Continuous learning: a design methodology for fault-tolerant neural networks

Authors:
Vincenzo Piuri
Affiliations:
Department of Electronics, Politecnico di Milano, piazza L. da Vinci 32, 120133 Milano, Italy
Venue:
IEA/AIE '90 Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2
Year:
1990

Citing 4
Cited 0

Fault Tolerance Techniques for Systolic Arrays

Computer
Neurocomputing: foundations of research

Neurocomputing: foundations of research
Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

Fault tolerance in artificial neural networks is an important feature, in particular when the application is critical or when maintenance is difficult. This paper presents a general design methodology for designing fault-tolerant architectures, starting from the behavioral description of the nominal network and from the nominal algorithm. The behavioral level is considered to detect errors due to hardware faults, while system survival is guaranteed by the reactivation of learning mechanisms of the nominal network. An example of the use of this methodology is presented and evaluated.