Presentation 1998/6/18
Energy Functions for Efficient Nonlinear Dimensionality Reduction by Multi Layer Perceptrons
Takashi TAKAHASHI, Ryuji TOKUNAGA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper investigates two simple energy functions which are valid for two different purposes of dimensionality reduction : feature extraction and data compression. These energy functions enable nonlinear perceptrons to organize data representations whose parameters, namely, outputs of the bottleneck layer units, are arranged in the order of their importance. The efficacy of these energy functions is shown by numerical experiments in comparison with conventional squared error functions and Principal Component Analysis.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) multi layer perceptron / feature extraction / data compression / principal component analysis
Paper # PRMU98-31
Date of Issue

Conference Information
Committee PRMU
Conference Date 1998/6/18(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Energy Functions for Efficient Nonlinear Dimensionality Reduction by Multi Layer Perceptrons
Sub Title (in English)
Keyword(1) multi layer perceptron
Keyword(2) feature extraction
Keyword(3) data compression
Keyword(4) principal component analysis
1st Author's Name Takashi TAKAHASHI
1st Author's Affiliation Doctoral Program in Engineering, University of Tsukuba()
2nd Author's Name Ryuji TOKUNAGA
2nd Author's Affiliation Institute of Information Sciences and Electronics, University of Tsukuba
Date 1998/6/18
Paper # PRMU98-31
Volume (vol) vol.98
Number (no) 126
Page pp.pp.-
#Pages 6
Date of Issue