Improving the Learning Platform for the Leukocoria Detection Project
dc.contributor.advisor | Hamerly, Gregory James, 1977- | |
dc.contributor.author | Boer, James | |
dc.date.accessioned | 2016-08-31T20:45:08Z | |
dc.date.available | 2016-08-31T20:45:08Z | |
dc.date.issued | 2016-08-31 | |
dc.description.abstract | ABSTRACT Improving the Learning Platform for the Leukocoria Detection Project James Boer, M.S. Mentor: Gregory J. Hamerly, Ph.D. In this paper we describe a new and signi cantly improved learning platform for the leukocoria detection project. We have developed an easily maintainable and extensible system that can train hundreds of semi-random convolutional neural networks very quickly on GPUs. Docker is used to enable simple and platform-agnostic deployment of the system. The Torch machine learning library is used to train the convolutional neural networks and a PostgreSQL database is used to store the training results. A literature review of recent convolutional neural network research is done to nd methods of improving accuracy. Training results are promising, with single-network performance at 96.6% using minimal data and 99.5% using data augmentation | en_US |
dc.identifier.uri | http://hdl.handle.net/2104/9793 | |
dc.license | GPL | en_US |
dc.subject | Leukocoria Dectection | en_US |
dc.title | Improving the Learning Platform for the Leukocoria Detection Project | en_US |