Automatic Pattern Recognition: A Study of the Probability of Error
IEEE Transactions on Pattern Analysis and Machine Intelligence
What size net gives valid generalization?
Neural Computation
Scaling and generalization in neural networks: a case study
Advances in neural information processing systems 1
Does extra knowledge necessarily improve generalization?
Neural Computation
Hi-index | 0.00 |
Exhaustive exploration of an ensemble of networks is used to model learning and generalization in layered neural networks. A simple Boolean learning problem involving networks with binary weights is numerically solved to obtain the entropy Sm and the average generalization ability Gm as a function of the size m of the training set. Learning curves Gm vs m are shown to depend solely on the distribution of generalization abilities over the ensemble of networks. Such distribution is determined prior to learning, and provides a novel theoretical tool for the prediction of network performance on a specific task.