{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T14:36:56Z","timestamp":1649083016963},"reference-count":0,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["International Journal of Distributed Sensor Networks"],"published-print":{"date-parts":[[2009,1,1]]},"abstract":"<jats:p> This paper addresses some issues on the weighted linear integration of modular neural networks (MNN: a paradigm of hybrid multi-learning machines). <\/jats:p><jats:p> First, from the general meaning of variable weights and variable elements synthesis, three basic kinds of integrated models are discussed that are intrinsic-factors-determined, extrinsic-factors-determined, and hybrid-factors-determined. The authors point out: integrations dominated by both of the internal and external elements are highly correlative with not only the historical quality of the sub-networks, but also with the environment in which the information is processed. <\/jats:p><jats:p> In the sense of the mean of square error (MSE), several sufficient conditions to improve the whole system's performance are given while deleting one\/some sub-networks in all the networks population. Meanwhile, when the whole performance of the current MNN system possesses is unsatisfactory, a corresponding improved strategy which need add one\/some sub-networks is presented. <\/jats:p><jats:p> For the optimal weights vector under the framework of the weighted sum of the sub-networks' outputs, we point out some constraints forms of the sub-networks' integrated weights are unreasonable and present a general form while the corresponding computational algorithms are described briefly. <\/jats:p><jats:p> The authors present a new training algorithm of sub-networks named \u201c\u2018Expert in one thing and good at many\u2019 (EOGM).\u201d In this algorithm, every sub-network is trained on a primary dataset with some of its near neighbors as the accessorial datasets. Simulated results with a kind of dynamic integration methods show the effectiveness of these algorithms, where the performance of the algorithm with EOGM is better than that of the algorithm with a common training method. <\/jats:p>","DOI":"10.1080\/15501320802540058","type":"journal-article","created":{"date-parts":[[2009,1,29]],"date-time":"2009-01-29T01:29:03Z","timestamp":1233192543000},"page":"46-46","source":"Crossref","is-referenced-by-count":0,"title":["Some Issues of the Paradigm of Multi-Learning Machine - Modular Neural Networks"],"prefix":"10.1177","volume":"5","author":[{"given":"Pan","family":"Wang","sequence":"first","affiliation":[{"name":"School of Automation, Wuhan University of Technology, Wuhan, Hubei, China"}]},{"given":"Shuai","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Automation, Wuhan University of Technology, Wuhan, Hubei, China"}]},{"given":"Zhun","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Technical University of Denmark, Lyngby, Denmark"}]}],"member":"179","published-online":{"date-parts":[[2009,1,1]]},"container-title":["International Journal of Distributed Sensor Networks"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/journals.sagepub.com\/doi\/pdf\/10.1080\/15501320802540058","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/journals.sagepub.com\/doi\/pdf\/10.1080\/15501320802540058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,8]],"date-time":"2021-06-08T02:53:42Z","timestamp":1623120822000},"score":1,"resource":{"primary":{"URL":"http:\/\/journals.sagepub.com\/doi\/10.1080\/15501320802540058"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,1,1]]},"references-count":0,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2009,1,1]]}},"alternative-id":["10.1080\/15501320802540058"],"URL":"https:\/\/doi.org\/10.1080\/15501320802540058","relation":{},"ISSN":["1550-1477","1550-1477"],"issn-type":[{"value":"1550-1477","type":"print"},{"value":"1550-1477","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,1,1]]}}}