Self-Organizing Neural Grove and Its Application to Incremental Learning

2013 ◽  
pp. 109-120
Author(s):  
Hirotaka Inoue
Keyword(s):  
Incremental Learning ◽  
Self Organizing

Incremental Learning, Recognition, and Generation of Time-Series Patterns Based on Self-Organizing Segmentation

2006 ◽  
Vol 10 (3) ◽  
pp. 395-408 ◽  
Author(s):  
Shogo Okada ◽  
◽  
Osamu Hasegawa
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Supervised Learning ◽  
Incremental Learning ◽  
Mixture Of Experts ◽  
Matching Method ◽  
Learning Function ◽  
Moving Images ◽  
Motion Unit ◽  
Self Organizing

We segments and symbolizes image information on a series of human behavior as an aggregate unit of motions in a self-organizing manner and proposes a system that recognizes the entire behavior as a symbol string. This system symbolizes the motion unit incrementally and also generates motion from a symbol. To implement the system, we used a mixture of experts with a non-monotonous recurrent neural network used as the expert and our own DP matching method. In addition, our proposal makes not only teacher-labeled patterns, but also teacher-unlabeled patterns available for learning. By using this function, we proposed semi-supervised learning using our proposal in this paper. We verified the evaluation of the effectiveness of our proposal and semi-supervised learning function by two experiments using moving images including seven gestures.

Sign in / Sign up

Export Citation Format

Share Document