Remy Kusters

@Michael__Rera @GJ_Both Thanks! Very interesting indeed.

Pour les inscriptions: meetup.com/IBM-Cloud-Pari… Pour l'abstract du papier de recherche de @EloiZablocki: arxiv.org/pdf/2101.05307… RT @vperrin @VasquesXavier @harleydavis @RemyKusters @AAairom @IBM_France

Excited to share the first preprint from the @IBMResearch Paris team. We present a differentiable rule induction algorithm, integrating the interpretability of rule learning with a neural network based prediction model. @IBM_France arxiv.org/abs/2201.06515

Last Friday I had the honour of seeing @GJ_Both succesfully defend his PhD. I am very grateful for all the wonderful work he did during the last three years. It was a pleasure working together.

2ème session du Café -Séminaire IBM Research mensuel sur l'#IA interprétable ce Jeudi 2 à 14h30 ! Nous accueillons Le Pr. Yoshua Bengio du Montreal Institute of Learning Algorithms, prix Turing 2018, qui parlera des Generative Flow Networks-GFlowNets meetup.com/IBM-Cloud-Pari…

"We demonize certain drugs, and celebrate others," says Michael Pollan (@michaelpollan). "Sugar is a drug, and celebrated. But it's high time we demonize it." @nytimes nytimes.com/2021/08/09/opi…

This is pure gold. Or germanium, who can tell. H/T @jim_deane pages.cs.wisc.edu/~kovar/hall.ht…

@arXiv_Daily @GJ_Both

Sparsistent Model Discovery deepai.org/publication/sp… by Georges Tod et al. including @RemyKusters #DeepLearning #Hyperparameter

@arXiv_Daily @GJ_Both

Fully differentiable model discovery deepai.org/publication/fu… by Gert-Jan Both and @RemyKusters #NeuralNetwork #ComputerScience

Our team at @IBMResearch is hiring a senior research scientist (Paris-Saclay) to work on safe, explainable and responsible AI systems. If you have 1+ years of research experience after PhD and are excited to join the team, get in touch! tinyurl.com/47rz2rdd

@stormkees @CriResearch @IBMResearch Hi Kees, thanks and let's catch up soon!

@RemyKusters @CriResearch @IBMResearch Congratulations Rémy! Sounds like a wonderful new challenge. We should catch up some time, curious to hear your plans!

After three fantastic years at @CriResearch I am happy to start a new adventure at @IBMResearch where I will continue to work on interpretable and explainable machine learning

W/@RemyKusters and @GJ_Both we worked on classification of trajectories based on a set of features of them inspired by the challenge by @AndiChallenge Some ongoing progress open for suggestions 👁️ github.com/remykusters/Tr… #trajectories #classification #randomwalks @CriResearch

New paper is out on performing automated model discovery using DeepMoD when very few sensors are available to collect the data. Paper will be presented at the ICLR workshop on AI for Modeling Oceans and Climate Change, May 7th!

The next round for research fellows @CriResearch is open again. Join this fantastic place to do research in the center of Paris!

Interesting read on how AI research shifted from theoretical science to an experimental science but lacking a proper methodology. In my own experience, the majority of papers still don’t share their code/data resulting in an avoidable replication crisis: bit.ly/2IyiW9s

Trust - Our World in Data ourworldindata.org/trust

Trying to discover interpretable models from data: Our team just released a modular package for deep learning-driven model discovery of PDEs and ODEs: DeePyMoD. Paper, code, and documentation is available on: github.com/PhIMaL/DeePyMoD arxiv.org/abs/2011.04336 @GJ_Both @criparis