Presentation 2002/6/20
Learning for Periodic Function Using Neural Network with Characteristics of Inertia, Viscosity, and Stiffness
Kunihiko NAKAZONO, Hiroshi KINJO, Tetsuhiko YAMAMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a neural network with characteristics of inertia, viscosity, and stiffness and its learning algorithm based on back propagation method. The simulation results show that the neural network with characteristics of inertia, viscosity, and stiffness learned by the back propagation method has good performances of the training for time series patterns which generated from sine functions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural network / Characteristic of inertia / Characteristic of viscosity / Characteristic of stiffness / Back propagation method / Recurrent neural network
Paper # NC2002-10
Date of Issue

Conference Information
Committee NC
Conference Date 2002/6/20(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) Learning for Periodic Function Using Neural Network with Characteristics of Inertia, Viscosity, and Stiffness
Sub Title (in English)
Keyword(1) Neural network
Keyword(2) Characteristic of inertia
Keyword(3) Characteristic of viscosity
Keyword(4) Characteristic of stiffness
Keyword(5) Back propagation method
Keyword(6) Recurrent neural network
1st Author's Name Kunihiko NAKAZONO
1st Author's Affiliation Faculty of Engineering, University of the Ryukyus()
2nd Author's Name Hiroshi KINJO
2nd Author's Affiliation Faculty of Engineering, University of the Ryukyus
3rd Author's Name Tetsuhiko YAMAMOTO
3rd Author's Affiliation Faculty of Engineering, University of the Ryukyus
Date 2002/6/20
Paper # NC2002-10
Volume (vol) vol.102
Number (no) 157
Page pp.pp.-
#Pages 5
Date of Issue