On the Information Storage Capacity of Local Learning Rules
- 1 September 1992
- journal article
- Published by MIT Press in Neural Computation
- Vol. 4 (5) , 703-711
- https://doi.org/10.1162/neco.1992.4.5.703
Abstract
A simple relation between the storage capacity A for autoassociation and H for heteroassociation with a local learning rule is demonstrated: H = 2A. Both values are bounded by local learning bounds: A ≤ LA and H ≤ LH. LH = 2LA is evaluated numerically.Keywords
This publication has 7 references indexed in Scilit:
- Optimal Plasticity from Matrix Memories: What Goes Up Must Come DownNeural Computation, 1990
- Information storage in sparsely coded memory netsNetwork: Computation in Neural Systems, 1990
- Neural networks with low levels of activity: Ising vs. McCulloch-Pitts neuronsZeitschrift für Physik B Condensed Matter, 1989
- The Enhanced Storage Capacity in Neural Networks with Low Activity LevelEurophysics Letters, 1988
- Information storage in neural networks with low levels of activityPhysical Review A, 1987
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- On associative memoryBiological Cybernetics, 1980