Analog Computation in Neutral Systems: Architectures and Complexity

Abstract

First, we studied the representation problem for the class of single- hidden-layer feedforward networks, which is fundamental for understanding limitations of learning algorithms, and which also contributed to understanding the behavior of learning algorithms in applications involving low-complexity networks. The second kind of problem studied concerns dynamics behavior in neural networks containing feedback (trellis-structured networks in one particular applications). Our work focused on studying stability issues and exploring the implications of computational complexity theory. Third, the PAC learning paradigm (probably Almost Correct) was analyzed with the goal of characterizing the effects of statistically dependent sequences of training examples on learning performance. The goal of all these efforts was to discover and explore insights about fundamental limitations on the computational capabilities of analog neural systems and, where possible, of more general classes of physical systems as well.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 17, 1991
Accession Number
ADA237856

Entities

People

  • Bradley W. Dickinson

Organizations

  • Princeton University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Computational Complexity
  • Computations
  • Data Science
  • Differential Equations
  • Dynamics
  • Electrical Engineering
  • Engineering
  • Feedback
  • Information Science
  • Learning
  • Neural Networks
  • Sequences
  • Signal Processing
  • Training

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks