Dynamics of Analog Electronic Neural Networks

Abstract

We review recent results on dynamics and stability of analog neural networks and discuss their application to associative memory and visual processing. Stability criteria for these networks, gaurantee convergence to fixed-point attractors under continuous-time and discrete-time, parallel updating. For associative memory, phase diagrams describing different attractor types are discussed, and it is shown that reducing analog transfer function steepness improves network performance. For visual processing, a two- dimensional, translation-invariant network is described. The network detects image features using a novel architecture that greatly reduces network wiring. Neural networks, Associative memory, Feature detection, Image processing, Analog computation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 31, 1992
Accession Number
ADA257019

Entities

People

  • Frederick R. Waugh

Organizations

  • Harvard University

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Analog Computers
  • Computer Vision
  • Computers
  • Computing System Architectures
  • Content Addressable Memory
  • Detectors
  • Diagrams
  • Dynamics
  • Equations
  • Image Processing
  • Neural Networks
  • Nonlinear Dynamics
  • Phase
  • Phase Diagrams
  • Scientists
  • Transfer Functions
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Computer Science/Computer Engineering/Data Science/Digital Signal Processing.
  • Mathematical Modeling and Probability Theory.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks
  • Microelectronics