A neural model for multi-expert architectures

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

We present a generalization of conventional artificial neural networks that allows for a functional equivalence to multi-expert systems. The new model provides an architectural freedom going beyond existing multi-expert models and an integrative formalism to compare and combine various techniques of learning. (We consider gradient, EM, reinforcement, and unsupervised learning.) Its uniform representation aims at a simple genetic encoding and evolutionary structure optimization of multi-expert systems. This paper contains a detailed description of the model and learning rules, empirically validates its functionality, and discusses future perspectives.
LaTeX, 8 pages, 5 figures

Keywords

Adaptation and Self-Organizing Systems, Disordered Systems and Neural Networks, Neural and Evolutionary Computing

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/80173

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/nlin/0202039
 http://arxiv.org/abs/nlin/0202039
 Proceedings of the International Joint Conference on Neural Networks (IJCNN 2002), 2755-2760.

Collections

arXiv