Maxout Networks for Visual Recognition

Gabriel Castaneda, Paul Morris and Taghi M. Khoshgoftaar
Additional contact information
Gabriel Castaneda: Florida Atlantic University, USA
Paul Morris: Florida Atlantic University, USA
Taghi M. Khoshgoftaar: Florida Atalntic University, USA

International Journal of Multimedia Data Engineering and Management (IJMDEM), 2019, vol. 10, issue 4, 1-25

Abstract: This study investigates the effectiveness of multiple maxout activation variants on image classification, facial identification and verification tasks using convolutional neural networks. A network with maxout activation has a higher number of trainable parameters compared to networks with traditional activation functions. However, it is not clear if the activation function itself or the increase in the number of trainable parameters is responsible for yielding the best performance on different entity recognition tasks. This article investigates if an increase in the number of convolutional filters on the rectified linear unit activation performs equal-to or better-than maxout networks. Our experiments compare rectified linear unit, leaky rectified linear unit, scaled exponential linear unit, and hyperbolic tangent to four maxout variants. Throughout the experiments, we found that on average, across all datasets, the rectified linear unit networks perform better than any maxout activation when the number of convolutional filters is increased six times.

Date: 2019
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 18/IJMDEM.2019100101 (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:jmdem0:v:10:y:2019:i:4:p:1-25

Access Statistics for this article

International Journal of Multimedia Data Engineering and Management (IJMDEM) is currently edited by Chengcui Zhang

More articles in International Journal of Multimedia Data Engineering and Management (IJMDEM) from IGI Global
Bibliographic data for series maintained by Journal Editor ().