Presentation 2003/7/21
Statistical Behavior of Learning Error of Layered Neural Network
Masashi KITAHARA, Taichi HAYASAKA, Shiro USUI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper compares statistical properties of regression models between sigmoidal and Heaviside basis functions, taking notice to least squared errors. Then, we use a Heaviside basis function with ramp function, and show that this function has similar statistical properties with the sigmoidal and Heaviside basis functions. These observations suggest the similarities in statistical properties between sigmodial and Heaviside basis functions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Regression model / Layered neural network / Least squared error / Tail probability / Tube method
Paper # NC2003-25
Date of Issue

Conference Information
Committee NC
Conference Date 2003/7/21(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) Statistical Behavior of Learning Error of Layered Neural Network
Sub Title (in English)
Keyword(1) Regression model
Keyword(2) Layered neural network
Keyword(3) Least squared error
Keyword(4) Tail probability
Keyword(5) Tube method
1st Author's Name Masashi KITAHARA
1st Author's Affiliation Department of Information and Computer Sciences, Toyohashi University of Technology()
2nd Author's Name Taichi HAYASAKA
2nd Author's Affiliation Department of Information and Computer Engineering, Toyota national College of Technology
3rd Author's Name Shiro USUI
3rd Author's Affiliation Brain Science Institute, RIKEN
Date 2003/7/21
Paper # NC2003-25
Volume (vol) vol.103
Number (no) 227
Page pp.pp.-
#Pages 6
Date of Issue