Generalization in a Hopfield network
Author:
- 1 January 1990
- journal article
- Published by EDP Sciences in Journal de Physique
- Vol. 51 (21) , 2421-2430
Abstract
The performance of a Hopfield network in learning an extensive number of concepts having access only to a finite supply of typical data which exemplify the concepts is studied. The minimal number of examples which must be taught to the network in order it starts to create representations for the concepts is calculated analitically. It is shown that the mixture states play a crucial role in the creation of these representationsKeywords
This publication has 7 references indexed in Scilit:
- Learning from Examples in a Single-Layer Neural NetworkEurophysics Letters, 1990
- On the storage of correlated patterns in Hopfield's modelJournal de Physique, 1990
- The Hebb Rule for Learning Linearly Separable Boolean Functions: Learning and GeneralizationEurophysics Letters, 1989
- Perceptron beyond the limit of capacityJournal de Physique, 1989
- Learning Networks of Neurons with Boolean LogicEurophysics Letters, 1987
- Statistical mechanics of neural networks near saturationAnnals of Physics, 1987
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences of the United States of America, 1982