Search Results for author: François Schnitzler

Found 4 papers, 2 papers with code

SkipW: Resource adaptable RNN with strict upper computational limit

no code implementations ICLR 2021 Tsiry Mayet, Anne Lambert, Pascal Leguyadec, Francoise Le Bolzer, François Schnitzler

We introduce Skip-Window, a method to allow recurrent neural networks (RNNs) to trade off accuracy for computational cost during the analysis of a sequence.

Activity Recognition

Off-policy evaluation for MDPs with unknown structure

no code implementations11 Feb 2015 Assaf Hallak, François Schnitzler, Timothy Mann, Shie Mannor

Off-policy learning in dynamic decision problems is essential for providing strong evidence that a new policy is better than the one in use.

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