Presentation 1998/3/19
Average Function Approximation Bounds for Adaptive Systems based on Functional Measures
Sumio WATANABE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We analyze average function approximation bounds for an adaptive approximation system based on the functional measure. The followings are proved. (1) If coefficients of the target function consist of real values and are independent from each other, then the adaptive approximation system is not effective. (2) If coefficients of the target function consist of real values and are subject to a competitive probability distribution, then the adaptive approximation system is more effective than the fixed approximation system. (3) If coefficients of the target function consist of quantized values, then the adaptive approximation system is more effective than the fixed approximation system.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Fucnitonal Measure / Function Approximation System / Approximation Bounds
Paper #
Date of Issue

Conference Information
Committee NC
Conference Date 1998/3/19(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Average Function Approximation Bounds for Adaptive Systems based on Functional Measures
Sub Title (in English)
Keyword(1) Fucnitonal Measure
Keyword(2) Function Approximation System
Keyword(3) Approximation Bounds
1st Author's Name Sumio WATANABE
1st Author's Affiliation Advanced Information Processing Division Precision and Intelligence Laboratory Tokyo Institute of Technology()
Date 1998/3/19
Paper #
Volume (vol) vol.97
Number (no) 623
Page pp.pp.-
#Pages 8
Date of Issue