A low-sensitivity recurrent neural network
Neural Computation
Neural Networks - 2003 Special issue: Neural network analysis of complex scientific data: Astronomy and geosciences
Neural Networks and Metabolic Networks: Fault Tolerance and Robustness Features
Proceedings of the 2009 conference on Neural Nets WIRN09: Proceedings of the 19th Italian Workshop on Neural Nets, Vietri sul Mare, Salerno, Italy, May 28--30 2009
Hi-index | 0.00 |
In this paper, we address the problem of robustness in multilayer perceptrons. We present the main theoretical results in the case of linear neural networks with one hidden layer in order to go beyond the empirical study we previously made. We show that the robustness can greatly be improved and that even without decreasing performance in normal use. Finally, we show how this behavior, clearly demonstrated in the linear case, is an approximation of the behavior of nonlinear networks