Exhaustive Learning
- 1 September 1990
- journal article
- Published by MIT Press in Neural Computation
- Vol. 2 (3) , 374-385
- https://doi.org/10.1162/neco.1990.2.3.374
Abstract
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.Keywords
This publication has 4 references indexed in Scilit:
- What Size Net Gives Valid Generalization?Neural Computation, 1989
- Consistent inference of probabilities in layered networks: predictions and generalizationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- The space of interactions in neural network modelsJournal of Physics A: General Physics, 1988
- Exhaustive Thermodynamical Analysis of Boolean Learning NetworksEurophysics Letters, 1987