TY - GEN
T1 - A walkthrough for the principle of logit separation
AU - Keren, Gil
AU - Sabato, Sivan
AU - Schuller, Björn
N1 - Publisher Copyright:
© 2019 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2019/1/1
Y1 - 2019/1/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85074924310&partnerID=8YFLogxK
U2 - 10.24963/ijcai.2019/861
DO - 10.24963/ijcai.2019/861
M3 - Conference contribution
AN - SCOPUS:85074924310
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 6191
EP - 6195
BT - Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
A2 - Kraus, Sarit
PB - International Joint Conferences on Artificial Intelligence
T2 - 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
Y2 - 10 August 2019 through 16 August 2019
ER -