Neural Networks - a Review fro a Statistical Perspective

Cheng, Bing and Titterington, D.M. (1994) Neural Networks - a Review fro a Statistical Perspective. Statistical Science, 9 (1). pp. 2-30. ISSN 0883-4237. (The full text of this publication is not available from this repository)

The full text of this publication is not available from this repository. (Contact us about this Publication)
Official URL
http://dx.doi.org/10.1214/ss/1177010638

Abstract

This paper informs a statistical readership about Artificial Neural Networks (ANNs), points out some of the links with statistical methodology and encourages cross-disciplinary research in the directions most likely to bear fruit. The areas of statistical interest are briefly outlined, and a series of examples indicates the flavor of ANN models. We then treat various topics in more depth. In each case, we describe the neural network architectures and training rules and provide a statistical commentary. The topics treated in this way are perceptrons (from single-unit to multilayer versions), Hopfield-type recurrent networks (including probabilistic versions strongly related to statistical physics and Gibbs distributions) and associative memory networks trained by so-called unsupervised learning rules. Perceptrons are shown to have strong associations with discriminant analysis and regression, and unsupervized networks with cluster analysis. The paper concludes with some thoughts on the future of the interface between neural networks and statistics.

Item Type: Review
Uncontrolled keywords: ARTIFICIAL NEURAL NETWORKS; ARTIFICIAL INTELLIGENCE; STATISTICAL PATTERN RECOGNITION; DISCRIMINANT ANALYSIS; NONPARAMETRIC REGRESSION; CLUSTER ANALYSIS; INCOMPLETE DATA; GIBBS DISTRIBUTIONS
Subjects: H Social Sciences > HA Statistics
Divisions: Faculties > Science Technology and Medical Studies > School of Mathematics Statistics and Actuarial Science > Statistics
Depositing User: P. Ogbuji
Date Deposited: 02 Jul 2009 18:41
Last Modified: 18 Jul 2014 10:21
Resource URI: http://kar.kent.ac.uk/id/eprint/20438 (The current URI for this page, for reference purposes)
  • Depositors only (login required):