A short proof of the posterior probability property of classifier neural networks

Authors:
Raúl Rojas
Affiliations:
Institut für Informatik, Freie Universität Berlin, Takustr. 9, 14195 Berlin, Germany
Venue:
Neural Computation
Year:
1996

Citing 2
Cited 9

Connectionist Speech Recognition: A Hybrid Approach

Connectionist Speech Recognition: A Hybrid Approach
Review:

Neural Computation

A Neural Network Based Model for Prognosis of Early Breast Cancer

Applied Intelligence
Stochastic Organization of Output Codes in Multiclass Learning Problems

Neural Computation
Risk-sensitive loss functions for sparse multi-category classification problems

Information Sciences: an International Journal
No-reference image quality assessment using modified extreme learning machine classifier

Applied Soft Computing
Probabilistic inference from arbitrary uncertainty using mixtures of factorized generalized gaussians

Journal of Artificial Intelligence Research
Online adaptive radial basis function networks for robust object tracking

Computer Vision and Image Understanding
Estimating the class posterior probabilities in protein secondary structure prediction

PRIB'11 Proceedings of the 6th IAPR international conference on Pattern recognition in bioinformatics
Texture segmentation using neural networks and multi-scale wavelet features

ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part II
Neural network based texture segmentation using a markov random field model

ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

It is now well known that neural classifiers can learn to compute a posteriori probabilities of classes in input space. This note offers a shorter proof than the traditional ones. Only one class has to be considered and straightforward minimization of the error function provides the main result. The method can be extended to any kind of differentiable error function. We also present a simple visual proof of the same theorem, which stresses the fact that the network must be perfectly trained and have enough plasticity.