KIAM Main page Web Library  •  Publication Searh  Русский 
Publication

Conference material: "Scientific service & Internet: proceedings of the 21th All-Russian Scientific Conference (September 23-28, 2019, Novorossiysk)"
Authors: Grechanik S.A.
Prospects of applying neural networks to supercompilation and equality saturation
Abstract:
Many methods of program transformation (including supercompilation and equality saturation) may be formulated as a set of term or graph rewriting rules that are applied in the order defined by heuristics. These heuristics are usually created by hand, so it is very interesting to automate their creation, e.g. with machine learning. In this paper we survey some approaches to tackle these problems with neural networks.
Keywords:
machine learning, neural networks, program analysis, program transformation
Publication language: russian,  страниц: 12 (p. 278-289)
Russian source text: