Publication details
Direct Approaches to Improving the Robustness of Multilayer Neural Networks
| Authors | |
|---|---|
| Year of publication | 1992 |
| Type | Article in Proceedings |
| Conference | Artificial Neural Networks II: Proceedings of the International Conference on Artificial Neural Networks ICANN 1999 |
| MU Faculty or unit | |
| Citation | |
| Web | http://www.fi.muni.cz/usr/sojka/publ.html |
| Field | Use of computers, robotics and its application |
| Keywords | multilayer perceptron; back propagation; robustness of neural nets |
| Description | Multilayer neural networks trained with backpropagation are in general not robust against the loss of a hidden neuron. In this paper we define a form of robustness called 1-node robustness and propose methods to improve it. One approach is based on modification of the error function by the addition of a ``robustness error''. It leads to more robust networks but at the cost of a reduced accuracy. A second approach, ``pruning-and-duplication'', consists of duplicating the neurons whose loss is the most damaging for the network. Pruned neurons are used for the duplication. This procedure leads to robust and accurate networks at low computational cost. It may also prove beneficial for generalisation. |