Presentation 2002/12/12
Singular Learning Machines in Pattern Recognition
Sumio WATANABE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A lot of learning machines such as hidden Markov models, layered neural networks, gaussian mixtures, reduced rank regressions, and Boltzmann machines are singular statistical models. The learning theory of regular statistical models can not be applied to them. In this paper we discuss the role of singular statistical models in pattern recognition.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Singular statistical models / hidden Markov models / pattern recognition.
Paper # NLC2002-49
Date of Issue

Conference Information
Committee NLC
Conference Date 2002/12/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Singular Learning Machines in Pattern Recognition
Sub Title (in English)
Keyword(1) Singular statistical models
Keyword(2) hidden Markov models
Keyword(3) pattern recognition.
1st Author's Name Sumio WATANABE
1st Author's Affiliation PI Lab., Tokyo Institute of Technology()
Date 2002/12/12
Paper # NLC2002-49
Volume (vol) vol.102
Number (no) 527
Page pp.pp.-
#Pages 6
Date of Issue