Title :
An improved architecture based on typical ART-2 neural network
Author :
Lv, Xiujiang ; Yao, Guangshun ; Zhao, Yan ; Zhang, Qiwen ; Li, Yu´e ; Wang, Ning
Author_Institution :
Dept. of Electron. & Electr. Eng., Changchun Univ. of Technol.
Abstract :
ART-2 is a self-organized and unsupervised artificial neural network constructed from adaptive resonance theory which can be used to classify continuous active data. But we found that the network has just used the big amplitude information during classifying the data by typical ART-2 network, especially the time series data. Therefore, we proposed an improved architecture based on typical ART-2. Then, we point out the superiority of improved ART-2 network over typical ART-2 network in theory. At last, a simulation is given to show the superiority
Keywords :
adaptive resonance theory; neural nets; time series; unsupervised learning; ART-2 neural network; adaptive resonance theory; self-organized neural network; time series data; unsupervised artificial neural network; Adaptive filters; Adaptive systems; Artificial neural networks; Electronic mail; Feedback loop; Neural networks; Neurofeedback; Neurons; Resonance; Subspace constraints;
Conference_Titel :
Systems and Control in Aerospace and Astronautics, 2006. ISSCAA 2006. 1st International Symposium on
Conference_Location :
Harbin
Print_ISBN :
0-7803-9395-3
DOI :
10.1109/ISSCAA.2006.1627563
