caa a22 4500 477074464 CHVBK 20180405111435.0 cr unu---uuuuu 170330e19961201xx s 000 0 eng 10.1007/BF02900896 doi (NATIONALLICENCE)springer-10.1007/BF02900896 Using neural networks for recognizing matching among terms [Elektronische Daten] [Carlos Mareco, Alberto Paccanaro] Some experiments have been carried out in order to identify a class of neural networks that would receive as inputs (n+1) terms {Tl, Tn.T} and would suggest which Tis are matched by a subterm of T, with varying n. A particular net was found that is able to solve the problem for n=1 with a good degree of accuracy. It is shown that the performance of the net is relatively independent of the size of the training set while it is strongly related to the length of the term T. This net was then used as building block for larger nets that were applied to solve the problem for higher values of n. Results of testing such nets are presented. Springer, 1996 Mareco Carlos LED, Universidad Católica de Asunción, Paraguay aut Paccanaro Alberto Dipartimento di Scienze dell'Informazione, Università di Milano, Italy aut Wuhan University Journal of Natural Sciences Wuhan University 1/3-4(1996-12-01), 617-622 1007-1202 1:3-4<617 1996 1 11859 https://doi.org/10.1007/BF02900896 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF02900896 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Mareco Carlos LED, Universidad Católica de Asunción, Paraguay aut NATIONALLICENCE 700 1- Paccanaro Alberto Dipartimento di Scienze dell'Informazione, Università di Milano, Italy aut NATIONALLICENCE 773 0- Wuhan University Journal of Natural Sciences Wuhan University 1/3-4(1996-12-01), 617-622 1007-1202 1:3-4<617 1996 1 11859 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer