Document Type

Article

Publication Date

11-1-2001

Publication Title

IEEE Transactions on Neural Networks

Abstract

The recursive training algorithm for the optimal interpolative (OI) classification network is extended to include distributed fault tolerance. The conventional OI Net learning algorithm leads to network weights that are nonoptimally distributed (in the sense of fault tolerance). Fault tolerance is becoming an increasingly important factor in hardware implementations of neural networks. But fault tolerance is often taken for granted in neural networks rather than being explicitly accounted for in the architecture or learning algorithm. In addition, when fault tolerance is considered, it is often accounted for using an unrealistic fault model (e.g., neurons that are stuck on or off rather than small weight perturbations). Realistic fault tolerance can be achieved through a smooth distribution of weights, resulting in low weight salience and distributed computation. Results of trained OI Nets on the Iris classification problem show that fault tolerance can be increased with the algorithm presented in this paper.

Original Citation

Simon, D.; , "Distributed fault tolerance in optimal interpolative nets," Neural Networks, IEEE Transactions on , vol.12, no.6, pp.1348-1357, Nov 2001 doi: 10.1109/72.963771

DOI

10.1109/72.963771

Version

Postprint

Volume

12

Issue

6