Learning algorithms for Boltzmann machines

Research output: Contribution to journalConference article

2 Scopus citations


The author describes a learning algorithm for Boltzmann machines, based on the usual alternation between 'learning' and 'hallucinating' phases. He outlines the rigorous proof that, for suitable choices of the parameters, the evolution of the weights follows very closely, with very high probability, an integral trajectory of the gradient of the likelihood function whose global maxima are exactly the desired weight patterns.

Original languageEnglish (US)
Pages (from-to)786-791
Number of pages6
JournalProceedings of the IEEE Conference on Decision and Control
StatePublished - Dec 1 1988
EventProceedings of the 27th IEEE Conference on Decision and Control - Austin, TX, USA
Duration: Dec 7 1988Dec 9 1988

All Science Journal Classification (ASJC) codes

  • Chemical Health and Safety
  • Control and Systems Engineering
  • Safety, Risk, Reliability and Quality

Fingerprint Dive into the research topics of 'Learning algorithms for Boltzmann machines'. Together they form a unique fingerprint.

  • Cite this