SVM-based Sketch Recognition: Which Hyperparameter Interval to Try?
Loading...
Date
2015
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Hyperparameters are among the most crucial factors that affect the performance of machine learning algorithms. In general, there is no direct method for determining a set of satisfactory parameters, so hyperparameter search needs to be conducted each time a model is to be trained. In this work, we analyze how similar hyperparameters perform across various datasets from the sketch recognition domain. Results show that hyperparameter search space can be reduced to a subspace despite differences in characteristics of datasets.
Description
@inproceedings{10.2312:exp.20151184,
booktitle = {Sketch-Based Interfaces and Modeling},
editor = {Ergun Akleman},
title = {{SVM-based Sketch Recognition: Which Hyperparameter Interval to Try?}},
author = {Yesilbek, Kemal Tugrul and Sen, Cansu and Cakmak, Serike and Sezgin, T. Metin},
year = {2015},
publisher = {The Eurographics Association},
ISBN = {},
DOI = {10.2312/exp.20151184}
}