Robustness in multilayer perceptrons

Authors:
P. Kerlirzin;F. Vallet
Affiliations:
Laboratoire Central de Recherches, Thomson-CSF 91404 Orsay (Cedex), France;Laboratoire Central de Recherches, Thomson-CSF 91404 Orsay (Cedex), France
Venue:
Neural Computation
Year:
1993

Citing 2
Cited 1

Parallel distributed processing: explorations in the microstructure of cognition, vol. 2: psychological and biological models

Parallel distributed processing: explorations in the microstructure of cognition, vol. 2: psychological and biological models
Distributed representations

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

Robust learning approach for neuro-inspired nanoscale crossbar architecture

ACM Journal on Emerging Technologies in Computing Systems (JETC) - Special Issue on Reliability and Device Degradation in Emerging Technologies and Special Issue on WoSAR 2011

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we study the robustness of multilayer networks versus the destruction of neurons. We show that the classical backpropagation algorithm does not lead to optimal robustness and we propose a modified algorithm that improves this capability.