Neural networks for proof-pattern recognition

Ekaterina Komendantskaya, Kacper Lichota

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

    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.
    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
    Pages427-434
    Number of pages8
    ISBN (Electronic)9783642332661
    ISBN (Print)9783642332654
    DOIs
    Publication statusPublished - 2012
    Event22nd International Conference on Artificial Neural Networks - Building Internef of the UNIL Campus Dorigny, Lausanne, Switzerland
    Duration: 11 Sep 201214 Sep 2012
    http://icann2012.org/

    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
    Internet address

    Fingerprint

    Pattern recognition
    Neural networks
    Backpropagation
    Feature extraction

    Cite this

    Komendantskaya, E., & Lichota, K. (2012). Neural networks for proof-pattern recognition. In A. E. P. Villa, W. Duch, P. Erdi, F. Masulli, & G. Palm (Eds.), Artificial Neural Networks and Machine Learning – ICANN 2012: 22nd International Conference on Artificial Neural Networks, Lausanne, Switzerland, September 11-14, 2012, Proceedings, Part II (pp. 427-434). (Lecture notes in computer science; Vol. 7553). Berlin: Springer . https://doi.org/10.1007/978-3-642-33266-1_53
    Komendantskaya, Ekaterina ; Lichota, Kacper. / Neural networks for proof-pattern recognition. Artificial Neural Networks and Machine Learning – ICANN 2012: 22nd International Conference on Artificial Neural Networks, Lausanne, Switzerland, September 11-14, 2012, Proceedings, Part II. editor / Alessandro E. P. Villa ; Wlodzislaw Duch ; Peter Erdi ; Francesco Masulli ; Gunther Palm. Berlin : Springer , 2012. pp. 427-434 (Lecture notes in computer science).
    @inproceedings{2cafaa88f71045a887d93031834d7471,
    title = "Neural networks for proof-pattern recognition",
    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.",
    author = "Ekaterina Komendantskaya and Kacper Lichota",
    year = "2012",
    doi = "10.1007/978-3-642-33266-1_53",
    language = "English",
    isbn = "9783642332654",
    series = "Lecture notes in computer science",
    publisher = "Springer",
    pages = "427--434",
    editor = "Villa, {Alessandro E. P. } and Wlodzislaw Duch and Peter Erdi and Francesco Masulli and Gunther Palm",
    booktitle = "Artificial Neural Networks and Machine Learning – ICANN 2012",

    }

    Komendantskaya, E & Lichota, K 2012, Neural networks for proof-pattern recognition. in AEP Villa, W Duch, P Erdi, F Masulli & G Palm (eds), Artificial Neural Networks and Machine Learning – ICANN 2012: 22nd International Conference on Artificial Neural Networks, Lausanne, Switzerland, September 11-14, 2012, Proceedings, Part II. Lecture notes in computer science, vol. 7553, Springer , Berlin, pp. 427-434, 22nd International Conference on Artificial Neural Networks, Lausanne, Switzerland, 11/09/12. https://doi.org/10.1007/978-3-642-33266-1_53

    Neural networks for proof-pattern recognition. / Komendantskaya, Ekaterina; Lichota, Kacper.

    Artificial Neural Networks and Machine Learning – ICANN 2012: 22nd International Conference on Artificial Neural Networks, Lausanne, Switzerland, September 11-14, 2012, Proceedings, Part II. ed. / Alessandro E. P. Villa; Wlodzislaw Duch; Peter Erdi; Francesco Masulli; Gunther Palm. Berlin : Springer , 2012. p. 427-434 (Lecture notes in computer science; Vol. 7553).

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

    TY - GEN

    T1 - Neural networks for proof-pattern recognition

    AU - Komendantskaya, Ekaterina

    AU - Lichota, Kacper

    PY - 2012

    Y1 - 2012

    N2 - 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.

    AB - 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.

    UR - http://www.scopus.com/inward/record.url?scp=84867678467&partnerID=8YFLogxK

    U2 - 10.1007/978-3-642-33266-1_53

    DO - 10.1007/978-3-642-33266-1_53

    M3 - Conference contribution

    SN - 9783642332654

    T3 - Lecture notes in computer science

    SP - 427

    EP - 434

    BT - Artificial Neural Networks and Machine Learning – ICANN 2012

    A2 - Villa, Alessandro E. P.

    A2 - Duch, Wlodzislaw

    A2 - Erdi, Peter

    A2 - Masulli, Francesco

    A2 - Palm, Gunther

    PB - Springer

    CY - Berlin

    ER -

    Komendantskaya E, Lichota K. Neural networks for proof-pattern recognition. In Villa AEP, Duch W, Erdi P, Masulli F, Palm G, editors, Artificial Neural Networks and Machine Learning – ICANN 2012: 22nd International Conference on Artificial Neural Networks, Lausanne, Switzerland, September 11-14, 2012, Proceedings, Part II. Berlin: Springer . 2012. p. 427-434. (Lecture notes in computer science). https://doi.org/10.1007/978-3-642-33266-1_53