Differential learning leads to efficient neural network classifiers

Authors:
J. B. Hampshire, II;B. V. K. Vijaya Kumar
Affiliations:
Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA;Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA
Venue:
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: plenary, special, audio, underwater acoustics, VLSI, neural networks - Volume I
Year:
1993

Citing 6
Cited 0

A theory of the learnable

Communications of the ACM
Optimal brain damage

Advances in neural information processing systems 2
Machine learning: a theoretical approach

Machine learning: a theoretical approach
A training algorithm for optimal margin classifiers

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Neural networks and the bias/variance dilemma

Neural Computation
A differential theory of learning for efficient statistical pattern recognition

A differential theory of learning for efficient statistical pattern recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

We outline a differential theory of learning for statistical pattern classification. The theory is based on classification figure-of-merit (CFM) objective functions, described in [9]. We outline the proof that differential learning is efficient, requiring the least classifier complexity and the smallest training sample size necessary to achieve Bayesian (i.e., minimum error) discrimination. We conclude with a practical application of the theory in which a simple differentially trained linear neural network classifier discriminates handwritten digits of the AT&T DB1 database with a 1.3% error rate. This error rate is less than one half the best previous result for a linear classifier on this optical character recognition (OCR) task [1].