Neural associative memory for brain modeling and information retrieval |
| |
Authors: | Andreas Knoblauch |
| |
Affiliation: | a Department of Neural Information Processing, University of Ulm, Oberer Eselsberg, D-89069 Ulm, Germany b MRC Cognition and Brain Sciences Unit, Speech and Language Group, 15 Chaucer Road, Cambridge CV2 2EF, England |
| |
Abstract: | This work concisely reviews and unifies the analysis of different variants of neural associative networks consisting of binary neurons and synapses (Willshaw model). We compute storage capacity, fault tolerance, and retrieval efficiency and point out problems of the classical Willshaw model such as limited fault tolerance and restriction to logarithmically sparse random patterns. Then we suggest possible solutions employing spiking neurons, compression of the memory structures, and additional cell layers. Finally, we discuss from a technical perspective whether distributed neural associative memories have any practical advantage over localized storage, e.g., in compressed look-up tables. |
| |
Keywords: | Spiking associative memory Neural modeling Algorithms Information retrieval Fault tolerance |
本文献已被 ScienceDirect 等数据库收录! |
|