A deep contractive autoencoder for solving multiclass classification problems

Aamir, Muhammad and Mohd Nawi, Nazri and Wahid, Fazli and Mahdin, Hairulnizam (2020) A deep contractive autoencoder for solving multiclass classification problems. Evolutionary Intelligence, 14. pp. 1619-1633. ISSN 1864-5909

[img] Text
AJ 2020 (313).pdf
Restricted to Registered users only

Download (5MB) | Request a copy

Abstract

Contractive auto encoder (CAE) is on of the most robust variant of standard Auto Encoder (AE). The major drawback associated with the conventional CAE is its higher reconstruction error during encoding and decoding process of input features to the network. This drawback in the operational procedure of CAE leads to its incapability of going into finer details present in the input features by missing the information worth consideration. Resultantly, the features extracted by CAE lack the true representation of all the input features and the classifier fails in solving classification problems efficiently. In this work, an improved variant of CAE is proposed based on layered architecture following feed forward mechanism named as deep CAE. In the proposed architecture, the normal CAEs are arranged in layers and inside each layer, the process of encoding and decoding take place. The features obtained from the previous CAE are given as inputs to the next CAE. Each CAE in all layers are responsible for reducing the reconstruction error thus resulting in obtaining the informative features. The feature set obtained from the last CAE is given as input to the softmax classifier for classification. The performance and efficiency of the proposed model has been tested on five MNIST variant-datasets. The results have been compared with standard SAE, DAE, RBM, SCAE, ScatNet and PCANet in term of training error, testing error and execution time. The results revealed that the proposed model outperform the aforementioned models.

Item Type: Article
Uncontrolled Keywords: Deep auto encoder; Contractive auto encoder; Feature reduction; Classification; MNIST variants
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800-8360 Electronics
Divisions: Faculty of Computer Science and Information Technology > Department of Software Engineering
Depositing User: Miss Afiqah Faiqah Mohd Hafiz
Date Deposited: 30 Jan 2022 08:21
Last Modified: 30 Jan 2022 08:21
URI: http://eprints.uthm.edu.my/id/eprint/6386

Actions (login required)

View Item View Item