Title :
An Enhanced Structure Based on Standard ART-2 Neural Network
Author :
Qiu, Dong ; Gao, Guoli ; Chen, Hongjun
Author_Institution :
Jilin Univ., Changchun
Abstract :
ART-2 is representative and unsupervised artificial neural network which can recognize complicated inputting patterns self-organized. This paper presents a new pattern aiming to discard amplitude during classifying the data by Standard ART-2 network, especially the time series data. So, we proposed an enhanced pattern based on standard ART-2. Finally, the problem of "discard amplitude" is successfully resolved by new structure and a simulation is given to show the superiority.
Keywords :
neural nets; pattern classification; ART-2 neural network; data classification; self-organized patterns; Adaptive filters; Artificial neural networks; Fuses; Neural networks; Neurofeedback; Neurons; Pattern recognition; Radiofrequency interference; Resonance; Subspace constraints;
Conference_Titel :
Networking, Sensing and Control, 2008. ICNSC 2008. IEEE International Conference on
Conference_Location :
Sanya
Print_ISBN :
978-1-4244-1685-1
Electronic_ISBN :
978-1-4244-1686-8
DOI :
10.1109/ICNSC.2008.4525248
