Search Results for author: Marcus Rüb

Found 1 papers, 0 papers with code

TinyProp -- Adaptive Sparse Backpropagation for Efficient TinyML On-device Learning

no code implementations17 Aug 2023 Marcus Rüb, Daniel Maier, Daniel Mueller-Gritschneder, Axel Sikora

On average, TinyProp is 2. 9 times faster than existing, static sparse backpropagation algorithms and the accuracy loss is reduced on average by 6 % compared to a typical static setting of the back-propagation ratio.

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