Explicit State Vector Representation for Heteroassociative Memories

Abstract

In summary, it has been shown that the commutative correlation operator used in most linear associative memory (AM) models enforces symmetries that preclude the learning of several classes of important mapping functions. It has also been shown, however, that these symmetries can be eliminated simply by using a different information representation scheme. The explicit state (ES) representation has been proposed as an alternative to the commonly used bipolar form and has been demonstrated to permit standard AM architectures to learn nonlinear mappings. In particular, it has been shown that the ES representation permits first-order AM models to learn nonlinear transformations of the form y = xT + b. This characterization is important because its properties are directly amenable to analysis by using the known properties of affine transformation. For example, it has been noted that this transformation renders the ES formulation immune to the effects of constant additive noise. It has also been shown that the ES representation can be easily generalized for the use of higher order correlation information.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 21, 1990
Accession Number
ADA229757

Entities

People

  • Jeffrey Uhlmann

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Additives (Chemicals)
  • Battle Management
  • Classification
  • Computational Complexity
  • Computers
  • Content Addressable Memory
  • Information Systems
  • Learning
  • Measurement
  • Military Research
  • Neural Networks
  • Probability
  • Security
  • Standards
  • Symmetry

Readers

  • Calculus or Mathematical Analysis
  • Environmental Remediation and Restoration.
  • Neural Network Machine Learning.