Evolving Recurrent Perceptrons

Abstract

This work investigates the application of evolutionary programming, a multi-agent stochastic search technique, to the generation of recurrent perceptions (nonlinear IIR filters) for time-series prediction tasks. The evolutionary programming paradigm is discussed and analogies are made to classical stochastic optimization methods. A hybrid optimization scheme is proposed based on multi-agent and single-agent random optimization techniques. This method is then used to determine both the model order and weight coefficients of linear, nonlinear, and parallel linear-nonlinear next-step predictors. The AIC is used as the cost function to score each candidate solution. Neural Networks, Evolutionary Programming, Signal Detection.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 1993
Accession Number
ADA273241

Entities

People

  • Don Waagen
  • John R. Mcdonnell

Organizations

  • Naval Command, Control and Ocean Surveillance Center

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Artificial Intelligence
  • Coefficients
  • Computer Programming
  • Demographic Cohorts
  • Differential Equations
  • Equations
  • Neural Networks
  • Nonlinear Differential Equations
  • Ocean Surveillance
  • Optimization
  • Random Variables
  • Signal Detection
  • Surveillance
  • Test Sets
  • Training

Fields of Study

  • Computer science
  • Engineering

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks