Improving Upon Standard Pattern Classification Algorithms by Implementing them as Multi-Layer Perceptrons

Abstract

The multi-layer perceptron (MLP) is a type of adaptive layered network often used as a pattern classifier. In more recent literature, MLPs are compared with simpler classification techniques using common datasets. We select two of these simple static pattern classification algorithms and briefly review the relevant techniques. After introducing a modest set of evaluation databases, the performance of the standard classifiers and MLPs are assessed. A technique for implementing the two standard classifiers as MLPs is presented and this novel approach is used to automatically design a 'good' set of initial weights for the MLP networks. Encouraging experimental results for these hybrid techniques are shown for illustration. Keywords: Pattern recognition; Speech; Images; Artificial intelligence.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 12, 1989
Accession Number
ADA220046

Entities

People

  • M. D. Bedworth

Organizations

  • Royal Signals and Radar Establishment

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Boundaries
  • Classification
  • Covariance
  • Data Sets
  • Frequency
  • Machine Learning
  • Network Topology
  • Pattern Recognition
  • Radar Signals
  • Recognition
  • Spectra
  • Standards
  • Step Functions
  • Test Sets
  • Training
  • Word Recognition

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks