IEICE Technical Committee Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
Tech. Rep. Archives
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2006-03-16 14:30
Application of a Forward-propagation Learning Rule for Adaptive Motor Control with Mixture Models
Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno (Toyohashi Univ. Tech.)
Abstract (in Japanese) (See Japanese page) 
(in English) We have proposed a forward-propagation learning (FPL) rule for acquiring neural inverse models. FPL can solve a credit assignment problem based on Newton-like method, while FPL has required evaluating the covariance of forward-propagated signals for goal-directed learning. In the current work, FPL is applied to several learning models which can be described by suitable probability representations, while former FPL could be only applied to multi-layered perceptron (MLP). Moreover, we propose a method to acquire an approximated inverse model which should be required in FPL in advance.
Keyword (in Japanese) (See Japanese page) 
(in English) forward-propagation learning rule / maximum likelihood estimation / normalized gaussian network / multiple paired forward and inverse model / TD learning / / /  
Reference Info. IEICE Tech. Rep., vol. 105, no. 658, NC2005-145, pp. 121-126, March 2006.
Paper # NC2005-145 
Date of Issue 2006-03-09 (NC) 
ISSN Print edition: ISSN 0913-5685
Download PDF

Conference Information
Committee NC  
Conference Date 2006-03-15 - 2006-03-17 
Place (in Japanese) (See Japanese page) 
Place (in English) Tamagawa University 
Topics (in Japanese) (See Japanese page) 
Topics (in English) General 
Paper Information
Registration To NC 
Conference Code 2006-03-NC 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Application of a Forward-propagation Learning Rule for Adaptive Motor Control with Mixture Models 
Sub Title (in English)  
Keyword(1) forward-propagation learning rule  
Keyword(2) maximum likelihood estimation  
Keyword(3) normalized gaussian network  
Keyword(4) multiple paired forward and inverse model  
Keyword(5) TD learning  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Yoshihiro Ohama  
1st Author's Affiliation Toyohashi University of Technology (Toyohashi Univ. Tech.)
2nd Author's Name Naohiro Fukumura  
2nd Author's Affiliation Toyohashi University of Technology (Toyohashi Univ. Tech.)
3rd Author's Name Yoji Uno  
3rd Author's Affiliation Toyohashi University of Technology (Toyohashi Univ. Tech.)
4th Author's Name  
4th Author's Affiliation ()
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2006-03-16 14:30:00 
Presentation Time 25 minutes 
Registration for NC 
Paper # NC2005-145 
Volume (vol) vol.105 
Number (no) no.658 
Page pp.121-126 
#Pages
Date of Issue 2006-03-09 (NC) 


[Return to Top Page]

[Return to IEICE Web Page]


The Institute of Electronics, Information and Communication Engineers (IEICE), Japan