Sparse, Robust and Discriminative Representation by Supervised Regularized Auto-Encoder

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 provides a representation of data that has some degree of sparsity and is robust against variation of data to extract useful information and reveal the underlying structure of data. 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 with data distribution. Results reveal that this method has better performance in comparison to other regularized auto-encoders regarding data classification.