Constructive recursive deterministic perceptron neural networks with genetic algorithms

Date

2013

Advisors

Journal Title

Journal ISSN

ISSN

0218-0014
1793-6381

Volume Title

Publisher

Type

Article

Peer reviewed

Yes

Abstract

The Recursive Deterministic Perceptron is a generalisation of the single layer perceptron neural network. This neural network can separate, in a deterministic manner, any classification problem (linearly separable or not). It relies on the principle that in any non linearly separable two-class classification problem, a linearly separable subset of one or more points belonging to one of the two classes can always be found. Small network topologies can be obtained when the linearly separable subsets are of maximum cardinality. This is referred to as the problem of Maximum Separability and has been proven to be NP-Complete. Evolutionary computing techniques are applied to handle this problem in a more efficient way than the standard approaches in terms of complexity. These techniques enhances the RDP training in terms of speed of conversion and level of generalisation. They provide an alternative to tackle large classification problems which is otherwise not feasible with the algorithmic versions of the RDP training methods.

Description

Keywords

Neural Networks, Evolutionary Computing, Linear Separability, Classification

Citation

Elizondo, D.A., Morris, R., Watson, T. and Passow, B.N. (2013) Constructive recursive deterministic perceptron neural networks with genetic algorithms. International Journal of Pattern Recognition and Artificial Intelligence, 27 (6) art. no. 1350019

Rights

Research Institute

Institute of Artificial Intelligence (IAI)