Gait synthesis for a biped robot climbing sloping surfaces using neural networks. II. Dynamic learning

2003 ◽  
Author(s):  
A.W. Salatian ◽  
Y.F. Zheng
Keyword(s):  
Neural Networks ◽  
Biped Robot ◽  
Dynamic Learning ◽  
Gait Synthesis

Gait synthesis for a 12-degree-of-freedom biped robot by the LIPM

2018 ◽  
Author(s):  
Christian Alberto Matilde Dominguez ◽  
Eduardo Morales Sanchez ◽  
Gerardo Israel Perez Soto
Keyword(s):  
Biped Robot ◽  
Degree Of Freedom ◽  
Gait Synthesis

DYNAMIC MEMORIZATION CHARACTERISTICS IN NEURAL NETWORKS WITH DIFFERENT NEURONAL DYNAMICS

2007 ◽  
Vol 17 (03) ◽  
pp. 161-170 ◽  
Author(s):  
NAOFUMI KATADA ◽  
HARUHIKO NISHIMURA
Keyword(s):  
Neural Networks ◽  
Stochastic Networks ◽  
Memory Formation ◽  
Experimental Results ◽  
Neuronal Dynamics ◽  
Dynamic Learning ◽  
External Stimulation ◽  
Stimulus Response ◽  
Response Scheme ◽  
Stochastic Activity

We introduce a stimulus-response scheme that supports plastic variation of synapse weights in neural networks, and analyze how memory formation evolves under external stimulation. In so doing, chaotic networks and stochastic networks that have very different dynamics are compared. Experimental results suggest that chaotic activity remarkably outperforms stochastic activity in stimulus-response memorization. This seems to be indicative of effectiveness of the chaos in dynamic learning by stimulus-response scheme oriented to natural learning.

Sign in / Sign up

Export Citation Format

Share Document