{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T16:39:56Z","timestamp":1648831196243},"reference-count":3,"publisher":"MIT Press - Journals","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2001,8,1]]},"abstract":"<jats:p> The goal of most learning processes is to bring a machine into a set of \u201ccorrect\u201d states. In practice, however, it may be difficult to show that the process enters this target set. We present a condition that ensures that the process visits the target set infinitely often almost surely. This condition is easy to verify and is true for many well-known learning rules.To demonstrate the utility of this method, we apply it to four types of learning processes: the perceptron, learning rules governed by continuous energy functions, the Kohonen rule, and the committee machine. <\/jats:p>","DOI":"10.1162\/08997660152469378","type":"journal-article","created":{"date-parts":[[2002,7,27]],"date-time":"2002-07-27T11:55:01Z","timestamp":1027770901000},"page":"1839-1861","source":"Crossref","is-referenced-by-count":0,"title":["Recurrence Methods in the Analysis of Learning Processes"],"prefix":"10.1162","volume":"13","author":[{"given":"S.","family":"Mendelson","sequence":"first","affiliation":[{"name":"Department of Mathematics, Technion, and Institute of Computer Science, Hebrew University, Jerusalem 91120, Israel"}]},{"given":"I.","family":"Nelken","sequence":"additional","affiliation":[{"name":"Department of Physiology, Hebrew University-Hadassah Medical School, and the Interdisciplinary Center for Neural Computation, Hebrew University, Jerusalem 91120, Israel"}]}],"member":"281","reference":[{"key":"p_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoap\/1177004611"},{"key":"p_2","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(95)00089-5"},{"key":"p_4","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.76.3021"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/08997660152469378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:48:57Z","timestamp":1615585737000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/13\/8\/1839-1861\/6525"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,8,1]]},"references-count":3,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2001,8,1]]}},"alternative-id":["10.1162\/08997660152469378"],"URL":"https:\/\/doi.org\/10.1162\/08997660152469378","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2001,8,1]]}}}