Discovery - University of Dundee - Online Publications

Library & Learning Centre

Neural networks for proof-pattern recognition

Neural networks for proof-pattern recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

View graph of relations

Authors

Research units

Info

Original languageEnglish
Title of host publicationArtificial Neural Networks and Machine Learning – ICANN 2012
Subtitle of host publication22nd International Conference on Artificial Neural Networks, Lausanne, Switzerland, September 11-14, 2012, Proceedings, Part II
EditorsAlessandro E. P. Villa, Wlodzislaw Duch, Peter Erdi, Francesco Masulli, Gunther Palm
Place of publicationBerlin
PublisherSpringer
Publication date2012
Pages427-434
Number of pages8
ISBN (Electronic)9783642332661
ISBN (Print)9783642332654
DOIs
StatePublished

Publication series

NameLecture notes in computer science
PublisherSpringer
Volume7553
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference22nd International Conference on Artificial Neural Networks
Abbreviated titleICANN 2012
CountrySwitzerland
CityLausanne
Period11/09/1214/09/12
Other
Internet addresshttp://icann2012.org/

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. © 2012 Springer-Verlag.

Documents

Library & Learning Centre

Contact | Accessibility | Policy