and Boltzmann Neural Networks

      • Cornelia Denz

      Pages 393-420

   7. Optical Realizations of Adaptive Resonance Theory Networks

      • Cornelia Denz

      Pages 421-433

   8. Outlook

      • Cornelia Denz

      Pages 434-434

5. Back Matter

   Pages 435-458

   PDF

In recent years, there has been a rapid expansion in the field of nonlinear optics as weIl as in the field of neural computing. Up to date, no one would doubt that nonlinear optics is one of the most promising fields of realizing large neural network models due to their inherent parallelism, the use of the speed of light and their ability to process two-dimensional data arrays without carriers or transformation bottlenecks. This is the reason why so many of the interesting applications of nonlinear optics - associative memories, Hopfield networks and self-organized nets - are realized in an all optical way using nonlinear optical processing elements. Both areas attracting people from a wide variety of disciplines and judged by the proliferation of published papers, conferences, international collaborations and enterprises, more people than ever before are now in­ volved in research and applications in these two fields. These people all bring a different background to the area, and one of the aims of this book is to provide a common ground from which new development can grow. Another aim is to explain the basic concepts of neural computation as weIl as its nonlinear optical realizations to an interested audi­ ence. Therefore, the book is about the whole field of optical neural network applications, covering all the major approaches and their important results. Especially, it its an in­ troduction that develops the concepts and ideas from their simple basics through their formulation into powerful experimental neural net systems.

• development
• implementation
• network
• networks
• neural networks
• optics
• techniques

• Institut für Angewandte Optik, AG Photorefraktive Optik, Technische Universität Darmstadt, Darmstadt, Germany

  Cornelia Denz

Dr. Cornelia Denz arbeitet am Institut für Angewandte Physik der Technischen Hochschule Darmstadt.

Policies and ethics