Associative memory: on the (puzzling) sparse coding limit
- 7 March 1991
- journal article
- Published by IOP Publishing in Journal of Physics A: General Physics
- Vol. 24 (5), 1093-1101
- https://doi.org/10.1088/0305-4470/24/5/023
Abstract
Recent studies of the information capacity in a sparsely coded memory net has led to some contradictory results. In the Willshaw model, where the couplings are binary (0 or 1), the maximal quantity of information that can be stored is 1n 2 approximately=0.69 bits per synapse. On the other hand a calculation a la Gardner (1988) for (0,1) couplings gives an upper bound for the maximal capacity of about 0.29 bits per synapse. In this study, the author considers two possible sources for this discrepancy. The first one is that the criteria for defining the maximal capacity are different (with or without a constraint of perfect errorless storage). The second one is a difference in the choice of the probability distribution of the random patterns used to compute this capacity. This analysis shows in particular that for the Willshaw model the maximal information capacity is much larger when the number of active neurons is exactly the same in every stored pattern, than when it is given only in average. In addition he gives an argument showing that this result may be generic, e.g., valid for any activity level and independent of the learning rule.Keywords
This publication has 14 references indexed in Scilit:
- Information storage in sparsely coded memory netsNetwork: Computation in Neural Systems, 1990
- Optimised network for sparsely coded patternsJournal of Physics A: General Physics, 1989
- Associative memory with high information contentPhysical Review A, 1989
- Neural networks with low levels of activity: Ising vs. McCulloch-Pitts neuronsZeitschrift für Physik B Condensed Matter, 1989
- Characteristics of sparsely encoded associative memoryNeural Networks, 1989
- Associative Memory in Asymmetric Diluted Network with Low Level of ActivityEurophysics Letters, 1988
- The Enhanced Storage Capacity in Neural Networks with Low Activity LevelEurophysics Letters, 1988
- Computing with Neural NetworksScience, 1987
- On associative memoryBiological Cybernetics, 1980
- Non-Holographic Associative MemoryNature, 1969