Broad Autoencoder Features Learning for Classification Problem

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number23
Journal / PublicationInternational Journal of Cognitive Informatics and Natural Intelligence
Volume15
Issue number4
Publication statusPublished - Oct 2021

Link(s)

Abstract

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.

Research Area(s)

  • Feature Learning, Pattern Classification, Stacked Autoencoders

Download Statistics

No data available