Deep boltzmann machines as feed-forward hierarchies

Grégoire Montavon, Mikio L. Braun, Klaus Robert Müller

Research output: Contribution to journalConference article

6 Citations (Scopus)

Abstract

The deep Boltzmann machine is a powerful model that extracts the hierarchical structure of observed data. While inference is typically slow due to its undirected nature, we argue that the emerging feature hierarchy is still explicit enough to be traversed in a feed forward fashion. The claim is corroborated by training a set of deep neural networks on real data and measuring the evolution of the representation layer after layer. The analysis reveals that the deep Boltzmann machine produces a feed-forward hierarchy of increasingly invariant representations that clearly surpasses the layer-wise approach.

Original languageEnglish
Pages (from-to)798-804
Number of pages7
JournalJournal of Machine Learning Research
Volume22
Publication statusPublished - 2012
Externally publishedYes
Event15th International Conference on Artificial Intelligence and Statistics, AISTATS 2012 - La Palma, Spain
Duration: 2012 Apr 212012 Apr 23

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Deep boltzmann machines as feed-forward hierarchies'. Together they form a unique fingerprint.

  • Cite this

    Montavon, G., Braun, M. L., & Müller, K. R. (2012). Deep boltzmann machines as feed-forward hierarchies. Journal of Machine Learning Research, 22, 798-804.