The effects of lesions on the generalization ability of a perceptron
D M L Barbato, José F. Fontanari · Journal of Physics A Mathematical and General · 1993
The authors investigate the effects of dilution (lesions) on the memorization and generalization abilities of a single-layer perceptron whose non-zero weights are constrained to take on binary (+or-1) values only. The diluted perceptron is trained to realize a Boolean linearly separable mapping generated by a fully connected perceptron. In the case where the training process is disturbed by noise and the vanishing weights are chosen so as to minimize the training error, one finds that the dilution can improve the storage capacity and the generalization ability of the network. If the weights are cut randomly, however, the dilution will always degrade the network's performance. In this case they show that the main effect of dilution is to introduce an effective noise in the training examples.