{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,5]],"date-time":"2022-04-05T13:09:55Z","timestamp":1649164195327},"reference-count":0,"publisher":"World Scientific Pub Co Pte Lt","issue":"supp01","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Neur. Syst."],"published-print":{"date-parts":[[1992,1]]},"abstract":"<jats:p> Some constraints intrinsic to unsupervised learning in attractor neural networks (ANN) are discussed. We present a very simple realizable model of ANN capable of dynamically learning and classifying input stimuli in a totally unsupervised fashion. The synapses of the network are analog dynamic variables whose values have to be periodically refreshed to avoid memory loss. Two refreshing mechanisms are discussed: the first one is a periodic deterministic refresh while the second one acts stochastically. Then some typical learning scenarios are described and constraints on storage capacity are exposed: in the worst case a network of N neurons can learn at most O(ln N) patterns while in the best case (stochastic learning) the number of stored patterns cannot surpass [Formula: see text]. We have come across these constraints in connection with a design of an organically learning ANN, implemented in silicon. <\/jats:p>","DOI":"10.1142\/s0129065792000322","type":"journal-article","created":{"date-parts":[[2004,11,23]],"date-time":"2004-11-23T22:29:42Z","timestamp":1101248982000},"page":"3-11","source":"Crossref","is-referenced-by-count":1,"title":["LEARNING CONSTRAINTS IN STORAGE CAPACITY IN NETWORKS WITH DYNAMIC SYNAPSES"],"prefix":"10.1142","volume":"03","author":[{"given":"Stefano","family":"Fusi","sequence":"first","affiliation":[{"name":"INFN, Sezione di Roma, Istituto di Fisica, Universit\u00e0 di Roma, La Sapienza, P.le Aldo Moro, Roma, Italy"}]},{"given":"Daniel J.","family":"Amit","sequence":"additional","affiliation":[{"name":"INFN, Sezione di Roma, Istituto di Fisica, Universit\u00e0 di Roma, La Sapienza, P.le Aldo Moro, Roma, Italy"}]}],"member":"219","published-online":{"date-parts":[[2011,11,21]]},"container-title":["International Journal of Neural Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0129065792000322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,7]],"date-time":"2019-08-07T12:22:06Z","timestamp":1565180526000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0129065792000322"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1992,1]]},"references-count":0,"journal-issue":{"issue":"supp01","published-online":{"date-parts":[[2011,11,21]]},"published-print":{"date-parts":[[1992,1]]}},"alternative-id":["10.1142\/S0129065792000322"],"URL":"https:\/\/doi.org\/10.1142\/s0129065792000322","relation":{},"ISSN":["0129-0657","1793-6462"],"issn-type":[{"value":"0129-0657","type":"print"},{"value":"1793-6462","type":"electronic"}],"subject":[],"published":{"date-parts":[[1992,1]]}}}