A Bayesian Analysis of Self-Organizing Maps

• Stephen P. Luttrell

  Adaptive Systems Theory Section, Defence Research Agency, St. Andrews Rd., Malvern, Worcestershire, WR14 3PS, United Kingdom

抄録

In this paper Bayesian methods are used to analyze some of the properties of a special type of Markov chain. The forward transitions through the chain are followed by inverse transitions (using Bayes' theorem) backward through a copy of the same chain; this will be called a folded Markov chain. If an appropriately defined Euclidean error (between the original input and its “reconstruction” via Bayes' theorem) is minimized with respect to the choice of Markov chain transition probabilities, then the familiar theories of both vector quantizers and self-organizing maps emerge. This approach is also used to derive the theory of self-supervision, in which the higher layers of a multilayer network supervise the lower layers, even though overall there is no external teacher.

収録刊行物

• Neural Computation

  Neural Computation 6 (5), 767-794, 1994-09

  MIT Press - Journals

キーワード

• Cognitive Neuroscience
• Arts and Humanities (miscellaneous)

詳細情報

• CRID: 1363670320592087808
• NII論文ID: 30036176723
• DOI: 10.1162/neco.1994.6.5.767
• ISSN: 1530888X
• ISSN: 08997667
• Web Site: https://www.mitpressjournals.org/doi/pdf/10.1162/neco.1994.6.5.767
• データソース種別:
  • Crossref
  • CiNii Articles