Abstract | ||
---|---|---|
The inherent fault tolerance of artificial neuralnetworks (ANNs) is usually assumed, but severalauthors have claimed that ANNs are not always faulttolerant and have demonstrated the need to evaluatetheir robustness by quantitative measures. For thispurpose, various alternatives have been proposed. Inthis paper we show the direct relation between themean square error (MSE) and the statisticalsensitivity to weight deviations, defining a measureof tolerance based on statistical sentitivity that wehave called Mean Square Sensitivity (MSS); this allowsus to predict accurately the degradation of the MSEwhen the weight values change and so constitutes auseful parameter for choosing between differentconfigurations of MLPs. The experimental resultsobtained for different MLPs are shown and demonstratethe validity of our model. |
Year | DOI | Venue |
---|---|---|
1999 | 10.1023/A:1018733418248 | Neural Processing Letters |
Keywords | Field | DocType |
mean square error degradation,multilayer perceptron,fault tolerance,statistical sensitivity | Mean square,Pattern recognition,Mean squared error,Robustness (computer science),Multilayer perceptron,Fault tolerance,Artificial intelligence,Statistical sensitivity,Artificial neural network,Machine learning,Mathematics | Journal |
Volume | Issue | ISSN |
10 | 2 | 1573-773X |
Citations | PageRank | References |
12 | 0.74 | 7 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jose L. Bernier | 1 | 36 | 1.66 |
J. Ortega | 2 | 940 | 73.05 |
M. M. Rodrì‘guez | 3 | 12 | 0.74 |
I. Rojas | 4 | 1750 | 143.09 |
A. Prieto | 5 | 419 | 25.23 |