Broad Autoencoder Features Learning for Classification Problem

Ting WANG, Wing W. Y. NG, Wendi LI, Sam KWONG

Research output: Journal PublicationsJournal Article (refereed)peer-review


Activation functions such as tanh and sigmoid functions are widely used in deep neural networks (DNNs) and pattern classification problems. To take advantage of different activation functions, this work proposes the broad autoencoder features (BAF). 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 by various nonlinear mappings from original input features with such a broad setting. It not only helps to excavate more information from the original input features through utilizing different activation functions, but also provides information diversity and increases the number of input nodes for classifier by parallel-connected strategy. Experimental results show that the BAF yields better-learned features and classification performances.
Original languageEnglish
Article numberoa23
JournalInternational Journal of Cognitive Informatics and Natural Intelligence
Issue number4
Publication statusPublished - Oct 2021
Externally publishedYes

Bibliographical note

This research was funded by National Natural Science Foundation of China under Grant 61876066 and Guangdong Province Science and Technology Plan Project (Collaborative Innovation and Platform Environment Construction) 2019A050510006.


  • Feature Learning
  • Pattern Classification
  • Stacked Autoencoders


Dive into the research topics of 'Broad Autoencoder Features Learning for Classification Problem'. Together they form a unique fingerprint.

Cite this