{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,19]],"date-time":"2025-04-19T05:07:38Z","timestamp":1745039258371},"reference-count":8,"publisher":"MIT Press - Journals","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[1999,5,1]]},"abstract":"<jats:p> Pruning a neural network to a reasonable smaller size, and if possible to give a better generalization, has long been investigated. Conventionally the common technique of pruning is based on considering error sensitivity measure, and the nature of the problem being solved is usually stationary. In this article, we present an adaptive pruning algorithm for use in a nonstationary environment. The idea relies on the use of the extended Kalman filter (EKF) training method. Since EKF is a recursive Bayesian algorithm, we define a weight-importance measure in term of the sensitivity of a posteriori probability. Making use of this new measure and the adaptive nature of EKF, we devise an adaptive pruning algorithm called adaptive Bayesian pruning. Simulation results indicate that in a noisy nonstationary environment, the proposed pruning algorithm is able to remove network redundancy adaptively and yet preserve the same generalization ability. <\/jats:p>","DOI":"10.1162\/089976699300016539","type":"journal-article","created":{"date-parts":[[2002,7,27]],"date-time":"2002-07-27T11:55:01Z","timestamp":1027770901000},"page":"965-976","source":"Crossref","is-referenced-by-count":9,"title":["An Adaptive Bayesian Pruning for Neural Networks in a Non-Stationary Environment"],"prefix":"10.1162","volume":"11","author":[{"given":"John","family":"Sum","sequence":"first","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-sing","family":"Leung","sequence":"additional","affiliation":[{"name":"School of Applied Science, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gilbert H.","family":"Young","sequence":"additional","affiliation":[{"name":"Department of Computing, Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lai-wan","family":"Chan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chinese University of Hong Kong, Shatin, N.T., Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wing-kay","family":"Kan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chinese University of Hong Kong, Shatin, N.T., Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","reference":[{"key":"p_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80122-4"},{"key":"p_4","doi-asserted-by":"publisher","DOI":"10.1109\/78.127966"},{"key":"p_5","doi-asserted-by":"publisher","DOI":"10.1109\/31.192419"},{"key":"p_8","doi-asserted-by":"publisher","DOI":"10.1049\/el:19961443"},{"key":"p_9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.3.448"},{"key":"p_14","doi-asserted-by":"publisher","DOI":"10.1109\/72.279191"},{"key":"p_15","doi-asserted-by":"publisher","DOI":"10.1109\/72.248452"},{"key":"p_16","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80139-X"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/089976699300016539","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:23:32Z","timestamp":1615584212000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/11\/4\/965-976\/6260"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999,5,1]]},"references-count":8,"journal-issue":{"issue":"4","published-print":{"date-parts":[[1999,5,1]]}},"alternative-id":["10.1162\/089976699300016539"],"URL":"https:\/\/doi.org\/10.1162\/089976699300016539","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[1999,5,1]]}}}