John B. Hampshire II, Barak A. Pearlmutter  Home/Search
Context Related
| unm.edu/~bap/paper...hire.bayes90.ps.gz Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: unm.edu/~bap/publications (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: This paper presents a number of proofs that equate the outputs of a Multi-Layer Perceptron (MLP) classifier and the optimal Bayesian discriminant function for asymptotically large sets of statistically independent training samples. Two broad classes of objective functions are shown to yield Bayesian discriminant performance. The first class are "reasonable error measures," which achieve Bayesian discriminant performance by engendering classifier outputs that asymptotically equate to a ... (Update)
Context of citations to this paper: More
...of error is minimized. Under certain circumstances, neural networks trained with BackProp will attempt to approximate this approach [10]. Now, since consistently assigns the most probable class to y, the probability distribution of Omega for a particular value of y, jY =...
...The first is modular design methods (for instance, of. 6, 7, 20, 21, 22] the second is Bayesian statistics (for instance, cf.[2, 1, 11, 12, 27]) and in pm ticular the Maximum A Poster ior i (MAP) classification rule (see [25] To this end we use the Pm tition Algorithm...
Cited by: More
Building Cost Functions Minimizing to Some Summary Statistics - Saerens (2000) (Correct)
Any Reasonable Cost Function Can be Used for A.. - Saerens, Latinne.. (2002) (Correct)
Learning to Predict Life and Death from Go Game Records - van der Werf, Winands.. (Correct)
Active bibliography (related documents): More All
0.3: Optimal Learning in Artificial Neural Networks: A Theoretical.. - Bianchini, Gori (Correct)
0.1: Equivalence Proofs for Multi-Layer Perceptron.. - Hampshire, II.. (1990) (Correct)
0.0: Neural Network Classification and Prior Class.. - Lawrence, Burns, Back.. (1998) (Correct)
Similar documents based on text: More All
0.9: Why Error Measures are Sub-Optimal for Training Neural.. - John Hampshire (1992) (Correct)
0.8: Differential Learning Leads to Efficient Neural Network.. - II, Kumar (1992) (Correct)
0.7: Differential Theory of Learning for Efficient Neural Network.. - II, Kuma (Correct)
Related documents from co-citation: More All
14: Neural Network Classifiers Estimate Bayesian a posteriori Probabilities (context) - Richard, Lippmann - 1991
10: Pattern classification and scene analysis (context) - Duda, Hart - 1973
9: A probabilistic approach to the understanding and training of neural network cla.. (context) - Gish - 1990
BibTeX entry: (Update)
J. B. II Hampshire and B. A. Perlmutter. Equivalence proofs for multilayer perceptron classifiers and the Bayesian discriminant function. Proceedings of the 1990 Connectionist Models Summer School, 1990. D. Touretzky, J. Elman, T. Sejnowski, and G. Hinton, eds. Morgan Kaufmann, San Mateo, CA. http://citeseer.ist.psu.edu/hampshire90equivalence.html More
@inproceedings{ hampshire90equivalence,
author = "J. B. {II} Hampshire and B. A. Perlmutter",
title = "Equivalence proofs for multilayer perceptron classifiers and the {B}ayesian discriminant function",
booktitle = ""Proceedings of the 1990 Connectionist Models Summer School, 1990. D. Touretzky, J. Elman, T. Sejnowski, and G. Hinton, eds. Morgan Kaufmann, San Mateo, {CA}."",
year = "1990",
url = "citeseer.ist.psu.edu/hampshire90equivalence.html" }
Citations (may not include all citations):2133 Pattern Classification and Scene Analysis (context) - Duda, Hart - 1973
357 Approximation by Superpositions of a Sigmoidal Function (context) - Cybenko - 1989
203 What Size Net Gives Valid Generalization (context) - Baum, Haussler - 1989
180 Connectionist Learning Procedures (context) - Hinton - 1987
110 Probability and Statistics (context) - DeGroot - 1986
65 Links Between Markov Models and Multilayer Perceptrons (context) - Bourlard, Wellekens - 1988
42 Pattern Classification Using Neural Networks (context) - Lippmann
41 Statistical Learning Networks: A Unifying View (context) - Barron - 1988
35 A Novel Objective Function for Improved Phoneme Recognition .. (context) - Waibel - 1990
29 A ProbabilisticApproach to the Understanding and Training of.. (context) - Gish - 1990
3 Minkowski-r BackPropagation: Learning in Connectionist Model.. (context) - Hanson, Burr - 1987
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.cs.unm.edu/~bap/publications.html): More
Relating Egomotion and Image Evolution - Pearlmutter, Gurvits (1995) (Correct)
VC Dimension of an Integrate-and-Fire Neuron Model - Zador (1996) (Correct)
Automatic Learning Rate Maximization by On-Line.. - LeCun, Simard.. (1992) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC