Unsupervised adaptation to improve fault tolerance of neural network classifiers | IEEE Conference Publication | IEEE Xplore

Unsupervised adaptation to improve fault tolerance of neural network classifiers


Abstract:

We investigate how to exploit the dynamics of unsupervised online learning rules for fault tolerance in neural network classifiers. We first design an adaptation mechanis...Show More

Abstract:

We investigate how to exploit the dynamics of unsupervised online learning rules for fault tolerance in neural network classifiers. We first design an adaptation mechanism that keeps neural network weights at a useful fixed point for classification problems. We then demonstrate the robustness of the system when the network inputs are subjected to faults.
Date of Conference: 26-26 June 2004
Date Added to IEEE Xplore: 12 July 2004
Print ISBN:0-7695-2145-2
Conference Location: Seattle, WA, USA

References

References is not available for this document.