By the same authors

From the same journal

Fast learning neural networks using Cartesian genetic programming

Research output: Contribution to journalArticle

Author(s)

Department/unit(s)

Publication details

JournalNeurocomputing
DateE-pub ahead of print - 15 May 2013
DatePublished (current) - 9 Dec 2013
Volume121
Number of pages16
Pages (from-to)274-289
Early online date15/05/13
Original languageEnglish

Abstract

A fast learning neuroevolutionary algorithm for both feedforward and recurrent networks is proposed. The method is inspired by the well known and highly effective Cartesian genetic programming (CGP) technique. The proposed method is called the CGP-based Artificial Neural Network (CGPANN). The basic idea is to replace each computational node in CGP with an artificial neuron, thus producing an artificial neural network. The capabilities of CGPANN are tested in two diverse problem domains. Firstly, it has been tested on a standard benchmark control problem: single and double pole for both Markovian and non-Markovian cases. Results demonstrate that the method can generate effective neural architectures in substantially fewer evaluations in comparison to previously published neuroevolutionary techniques. In addition, the evolved networks show improved generalization and robustness in comparison with other techniques. Secondly, we have explored the capabilities of CGPANNs for the diagnosis of Breast Cancer from the FNA (Finite Needle Aspiration) data samples. The results demonstrate that the proposed algorithm gives 99.5% accurate results, thus making it an excellent choice for pattern recognitions in medical diagnosis, owing to its properties of fast learning and accuracy.

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations