Broad Autoencoder Features Learning for Classification Problem

Ting Wang, Wing W. Y. Ng, Wendi Li and Sam Kwong
Additional contact information
Ting Wang: South China University of Technology, Guangzhou, China
Wing W. Y. Ng: South China University of Technology, Guangzhou, China
Wendi Li: South China University of Technology, Guangzhou, China
Sam Kwong: Hong Kong City University, Kowloon, Hong Kong

International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 2021, vol. 15, issue 4, 1-15

Abstract: Activation functions such as Tanh and Sigmoid functions are widely used in Deep Neural Networks (DNNs) and pattern classification problems. To take advantages of different activation functions, the Broad Autoencoder Features (BAF) is proposed in this work. The BAF consists of four parallel-connected Stacked Autoencoders (SAEs) and each of them uses a different activation function, including Sigmoid, Tanh, ReLU, and Softplus. The final learned features can merge such features by various nonlinear mappings from original input features with such a broad setting. This helps to excavate more information from the original input features. Experimental results show that the BAF yields better-learned features and classification performances.

Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... IJCINI.20211001.oa23 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jcini0:v:15:y:2021:i:4:p:1-15

Access Statistics for this article

International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) is currently edited by Kangshun Li

More articles in International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) from IGI Global
Bibliographic data for series maintained by Journal Editor ().