Assessment of sequential boltzmann machines on a lexical processing task

Alberto Testolin, Alessandro Sperduti, Ivilin Stoianov, Marco Zorzi

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

Abstract

The Recurrent Temporal Restricted Boltzmann Machine is a promising probabilistic model for processing temporal data. It has been shown to learn physical dynamics from videos (e.g. bouncing balls), but its ability to process sequential data has not been tested on symbolic tasks. Here we assess its capabilities on learning sequences of letters corresponding to English words. It emerged that the model is able to extract local transition rules between items of a sequence (i.e. English graphotactic rules), but it does not seem to be suited to encode a whole word.

Original languageEnglish
Title of host publicationESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Publisheri6doc.com publication
Pages275-280
Number of pages6
ISBN (Print)9782874190490
Publication statusPublished - 2012
Event20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2012 - Bruges, Belgium
Duration: Apr 25 2012Apr 27 2012

Other

Other20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2012
CountryBelgium
CityBruges
Period4/25/124/27/12

ASJC Scopus subject areas

  • Information Systems
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Assessment of sequential boltzmann machines on a lexical processing task'. Together they form a unique fingerprint.

Cite this