A walkthrough for the principle of logit separation

Gil Keren, Sivan Sabato, Björn Schuller

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
EditorsSarit Kraus
PublisherInternational Joint Conferences on Artificial Intelligence
Pages6191-6195
Number of pages5
ISBN (Electronic)9780999241141
DOIs
StatePublished - 1 Jan 2019
Event28th International Joint Conference on Artificial Intelligence, IJCAI 2019 - Macao, China
Duration: 10 Aug 201916 Aug 2019

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
Volume2019-August
ISSN (Print)1045-0823

Conference

Conference28th International Joint Conference on Artificial Intelligence, IJCAI 2019
Country/TerritoryChina
CityMacao
Period10/08/1916/08/19

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'A walkthrough for the principle of logit separation'. Together they form a unique fingerprint.

Cite this