{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,3]],"date-time":"2022-04-03T09:00:01Z","timestamp":1648976401249},"reference-count":0,"publisher":"World Scientific Pub Co Pte Lt","issue":"04","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Neur. Syst."],"published-print":{"date-parts":[[1991,1]]},"abstract":"<jats:p> This paper proposes an extension to the basic framework of distributed representation through the learning and use of different sorts of information\u2014\u201cmultiple representations\u201d\u2014in connectionist\/neural network systems. In current distributed networks units are typically ascribed only one \u201crepresenting\u201d or information carrying state (activation). Similarly, connections carry a single piece of information (a weight derived from the structure of the population of patterns). In this paper we explore units and connections with multiple information carrying states. In this extended framework, multiple distributed representations can coexist with a given pattern of activation. Processing may be based on the interaction of these representations and multiple learning processes can occur simultaneously in a network. We illustrate these extensions using (in addition to patterns of activation) \u201ccentrality distribution\u201d representations. Centrality distributions are applied to two tasks, the representation of category and type hierarchy information and the highlighting of exceptional mappings to speed up learning. We suggest that the use of multiple distributed representations in a network can increase the flexibility and power of connectionist systems while remaining within the subsymbolic paradigm. This topic is of particular relevance in the context of the recent interest in the limitations of connectionism and the interface between connectionist and symbolic methods. <\/jats:p>","DOI":"10.1142\/s0129065791000327","type":"journal-article","created":{"date-parts":[[2004,11,25]],"date-time":"2004-11-25T00:50:24Z","timestamp":1101343824000},"page":"345-362","source":"Crossref","is-referenced-by-count":2,"title":["MULTIPLE REPRESENTATIONS IN CONNECTIONIST SYSTEMS"],"prefix":"10.1142","volume":"02","author":[{"given":"Anthony V.","family":"Robins","sequence":"first","affiliation":[{"name":"AI Laboratory, Department of Computer Science, University of Otago, P. O. Box 56, Dunedin, New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2011,11,21]]},"container-title":["International Journal of Neural Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0129065791000327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,7]],"date-time":"2019-08-07T01:52:32Z","timestamp":1565142752000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0129065791000327"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1991,1]]},"references-count":0,"journal-issue":{"issue":"04","published-online":{"date-parts":[[2011,11,21]]},"published-print":{"date-parts":[[1991,1]]}},"alternative-id":["10.1142\/S0129065791000327"],"URL":"https:\/\/doi.org\/10.1142\/s0129065791000327","relation":{},"ISSN":["0129-0657","1793-6462"],"issn-type":[{"value":"0129-0657","type":"print"},{"value":"1793-6462","type":"electronic"}],"subject":[],"published":{"date-parts":[[1991,1]]}}}