Abstract | ||
---|---|---|
In this paper a study of the influence of input perturbations on a functional network is presented. A quantitative measure, related to the mean squared error degradation in presence of input noise, is introduced. This measure, based on statistical sensitivity, provides an estimation of the generalization ability and noise immunity of functional networks and lets to predict the performance degradation of a functional network. The experimental results corroborated the validity of the proposed model. |
Year | DOI | Venue |
---|---|---|
2001 | 10.1007/3-540-45720-8_33 | IWANN (1) |
Keywords | Field | DocType |
functional networks,generalization ability,input perturbation,noise immunity,performance degradation,functional network,error degradation,quantitative measure,input noise,mean square error | Pattern recognition,Computer science,Functional networks,Mean squared error,Artificial intelligence,Statistical sensitivity,Noise immunity | Conference |
ISBN | Citations | PageRank |
3-540-42235-8 | 2 | 0.40 |
References | Authors | |
7 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Enrique Castillo | 1 | 555 | 59.86 |
Oscar Fontenla-Romero | 2 | 337 | 39.49 |
Bertha Guijarro-Berdiñas | 3 | 296 | 34.36 |
Amparo Alonso-Betanzos | 4 | 885 | 76.98 |