Effect of the temperature parameter on convergence in the Boltzmann machines

Lior Shtram, Shai Policker, Amir B. Geva

Research output: Contribution to conferencePaperpeer-review

Abstract

Boltzmann machines show attractive features in traditional neural network tasks. We tested the robustness of the Boltzmann machine in a non-linear mapping task. The system's errors were classified into several categories and the distribution of errors between the categories was studied. Using simulations, it is demonstrated that limitation of the temperature parameter causes the distribution of the network's errors to be unique and different from its usual error distribution. The phenomenon receives a mathematical explanation rooted in the statistical mechanics basics of the Boltzmann machine. This has applications in designing and evaluating mapping tasks for the Boltzmann machines and can help speed up system's convergence, which is known to be a major deficit of the Boltzmann Machine.

Original languageEnglish
Pages200-203
Number of pages4
StatePublished - 1 Dec 1996
EventProceedings of the 1996 19th Convention of Electrical and Electronics Engineers in Israel - Jerusalem, Isr
Duration: 5 Nov 19966 Nov 1996

Conference

ConferenceProceedings of the 1996 19th Convention of Electrical and Electronics Engineers in Israel
CityJerusalem, Isr
Period5/11/966/11/96

Fingerprint

Dive into the research topics of 'Effect of the temperature parameter on convergence in the Boltzmann machines'. Together they form a unique fingerprint.

Cite this