Title :
Learning sufficient representation for spatio-temporal deep network using information filter
Author :
Yuhuang Hu ; Neoh, D.T.H. ; Sahari, K.S.M. ; Chu Kiong Loo
Author_Institution :
Dept. of Artificial Intell., Univ. of Malaya, Kuala Lumpur, Malaysia
Abstract :
This article introduced an improved spatio - temporal deep network based on information filter method for learning sufficient representation. The proposed method aims to improve feature learning capability while modeling spatial and temporal dependencies. Experiments on pattern recognition are conducted to validate the effectiveness of the proposed method.
Keywords :
feature extraction; information filtering; information filters; learning (artificial intelligence); neural nets; feature extraction; feature learning capability; information filter method; learning sufficient representation; pattern recognition; spatio-temporal deep network; Clustering algorithms; Computer architecture; Dictionaries; Educational institutions; Encoding; Image reconstruction; Training;
Conference_Titel :
System Integration (SII), 2014 IEEE/SICE International Symposium on
Conference_Location :
Tokyo
Print_ISBN :
978-1-4799-6942-5
DOI :
10.1109/SII.2014.7028116
