{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:07:38Z","timestamp":1781021258817,"version":"3.54.1"},"reference-count":28,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2010,2,11]],"date-time":"2010-02-11T00:00:00Z","timestamp":1265846400000},"content-version":"vor","delay-in-days":9172,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Cognitive Science"],"published-print":{"date-parts":[[1985,1]]},"abstract":"<jats:p>The computational power of massively parallel networks of simple processing elements resides in the communication bandwidth provided by the hardware connections between elements. These connections can allow a significant fraction of the knowledge of the system to be applied to an instance of a problem in a very short time. One kind of computation for which massively parallel networks appear to be well suited is large constraint satisfaction searches, but to use the connections efficiently two conditions must be met: First, a search technique that is suitable for parallel networks must be found. Second, there must be some way of choosing internal representations which allow the preexisting hardware connections to be used efficiently for encoding the constraints in the domain being searched. We describe a general parallel search method, based on statistical mechanics, and we show how it leads to a general learning rule for modifying the connection strengths so as to incorporate knowledge about a task domain in an efficient way. We describe some simple examples in which the learning algorithm creates internal representations that are demonstrably the most efficient way of using the preexisting connectivity structure.<\/jats:p>","DOI":"10.1207\/s15516709cog0901_7","type":"journal-article","created":{"date-parts":[[2005,7,18]],"date-time":"2005-07-18T01:08:51Z","timestamp":1121648931000},"page":"147-169","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2080,"title":["A Learning Algorithm for Boltzmann Machines*"],"prefix":"10.1111","volume":"9","author":[{"given":"David H.","family":"Ackley","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geoffrey E.","family":"Hinton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Terrence J.","family":"Sejnowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2010,2,11]]},"reference":[{"key":"e_1_2_1_2_1","first-page":"213","volume-title":"Proceedings of the National Conference on Artificial Intelligence AAAI\u201082","author":"Berliner H. J.","year":"1982"},{"key":"e_1_2_1_3_1","volume-title":"The Monte\u2010Carlo method in statistical physics","author":"Binder K.","year":"1978"},{"key":"e_1_2_1_4_1","volume-title":"The Hashnet Interconnection Scheme","author":"Fahlman S. E.","year":"1980"},{"key":"e_1_2_1_5_1","first-page":"109","volume-title":"Proceedings of the National Conference on Artificial Intelligence AAAI\u201083","author":"Fahlman S. E.","year":"1983"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00335349"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0603_1"},{"key":"e_1_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Geman S. &Geman D.(1983).Stochastic relaxation Gibbs distributions and the Bayesian restoration of images. Unpublished manuscript.","DOI":"10.1109\/TPAMI.1984.4767596"},{"key":"e_1_2_1_9_1","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3132.001.0001","volume-title":"From images to surfaces","author":"Grimson W. E. L.","year":"1981"},{"key":"e_1_2_1_10_1","first-page":"408","volume-title":"Computer Vision","author":"Hinton G. E.","year":"1977"},{"key":"e_1_2_1_11_1","volume-title":"Parallel Models of Associative Memory","author":"Hinton G. E.","year":"1981"},{"key":"e_1_2_1_12_1","volume-title":"Parallel models of associative memory","author":"Hinton G. E.","year":"1981"},{"key":"e_1_2_1_13_1","volume-title":"Proceedings of the Fifth Annual Conference of the Cognitive Science Society","author":"Hinton G. E.","year":"1983"},{"key":"e_1_2_1_14_1","first-page":"448","volume-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","author":"Hinton G. E.","year":"1983"},{"key":"e_1_2_1_15_1","volume-title":"Boltzmann Machines: Constraint satisfaction networks that learn","author":"Hinton G. E.","year":"1984"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.79.8.2554"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.220.4598.671"},{"key":"e_1_2_1_18_1","volume-title":"Information theory and statistics","author":"Kullback S.","year":"1959"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.1699114"},{"key":"e_1_2_1_20_1","volume-title":"Perceptrons","author":"Minsky M.","year":"1968"},{"key":"e_1_2_1_21_1","doi-asserted-by":"crossref","DOI":"10.21236\/ADA125318","volume-title":"Intellectual issues in the history of artificial intelligence","author":"Newell A.","year":"1982"},{"key":"e_1_2_1_22_1","volume-title":"Human problem solving","author":"Newell A.","year":"1972"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.85.2.59"},{"key":"e_1_2_1_24_1","volume-title":"Probability theory","author":"Renyi A.","year":"1962"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.21236\/AD0256582"},{"key":"e_1_2_1_26_1","first-page":"109","volume-title":"Proceedings of the National Conference on Artificial Intelligence AAAI\u201083","author":"Smolensky P.","year":"1983"},{"key":"e_1_2_1_27_1","volume-title":"Multiresolution computation of visible\u2010surface representations","author":"Terzopoulos D.","year":"1984"},{"key":"e_1_2_1_28_1","volume-title":"The Psychology of Computer Vision","author":"Waltz D. L.","year":"1975"},{"key":"e_1_2_1_29_1","volume-title":"Artificial Intelligence","author":"Winston P. H.","year":"1984"}],"container-title":["Cognitive Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1207%2Fs15516709cog0901_7","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1207\/s15516709cog0901_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T13:25:49Z","timestamp":1697808349000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1207\/s15516709cog0901_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1985,1]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[1985,1]]}},"alternative-id":["10.1207\/s15516709cog0901_7"],"URL":"https:\/\/doi.org\/10.1207\/s15516709cog0901_7","archive":["Portico"],"relation":{},"ISSN":["0364-0213","1551-6709"],"issn-type":[{"value":"0364-0213","type":"print"},{"value":"1551-6709","type":"electronic"}],"subject":[],"published":{"date-parts":[[1985,1]]},"assertion":[{"value":"2010-02-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}