Search Results for author: Diederik Vink

Found 1 papers, 0 papers with code

Multi-Precision Policy Enforced Training (MuPPET) : A Precision-Switching Strategy for Quantised Fixed-Point Training of CNNs

no code implementations ICML 2020 Aditya Rajagopal, Diederik Vink, Stylianos Venieris, Christos-Savvas Bouganis

Large-scale convolutional neural networks (CNNs) suffer from very long training times, spanning from hours to weeks, limiting the productivity and experimentation of deep learning practitioners.

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