Neural-Network Inverse Dynamic Online Learning Control on Physical Exoskeleton

2006 ◽  
pp. 702-710 ◽  
Author(s):  
Heng Cao ◽  
Yuhai Yin ◽  
Ding Du ◽  
Lizong Lin ◽  
Wenjin Gu ◽  
...  
Keyword(s):  
Neural Network ◽  
Online Learning ◽  
Learning Control ◽  
Inverse Dynamic

scholarly journals A Novel Neuron in Kernel Domain

2013 ◽  
Vol 2013 ◽  
pp. 1-11 ◽  
Author(s):  
Zahra Khandan ◽  
Hadi Sadoghi Yazdi
Keyword(s):  
Neural Network ◽  
Online Learning ◽  
Mean Square ◽  
Least Mean Square ◽  
Backpropagation Neural Network ◽  
Adaptive Parameters ◽  
Kernel Parameter ◽  
Online Learning Algorithms ◽  
Adaptive Kernel ◽  
Kernel Least Mean Square

Kernel-based neural network (KNN) is proposed as a neuron that is applicable in online learning with adaptive parameters. This neuron with adaptive kernel parameter can classify data accurately instead of using a multilayer error backpropagation neural network. The proposed method, whose heart is kernel least-mean-square, can reduce memory requirement with sparsification technique, and the kernel can adaptively spread. Our experiments will reveal that this method is much faster and more accurate than previous online learning algorithms.

Sign in / Sign up

Export Citation Format

Share Document