Machine learning coalgebraic proofs

Ekaterina Komendantskaya

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

This chapter argues for a novel method to machine learn patterns in formal proofs using statistical machine learning methods. The method exploits coalgebraic approach to proofs. The success of the method is demonstrated on three applications allowing to distinguish well-formed proofs from ill-formed proofs, identify families of proofs and even families of potentially provable goals.

Original languageEnglish
Title of host publicationLatest Advances in Inductive Logic Programming
PublisherImperial College Press
Pages191-198
Number of pages8
ISBN (Electronic)9781783265091
ISBN (Print)9781783265084
DOIs
Publication statusPublished - Dec 2014

Fingerprint Dive into the research topics of 'Machine learning coalgebraic proofs'. Together they form a unique fingerprint.

  • Projects

    Cite this

    Komendantskaya, E. (2014). Machine learning coalgebraic proofs. In Latest Advances in Inductive Logic Programming (pp. 191-198). Imperial College Press. https://doi.org/10.1142/9781783265091_0020