International Journal of Information and Communication Technology Research
مجله بین المللی ارتباطات و فناوری اطلاعات
International Journal of Information and Communication Technology Research
Engineering & Technology
http://ijict.itrc.ac.ir
1
admin
2251-6107
2783-4425
doi
1652
25391
en
jalali
1398
3
1
gregorian
2019
6
1
11
2
online
1
fulltext
en
Sparse, Robust and Discriminative Representation by Supervised Regularized Auto-encoder
فناوری اطلاعات
Information Technology
پژوهشي
Research
Recent researches have determined that regularized auto-encoders can provide a good representation of data which improves the performance of data classification. These type of auto-encoders which are usually over-complete, provide a representation of data that has some degree of sparsity and is robust against variation of data to extract meaningful information and reveal the underlying structure of data by making a change in classic auto- encoders’ structure and/or adding regularizing terms to the objective function. The present study aimed to propose a novel approach to generate sparse, robust, and discriminative features through supervised regularized auto-encoders, in which unlike most existing auto-encoders, the data labels are used during feature extraction to improve discrimination of the representation and also, the sparsity ratio of the representation is completely adaptive and dynamically determined based on data distribution and complexity. Results reveal that this method has better performance in comparison to other regularized auto-encoders regarding data classification.
Supervised Auto-encoder, Feature Learning, Discriminative Representation, Manifold
29
37
http://ijict.itrc.ac.ir/browse.php?a_code=A-10-1588-1&slc_lang=en&sid=1
Nima
Farajian
nimaff2000@yahoo.com
10031947532846001447
10031947532846001447
Yes
Department of Computer Engineering, Faculty of Computer and Electrical Engineering University of Kashan