AuthorsR. Borgli, H. Borgli, P. Halvorsen, M. Riegler, and H. K. Stensland
TitleAutomatic Hyperparameter Optimization in Keras for the MediaEval 2018 Medico Multimedia Task
AfilliationMachine Learning
Project(s)Department of Holistic Systems
StatusPublished
Publication TypeProceedings, refereed
Year of Publication2018
Conference NameWorking Notes Proceedings of the MediaEval 2018 Workshop
PublisherCEUR Workshop Proceedings (CEUR-WS.org)
Keywordsautomatic hyperparameter optimization, Bayesian optimization, CNN, convolutional neural networks, dataset manipulation, gpyopt, hyperparameter optimization, keras, saga, tensorflow, Transfer Learning
Abstract

This paper details the approach to the MediaEval 2018 Medico Multimedia Task made by the Rune team. The decided upon approach uses a work-in-progress hyperparameter optimization system called Saga. Saga is a system for creating the best hyperparameter finding in Keras, a popular machine learning framework, using Bayesian optimization and transfer learning. In addition to optimizing the Keras classifier configuration, we try manipulating the dataset by adding extra images in a class lacking in images and splitting a commonly misclassified class into two classes.

Citation KeyruneMedico2018