Neural networks for proof-pattern recognition

Authors:
Ekaterina Komendantskaya;Kacper Lichota
Affiliations:
School of Computing, University of Dundee, UK;School of Computing, University of Dundee, UK
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II
Year:
2012

Citing 6
Cited 0

Foundations of logic programming; (2nd extended ed.)

Foundations of logic programming; (2nd extended ed.)
Automatic acquisition of search control knowledge from multiple proof attempts

Information and Computation
Logic and Learning

Logic and Learning
MaLARea SG1 - Machine Learner for Automated Reasoning with Semantic Guidance

IJCAR '08 Proceedings of the 4th international joint conference on Automated Reasoning
Neuro-symbolic representation of logic programs defining infinite sets

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part I
Coalgebraic semantics for derivations in logic programming

CALCO'11 Proceedings of the 4th international conference on Algebra and coalgebra in computer science

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a new method of feature extraction that allows to apply pattern-recognition abilities of neural networks to data-mine automated proofs. We propose a new algorithm to represent proofs for first-order logic programs as feature vectors; and present its implementation. We test the method on a number of problems and implementation scenarios, using three-layer neural nets with backpropagation learning.