{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:22:11Z","timestamp":1759134131190},"reference-count":29,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2006,10,24]],"date-time":"2006-10-24T00:00:00Z","timestamp":1161648000000},"content-version":"vor","delay-in-days":4801,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Concurrency: Pract. Exper."],"published-print":{"date-parts":[[1993,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The paper reports two techniques for parallelizing on a MIMD multicomputer a class of learning algorithms (competitive learning) for artificial neural networks widely used in pattern recognition and understanding. The first technique presented, following the <jats:italic>divide et impera<\/jats:italic> strategy, achieves O(<jats:italic>n\/p<\/jats:italic> + log<jats:italic>P<\/jats:italic>) time for <jats:italic>n<\/jats:italic> neurons and <jats:italic>P<\/jats:italic> processors interconnected as a tree. A modification of the algorithm allows the application of a systolic technique with the processors interconnected as a ring; this technique has the advantage that the communication time does not depend on the number of processors. The two techniques are also compared on the basis of predicted and measured performance on a transputer\u2010based MIMD machine. As the number of processors grows the advantage of the systolic approach increases. On the contrary, the <jats:italic>divide et impera<\/jats:italic> approach is more advantageous in the retrieving phase.<\/jats:p>","DOI":"10.1002\/cpe.4330050602","type":"journal-article","created":{"date-parts":[[2006,11,17]],"date-time":"2006-11-17T16:36:03Z","timestamp":1163781363000},"page":"449-470","source":"Crossref","is-referenced-by-count":9,"title":["Competitive neural networks on message\u2010passing parallel computers"],"prefix":"10.1002","volume":"5","author":[{"given":"Michele","family":"Ceccarelli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alfredo","family":"Petrosino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Vaccaro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2006,10,24]]},"reference":[{"key":"e_1_2_1_2_2","volume-title":"Adaptive Pattern Recognition and Neural Networks","author":"Pao Y. H.","year":"1989"},{"key":"e_1_2_1_3_2","volume-title":"Pattern Classification and Scene Analysis","author":"Duda R.","year":"1973"},{"key":"e_1_2_1_4_2","volume-title":"Algorithms for Clustering Data","author":"Jain A.","year":"1988"},{"key":"e_1_2_1_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/0743-7315(92)90068-X"},{"key":"e_1_2_1_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/0743-7315(89)90065-8"},{"key":"e_1_2_1_7_2","first-page":"165","article-title":"Parallel architectures for artificial neural nets","volume":"2","author":"Kung S. Y.","year":"1990","journal-title":"Proc. IEEE Internat. Conf. Neural Networks"},{"key":"e_1_2_1_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8191(90)90088-Q"},{"key":"e_1_2_1_9_2","first-page":"812","article-title":"Parallelizing the self\u2010organizing feature map on multiprocessor systems","volume":"17","author":"Hodges R. E.","year":"1991","journal-title":"Parallel Comput."},{"key":"e_1_2_1_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00288907"},{"key":"e_1_2_1_11_2","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1962.sp006837"},{"key":"e_1_2_1_12_2","first-page":"54","article-title":"A massively parallel architecture for a self\u2010organizing neural pattern recognition machine","volume":"37","author":"Carpenter G. A.","year":"1987","journal-title":"CVGIP"},{"key":"e_1_2_1_13_2","volume-title":"Self Organization and Associative Memory","author":"Kohonen T.","year":"1984"},{"key":"e_1_2_1_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"e_1_2_1_15_2","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0901_5"},{"key":"e_1_2_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.58325"},{"key":"e_1_2_1_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00197290"},{"key":"e_1_2_1_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00205972"},{"key":"e_1_2_1_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90047-O"},{"key":"e_1_2_1_20_2","doi-asserted-by":"crossref","unstructured":"D. A.Pomerleau G. L.Gusciora D. S.TouretzkyandH. T.Kung \u2018Neural network simulation at Warp speed: How we got 17 million connections per second\u2019 in IEEE Internat. Conf. on Neural Networks San Diego CA 1988 pp.143\u2013150.","DOI":"10.1109\/ICNN.1988.23922"},{"key":"e_1_2_1_21_2","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/30.5.413"},{"key":"e_1_2_1_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8191(90)90084-M"},{"key":"e_1_2_1_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/0743-7315(89)90063-4"},{"key":"e_1_2_1_24_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.2.141"},{"key":"e_1_2_1_25_2","volume-title":"Parallel Processing: state of the art report","author":"May D.","year":"1988"},{"key":"e_1_2_1_26_2","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4330010202"},{"key":"e_1_2_1_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90025-G"},{"key":"e_1_2_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.58324"},{"key":"e_1_2_1_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90044-L"},{"key":"e_1_2_1_30_2","first-page":"147","volume-title":"Parallel Architectures and Neural Networks '91","author":"Ceccarelli M.","year":"1991"}],"container-title":["Concurrency: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fcpe.4330050602","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.4330050602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,24]],"date-time":"2023-10-24T21:59:28Z","timestamp":1698184768000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.4330050602"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1993,9]]},"references-count":29,"journal-issue":{"issue":"6","published-print":{"date-parts":[[1993,9]]}},"alternative-id":["10.1002\/cpe.4330050602"],"URL":"https:\/\/doi.org\/10.1002\/cpe.4330050602","archive":["Portico"],"relation":{},"ISSN":["1040-3108","1096-9128"],"issn-type":[{"value":"1040-3108","type":"print"},{"value":"1096-9128","type":"electronic"}],"subject":[],"published":{"date-parts":[[1993,9]]}}}