When Networks Disagree: Ensemble Methods for Hybrid Neural Networks

Abstract

This paper presents a general theoretical framework for ensemble methods of constructing significantly improved regression estimates. Given a population of regression estimators, the authors construct a hybrid estimator that is as good or better in the mean square error sense than any estimator in the population. They argue that the ensemble method presented has several properties: (1) it efficiently uses all the networks of a population -- none of the networks need to be discarded; (2) it efficiently uses all of the available data for training without over-fitting; (3) it inherently performs regularization by smoothing in functional space, which helps to avoid over-fitting; (4) it utilizes local minima to construct improved estimates whereas other neural network algorithms are hindered by local minima; (5) it is ideally suited for parallel computation; (6) it leads to a very useful and natural measure of the number of distinct estimators in a population; and (7) the optimal parameters of the ensemble estimator are given in closed form. Experimental results show that the ensemble method dramatically improves neural network performance on difficult real-world optical character recognition tasks.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 27, 1992
Accession Number
ADA260045

Entities

People

  • Leon Cooper
  • Michael P. Perrone

Organizations

  • Brown University

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Character Recognition
  • Classification
  • Computations
  • Computing System Architectures
  • Data Sets
  • Estimators
  • Information Processing
  • Information Systems
  • Military Research
  • Neural Networks
  • New York
  • Optical Character Recognition
  • Parallel Computing
  • Recognition
  • United States

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Statistical inference.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks
  • Space