Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN

no code implementations • 13 Oct 2023 • Florence Regol, Joud Chataoui, Mark Coates

Training an EDNN architecture is challenging as it consists of two intertwined components: the gating mechanism (GM) that controls early-exiting decisions and the intermediate inference modules (IMs) that perform inference from intermediate representations.