DocumentCode
1902545
Title
On self-consistent sensory-motor learning algorithm
Author
Hu, Shengfa ; Yan, Pingfan ; Li, Yanda
Author_Institution
Dept. of Autom., Tsinghua Univ., Beijing, China
fYear
1993
fDate
1993
Firstpage
162
Abstract
The uniqueness of the weight vector for the self-consistent sensory-motor learning algorithm and the algorithm´s convergence is investigated. The effect of the choice of the local receptive field´s parameters to sensing noise, intrinsic unit noise, and target function is discussed. An adaptive strategy to choose the local receptive field´s parameter is suggested
Keywords
convergence; learning (artificial intelligence); neural nets; robots; adaptive strategy; convergence; intrinsic unit noise; self-consistent sensory-motor learning algorithm; sensing noise; target function; uniqueness; weight vector; Artificial neural networks; Automation; Cameras; Control systems; Convergence; End effectors; Mechanical systems; Robot kinematics; Robot sensing systems; Topology;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1993., IEEE International Conference on
Conference_Location
San Francisco, CA
Print_ISBN
0-7803-0999-5
Type
conf
DOI
10.1109/ICNN.1993.298550
Filename
298550
Link To Document