Loss Functions

Early exiting using confidence measures

Introduced by Teerapittayanon et al. in BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks

Exit whenever the model is confident enough allowing early exiting from hidden layers

Source: BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Language Modelling 3 8.82%
Model Compression 2 5.88%
Text Classification 2 5.88%
Named Entity Recognition 2 5.88%
Edge-computing 2 5.88%
Text Generation 1 2.94%
Dialogue Understanding 1 2.94%
NER 1 2.94%
Image Captioning 1 2.94%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories