Basin Sculpting a Hybrid Recurrent Feedforward Neural Network

Abstract

The architecture of a recurrent neural-network-based content-addressable memory is detailed along with companion training algorithm. The memory is designed to store vectors composed of strings of the integers 1 through 9. The performance characteristics of the model-memory capacity and basin size-are presented.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1998
Accession Number
ADA336386

Entities

People

  • Michael J. Brabel

Organizations

  • United States Army Research Laboratory

Tags

Communities of Interest

  • C4I

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Content Addressable Memory
  • Education
  • Equations
  • Instructions
  • Military Research
  • Neural Networks
  • Recurrent Neural Networks
  • Training

Fields of Study

  • Computer science

Readers

  • Business Analytics
  • Computer Programming and Software Development.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks