Guiding term reduction through a neural network: Some preliminary results for the group theory
Some experiments have been carried out in order to build Neural Networks which, given a term belonging to an Equational Theory, could suggest which rewrite rules belonging to the Completed TRS for that theory represent the best choice at each reduction step in order to minimize the number of reductions needed to reach the normal form. For the Groups Theory a net was built which had an accuracy of 61%. Moreover the same net in the 71% of the cases could correctly suggest a rule applicable to the term.
Unable to display preview. Download preview PDF.
- 1.N. Dershowitz , “Completion and its applications”, in Resolution of equations in algebraic structures, pp. 31–48.Google Scholar
- 2.J.A. Freeman, D.M. Skapura , “Neural Networks-Algorithms, Applications, and Programming Techniques”, Addison-Wesley.Google Scholar
- 3.J. Hsiang, M. Rusinovitch , “On Word Problems in Equational Theories”, 14th Int. Conf. on Automata Languages and Programming, Karlsrhue.Google Scholar
- 4.J.M. Hullot , “A catalogue of canonical term rewriting systems”, Rept. CSL-113, SRI International, Menlo Park, CA.Google Scholar
- 5.D.E. Knuth, P. Bendix , “Simple Word Problems in Universal Algebras”, Proceedings of the Conf. on Computational Problems in Abstract Algebras, Pergamon Press, pp. 263–298.Google Scholar
- 6.P.D. Wasserman , “Neural Computing: Theory and Practice”, van Nostrand Reinhold, New YorkGoogle Scholar