Thumbnail Image
Publication

Fine-Grained Categorization Using a Mixture of Transfer Learning Networks

Journal Title
Keywords
transfer learning
 machine learning
Readers/Advisors
Hashem, Sherif, Adriamanalimanana, Bruno, Carpenter, Michael A., Reale, Michael J.
Journal Title
Term and Year
Spring 2021
Publication Date
2021-05-15
Book Title
Publication Volume
Publication Issue
Publication Begin
Publication End
Number of pages
Collections
SUNY Polytechnic Institute College of Engineering
Show all metadata
Files
Thumbnail Image
Firsching_Masters_Project.pdf
Adobe PDF, 885.92 KB
Thumbnail Image
advisor sheet signed Justin - signed cover page - May 2021__ (1) (1).pdf
Adobe PDF, 426.72 KB
Thumbnail Image
signed dec page Firsching_Masters_Project - 13 May 2021 (1) (1).pdf
Adobe PDF, 1.11 MB
Research Projects
Organizational Units
Journal Issue
URI
http://hdl.handle.net/20.500.12648/8624
Abstract
In this paper, we apply a mixture of experts approach to further enhance the accuracy of transfer learning networks on a fine-grained categorization problem, expanding on the work of Firsching and Hashem [4]. Mixture of experts approaches may help to improve accuracy on categorization problems. Likewise, transfer learning is a highly effective tech nique for solving problems in machine learning of varying complexities. We here illustrate that mixtures of trained transfer learning networks, when applied properly, may further improve categorization accuracy.
Citation
DOI
Description
Accessibility Statement
Embedded videos