Efficient perceptron learning using constrained steepest descent

An algorithm is proposed for training the single-layered perceptron. The algorithm follows successive steepest descent directions with respect to the perceptron cost function, taking care not to increase the number of misclassified patterns. The problem of finding these directions is stated as a qua...

Full description

Saved in:
Bibliographic Details
Published in:Neural networks 2000-04, Vol.13 (3), p.351-364
Main Authors: Perantonis, S.J., Virvilis, V.
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Feasible directions
Learning algorithm
Models, Neurological
Neural Networks (Computer)
Perceptron
Quadratic programming
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:An algorithm is proposed for training the single-layered perceptron. The algorithm follows successive steepest descent directions with respect to the perceptron cost function, taking care not to increase the number of misclassified patterns. The problem of finding these directions is stated as a quadratic programming task, to which a fast and effective solution is proposed. The resulting algorithm has no free parameters and therefore no heuristics are involved in its application. It is proved that the algorithm always converges in a finite number of steps. For linearly separable problems, it always finds a hyperplane that completely separates patterns belonging to different categories. Termination of the algorithm without separating all given patterns means that the presented set of patterns is indeed linearly inseparable. Thus the algorithm provides a natural criterion for linear separability. Compared to other state of the art algorithms, the proposed method exhibits substantially improved speed, as demonstrated in a number of demanding benchmark classification tasks.
ISSN:0893-6080
1879-2782
DOI:10.1016/S0893-6080(00)00016-2