{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T05:39:38Z","timestamp":1648877978995},"reference-count":12,"publisher":"World Scientific Pub Co Pte Lt","issue":"04","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Comp. Intel. Appl."],"published-print":{"date-parts":[[2002,12]]},"abstract":"<jats:p> Although Artificial Neural Networks have been satisfactorily employed in several problems, such as clustering, pattern recognition, dynamic systems control and prediction, they still suffer from significant limitations. One of them is that the induced concept representation is not usually comprehensible to humans. Several techniques have been suggested to extract meaningful knowledge from trained networks. This paper proposes the use of symbolic learning algorithms, commonly used by the Machine Learning community, such as C4.5, C4.5rules and CN2, to extract symbolic representations from trained networks. The approach proposed is similar to that used by the Trepan algorithm, which extracts symbolic representations, expressed as decision trees, from trained networks. Experimental results are presented and discussed in order to compare the knowledge extracted from Artificial Neural Networks using the proposed approach and the Trepan approach. Results are compared regarding two aspects: fidelity and comprehensibility. <\/jats:p>","DOI":"10.1142\/s1469026802000695","type":"journal-article","created":{"date-parts":[[2003,1,3]],"date-time":"2003-01-03T11:32:33Z","timestamp":1041593553000},"page":"365-376","source":"Crossref","is-referenced-by-count":1,"title":["AN APPROACH TO EXPLAIN NEURAL NETWORKS USING SYMBOLIC ALGORITHMS"],"prefix":"10.1142","volume":"02","author":[{"given":"CLAUDIA R.","family":"MILAR\u00c9","sequence":"first","affiliation":[{"name":"University of S\u00e3o Paulo \u2014 USP, Institute of Mathematics and Computer Science \u2014 ICMC, Department of Computer Science and Statistics \u2014 SCE, Laboratory of Computational Intelligence \u2014 LABIC, P. O. Box 668, 13560-970 \u2014 S\u00e3o Carlos,  S\u00e3o Paulo, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"ANDR\u00c9 C. P.","family":"DE L. F. DE CARVALHO","sequence":"additional","affiliation":[{"name":"University of S\u00e3o Paulo \u2014 USP, Institute of Mathematics and Computer Science \u2014 ICMC, Department of Computer Science and Statistics \u2014 SCE, Laboratory of Computational Intelligence \u2014 LABIC, P. O. Box 668, 13560-970 \u2014 S\u00e3o Carlos,  S\u00e3o Paulo, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"MARIA C.","family":"MONARD","sequence":"additional","affiliation":[{"name":"University of S\u00e3o Paulo \u2014 USP, Institute of Mathematics and Computer Science \u2014 ICMC, Department of Computer Science and Statistics \u2014 SCE, Laboratory of Computational Intelligence \u2014 LABIC, P. O. Box 668, 13560-970 \u2014 S\u00e3o Carlos,  S\u00e3o Paulo, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2011,11,20]]},"reference":[{"key":"p_1","doi-asserted-by":"publisher","DOI":"10.1016\/0950-7051(96)81920-4"},{"key":"p_3","doi-asserted-by":"publisher","DOI":"10.1109\/72.159059"},{"key":"p_4","first-page":"4","volume":"3","author":"Clark P.","year":"1989","journal-title":"Mach. Learn."},{"key":"p_6","first-page":"7","volume":"10","author":"Dietterich T. G.","year":"1997","journal-title":"Neural Comput."},{"key":"p_7","first-page":"8","volume":"24","author":"Fu L.","year":"1994","journal-title":"IEEE Trans. Syst. Man Cybernet."},{"key":"p_10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"p_12","first-page":"247","author":"Moreno J.","year":"1998","journal-title":"MG"},{"key":"p_13","doi-asserted-by":"publisher","DOI":"10.1007\/BF00444296"},{"key":"p_18","doi-asserted-by":"publisher","DOI":"10.1109\/72.809084"},{"key":"p_21","first-page":"302","author":"Tchoumatchenko I.","year":"1994","journal-title":"NJ"},{"key":"p_23","doi-asserted-by":"publisher","DOI":"10.1109\/72.728352"},{"key":"p_25","first-page":"71","volume":"131","author":"Towell G.","year":"1993","journal-title":"Mach. Learn."}],"container-title":["International Journal of Computational Intelligence and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S1469026802000695","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,7]],"date-time":"2019-08-07T15:19:05Z","timestamp":1565191145000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S1469026802000695"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002,12]]},"references-count":12,"journal-issue":{"issue":"04","published-online":{"date-parts":[[2011,11,20]]},"published-print":{"date-parts":[[2002,12]]}},"alternative-id":["10.1142\/S1469026802000695"],"URL":"https:\/\/doi.org\/10.1142\/s1469026802000695","relation":{},"ISSN":["1469-0268","1757-5885"],"issn-type":[{"value":"1469-0268","type":"print"},{"value":"1757-5885","type":"electronic"}],"subject":[],"published":{"date-parts":[[2002,12]]}}}