Search Results for author: Joud Chataoui

Found 3 papers, 2 papers with code

Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE

no code implementations20 Jun 2024 Florence Regol, Joud Chataoui, Bertrand Charpentier, Mark Coates, Pablo Piantanida, Stephan Gunnemann

Machine learning models can solve complex tasks but often require significant computational resources during inference.

Quantization

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

1 code implementation13 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.

Dynamic neural networks

Cannot find the paper you are looking for? You can Submit a new open access paper.