Cited 0 time in webofscience Cited 0 time in scopus

Classification performance analysis regarding margin of energy-based model

Title
Classification performance analysis regarding margin of energy-based model
Authors
Kang, Myeong K.Park, Kyo H.Kim, Seong W.Kim, Min J.Lee, Sang Cheol
DGIST Authors
Lee, Sang Cheol
Issue Date
2017-12-28
Citation
2017 International Conference on Industrial Design Engineering, ICIDE 2017, 34-37
Type
Conference
ISBN
9781450348669
Abstract
When you train an energy-based model, it is important to set a good margin. However, it is almost impossible to train a good margin using stochastic gradient descent (SDG). Because the margin will saturate to zero while minimizing the cost function. For that reason, we usually set the margin to a non-trainable scalar to penalize offending answers linearly to more apart than a certain distance. A good performance setting relates to the length of margin and dimension to which the feature being mapped. In this paper, we will show that a large margin does not always lead to a better performance and affirm the well-tuned margin can achieve better results. © 2017 Association for Computing Machinery.
URI
http://hdl.handle.net/20.500.11750/9048
DOI
10.1145/3178264.3178280
Publisher
Association for Computing Machinery
Related Researcher
Files:
There are no files associated with this item.
Collection:
Convergence Research Center for Future Automotive Technology2. Conference Papers


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE