Dimensionality-Reduction Using Connectionist Networks,

Abstract

A method is presented for using connectionist networks of simple computing elements to discover a particular type of constraint in multidimensional data. Suppose that some data source provides samples consisting of n dimensional feature vectors, but that this data all happens to lie on an m dimensional surface embedded in the n dimensional feature space. Then occurrences of data can be more concisely described by specifying an m dimensional location on the embedded surface than by reciting all n components of the feature vector. The recording of data in such a way is known as dimensional reduction. This paper describes a method for performing dimensionality reduction in a wide class of situations for which an assumption of linearity need not be made about the underlying constraint surface. The method takes advantage of self organizing properties of connectionist networks of simple computing elements. We present a scheme for representing the values of continuous (scalar) variables in subsets of units. The back propagation weight updating method for training connectionist networks is extended by the use of auxiliary pressure in order to coax hidden units into the prescribed representation for scalar valued variables.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1987
Accession Number
ADA183632

Entities

People

  • Eric Saund

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Coding
  • Computer Vision
  • Contracts
  • Coordinate Systems
  • Dimensionality Reduction
  • Information Systems
  • Machine Learning
  • Massachusetts
  • Military Research
  • Neural Networks
  • Pattern Recognition
  • Self Organizing Systems
  • Training
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Calculus or Mathematical Analysis
  • Neural Network Machine Learning.

Technology Areas

  • Space