Approximation of chaotic shapes with tree-structured neural networks

Andras, Peter

Abstract

The approximation of highly irregular decision regions is a challenging problem in pattern recognition and classification. Existing neural networks require many neurons for approximating irregular decision regions. A new tree-structured neural network algorithm is proposed that does not suffer from this limitation. The network approximates irregular regions parsimoniously by using receptive fields having a special overlapping structure The performance of the proposed network is evaluated on an approximation task involving a highly irregular decision region defined by the Mandelbrot set. The results show that the tree-structured neural network approximates decision regions much more parsimoniously than Kohonen and reduced Coulomb-potential networks.

Citation

Andras, P. (1999). Approximation of chaotic shapes with tree-structured neural networks. In IJCNN'99: International Joint Conference on Neural Networks, Proceedings (817-820). https://doi.org/10.1109/IJCNN.1999.831056

• Conference Name: IJCNN'99: International Joint Conference on Neural Networks
• Conference Location: Washington, DC, USA
• Start Date: Jul 10, 1999
• End Date: Jul 16, 1999
• Publication Date: 1999
• Deposit Date: Nov 23, 2021
• Publisher: Institute of Electrical and Electronics Engineers
• Volume: 2
• Pages: 817-820
• Series ISSN: 1098-7576
• Book Title: IJCNN'99: International Joint Conference on Neural Networks, Proceedings
• ISBN: 0-7803-5529-6
• DOI: https://doi.org/10.1109/IJCNN.1999.831056
• Public URL: http://researchrepository.napier.ac.uk/Output/2809187