A walkthrough for the principle of logit separation

  • We consider neural network training, in applications in which there are many possible classes, but at test-time, the task is a binary classification task of determining whether the given example belongs to a specific class. We define the Single Logit Classification (SLC) task: training the network so that at test-time, it would be possible to accurately identify whether the example belongs to a given class in a computationally efficient manner, based only on the output logit for this class. We propose a natural principle, the Principle of Logit Separation, as a guideline for choosing and designing loss functions that are suitable for SLC. We show that the Principle of Logit Separation is a crucial ingredient for success in the SLC task, and that SLC results in considerable speedups when the number of classes is large.

Download full text files

Export metadata

Statistics

Number of document requests

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Gil Keren, Sivan Sabato, Björn SchullerORCiDGND
URN:urn:nbn:de:bvb:384-opus4-717468
Frontdoor URLhttps://opus.bibliothek.uni-augsburg.de/opus4/71746
URL:https://www.ijcai.org/proceedings/2019/
ISBN:978-0-9992411-4-1OPAC
Parent Title (English):Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), Macao, 10-16 August 2019
Publisher:AAAI Press
Place of publication:Palo Alto, CA
Editor:Sarit Kraus
Type:Conference Proceeding
Language:English
Year of first Publication:2019
Publishing Institution:Universität Augsburg
Release Date:2020/03/04
First Page:6191
Last Page:6195
DOI:https://doi.org/10.24963/ijcai.2019/861
Institutes:Fakultät für Angewandte Informatik
Fakultät für Angewandte Informatik / Institut für Informatik
Fakultät für Angewandte Informatik / Institut für Informatik / Lehrstuhl für Embedded Intelligence for Health Care and Wellbeing
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):Deutsches Urheberrecht