Retrieval process of an associative memory with a general input-output function
✍ Scribed by Hidetoshi Nishimori; Ioan Opriş
- Publisher
- Elsevier Science
- Year
- 1993
- Tongue
- English
- Weight
- 621 KB
- Volume
- 6
- Category
- Article
- ISSN
- 0893-6080
No coin nor oath required. For personal study only.
✦ Synopsis
The retrieval process ofan associative memory with a general input-output function is studied by means 0/a signal-to-noise ratio analysis. We derive a set 0/ recursion relations for macroscopic variables to describe the time development ofthe network. By taking the equilibrium limit ofthe recursion relations, we find that a certain type of nonmonotonic input-output relation ofa single neuron yields an enhanced memory capacity ofthe network compared with the conventional monotonic relation. This behavior is in agreement with the prediction 0/Morita et al. who used numerical simulations as wellas geometrical arguments to reach their conclusion. Our method reveals the relation between the type ofthe input-output/unction and the memory capacity in a generic associative memory.