OPTIMIZATION OF RECOGNITION SYSTEM TRAINING,

Abstract

Several schemes are investigated for training pattern-recognition systems. A method is presented for analyzing the process of training a linear perceptron by means of oriented graphs. A statistical model is also introduced which permits one to minimize the length of the training sequence of a recognition system by means of series analysis.

Document Details

Document Type
Technical Report
Publication Date
Aug 07, 1969
Accession Number
AD0699224

Entities

People

  • T. Gergely
  • V. P. Medvedev

Organizations

  • National Air and Space Intelligence Center

Tags

DTIC Thesaurus Topics

  • Optimization
  • Pattern Recognition
  • Recognition
  • Sequences
  • Training

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms