Abstract | ||
---|---|---|
This paper presents a study of the influence of perturbations in the parameters of a functional network. A quantitative measure is introduced, related to the change in the mean squared error when noise is applied to the network parameters. This measure, based on statistical sensitivity, provides a fault tolerance estimate for a functional network and allows the performance degradation of this kind of system to be predicted. It can be used, therefore, to evaluate performance differences between the training process carried out on a computer and its hardware implementation. The experimental results obtained for different functional network architectures and a feedforward multilayer neural network confirm the validity of the proposed model. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1016/j.neucom.2004.03.011 | Neurocomputing |
Keywords | Field | DocType |
Statistical sensitivity,Fault tolerance,Parameter perturbation,Functional networks,Neural networks | Computer science,Functional networks,Network architecture,Mean squared error,Probabilistic neural network,Fault tolerance,Artificial intelligence,Statistical sensitivity,Artificial neural network,Machine learning,Feed forward | Journal |
Volume | Issue | ISSN |
62 | C | 0925-2312 |
Citations | PageRank | References |
5 | 0.46 | 22 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Oscar Fontenla-Romero | 1 | 337 | 39.49 |
Enrique Castillo | 2 | 555 | 59.86 |
Amparo Alonso-Betanzos | 3 | 885 | 76.98 |
Bertha Guijarro-Berdiñas | 4 | 296 | 34.36 |