Sciweavers

TNN
1998

Bayesian retrieval in associative memories with storage errors

13 years 9 months ago
Bayesian retrieval in associative memories with storage errors
Abstract—It is well known that for finite-sized networks, onestep retrieval in the autoassociative Willshaw net is a suboptimal way to extract the information stored in the synapses. Iterative retrieval strategies are much better, but have hitherto only had heuristic justification. We show how they emerge naturally from considerations of probabilistic inference under conditions of noisy and partial input and a corrupted weight matrix. We start from the conditional probability distribution over possible patterns for retrieval. This contains all possible information that is available to an observer of the network and the initial input. Since this distribution is over exponentially many patterns, we use it to develop two approximate, but tractable, iterative retrieval methods. One performs maximum likelihood inference to find the single most likely pattern, using the (negative log of the) conditional probability as a Lyapunov function for retrieval. In physics terms, if storage error...
Friedrich T. Sommer, Peter Dayan
Added 23 Dec 2010
Updated 23 Dec 2010
Type Journal
Year 1998
Where TNN
Authors Friedrich T. Sommer, Peter Dayan
Comments (0)