Volume 11, Issue 2 (6-2019)                   2019, 11(2): 29-37 | Back to browse issues page

XML Print


Department of Computer Engineering, Faculty of Computer and Electrical Engineering University of Kashan , nimaff2000@yahoo.com
Abstract:   (1206 Views)
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. 
Full-Text [PDF 1136 kb]   (422 Downloads)    
Type of Study: Research | Subject: Information Technology

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.