Minimally Connective, Auto-associative, Neural Networks
- 1 January 1994
- journal article
- research article
- Published by Taylor & Francis in Connection Science
- Vol. 6 (4) , 461-469
- https://doi.org/10.1080/09540099408915734
Abstract
Classic barriers to using auto-associative neural networks to model mammalian memory include the unrealistically high synaptic connectivity of fully connected networks, and the relative paucity of information that has been stored in networks with realistic numbers of synapses per neuron and learning rules amenable to physiological implementation. We describe extremely large, auto-associative networks with low synaptic density. The networks have no direct connections between neurons of the same layer. Rather, the neurons of one layer are 'linked' by connections to neurons of some other layer. Patterns of projections of one layer on to another which form projective planes, or other cognate geometries, confer considerable computational power an the network.Keywords
This publication has 6 references indexed in Scilit:
- Neural network parallel computing for BIBD problemsIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1992
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- On associative memoryBiological Cybernetics, 1980
- A simple neural network generating an interactive memoryMathematical Biosciences, 1972
- Correlation Matrix MemoriesIEEE Transactions on Computers, 1972
- Non-Holographic Associative MemoryNature, 1969