Neural networks with hierarchically correlated patterns
- 1 January 1988
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review A
- Vol. 37 (2) , 570-577
- https://doi.org/10.1103/physreva.37.570
Abstract
The Hopfield model of neural networks is extended to allow for the storage and retrieval of hierarchically correlated patterns. The overlaps between these patterns form an ultrametric tree. Intermediate states, which serve as ancestors for the following levels, are generated at each level of the tree. The states belonging to each level are stored, by a modified learning rule, in a series of identical networks, one for each level. The retrieval of a particular pattern is preceded and assisted by the successive retrieval of its ancestors. The performance of this scheme is studied analytically and numerically.Keywords
This publication has 17 references indexed in Scilit:
- Statistical mechanics of neural networks near saturationPublished by Elsevier ,2004
- Information storage in neural networks with low levels of activityPhysical Review A, 1987
- Associative recall of memory without errorsPhysical Review A, 1987
- Neural networks with nonlinear synapses and a static noisePhysical Review A, 1986
- Ultrametricity for physicistsReviews of Modern Physics, 1986
- Storing Infinite Numbers of Patterns in a Spin-Glass Model of Neural NetworksPhysical Review Letters, 1985
- Spin-glass models of neural networksPhysical Review A, 1985
- Information storage and retrieval in spin-glass like neural networksJournal de Physique Lettres, 1985
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982