Neural network endowed with symbolic processing ability

Vogiatzis, Dimitrios; Stafylopatis, Andreas

dc.contributor.author	Vogiatzis, Dimitrios	en
dc.contributor.author	Stafylopatis, Andreas	en
dc.date.accessioned	2014-03-01T02:41:34Z
dc.date.available	2014-03-01T02:41:34Z
dc.date.issued	1999	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30538
dc.subject	Reinforcement Learning	en
dc.subject	Neural Network	en
dc.subject	Reward Dependence	en
dc.subject.other	Functions	en
dc.subject.other	Learning systems	en
dc.subject.other	Reinforcement learning	en
dc.subject.other	Neural networks	en
dc.title	Neural network endowed with symbolic processing ability	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/IJCNN.1999.830809	en
heal.identifier.secondary	http://dx.doi.org/10.1109/IJCNN.1999.830809	en
heal.publicationDate	1999	en
heal.abstract	We propose a neural network method for the generation of symbolic expressions using reinforcement learning. According to the proposed method, a human decides on the kind and number of primitive functions which, with the appropriate composition (in the mathematical sense), can represent a mapping between two domains. The appropriate composition is achieved by an agent which tries many compositions and receives a reward depending on the quality of the composed function.	en
heal.publisher	IEEE, United States	en
heal.journalName	Proceedings of the International Joint Conference on Neural Networks	en
dc.identifier.doi	10.1109/IJCNN.1999.830809	en
dc.identifier.volume	6	en
dc.identifier.spage	4054	en
dc.identifier.epage	4058	en