Connectionist Models for Intelligent Computation

Abstract

This final report covers the work done by our group of neural network computing at the University of Maryland for the past three years. We studied the neural network's capability of processing temporal or sequential data. Recurrent neural networks were used to perform inference cn grammars. An external memory stack was constructed to work with the neural network to perform inferences on context free languages. And finally, a spatially homogeneous locally connected recurrent neural network that could simulate any given turing machine, including the universal Turing machine was devised. It is capable of performing universal computations and demonstrated the universal power of recurrent neural network architectures. To train these sequential neural net machine, we have investigated the forward propagating learning algorithms.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 28, 1994
Accession Number
ADA286436

Entities

People

  • H. H. Chen
  • Y. C. Lee

Organizations

  • University of Maryland

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence Software
  • Automata
  • Cognitive Science
  • Computational Science
  • Computations
  • Context Free Grammars
  • Information Systems
  • Language
  • Learning
  • Machines
  • Network Computing
  • Neural Networks
  • Probability
  • Recurrent Neural Networks
  • Signal Processing
  • Simulations
  • Training

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks