OctConv can replace a standard convolution in neural networks without requiring any other network architecture adjustments. It can boost accuracy for image- and video-recognition tasks, while reducing the memory and computational footprint. ai.facebook.com/blog/octconv-a… #ICCV2019

Check out our new paper)

Excited to be presenting my work on Factorized Higher-Order CNNs, with an Application to Spatio-Temporal Emotion Estimation, with @antoinetslc, Adrian Bulat, Yannis Panagakis, Timothy Hospedales and Maja Pantic at CVPR News #CVPR2020 openaccess.thecvf.com/content_CVPR_2… 1/4

Can't wait to learn an interpolation based trick to speed up NeuralODEs? Come to our #NeurIPS2020 poster at 9:00-11:00 PDT, Dec. 8th (Poster Session 2)! arxiv.org/abs/2003.05271

Participate in NeurIPS 2021 Shifts Challenge on uncertainty and robustness to distributional shift! Test how robust is your model!

Check out our new papers on memory footprint reduction during training!

Thrilled to have two papers presented at ICML Conference! Dive in and explore our research on memory-efficient training of neural networks! #ICML2023 #EfficientML

Dans le cadre de #NeurIPS2023, l'équipe Topal, Scool, NVIDIA AI et l'UFRJ organisent un atelier sur l'entraînement efficace des #réseaux de #neurones. A vos stylos : un appel à communications est lancé jusqu'au 29/09 ! 👉 want-ai-hpc.github.io/neurips2023/ca…

📢 Join us at the #AI #WANTScale workshop at #NeurIPS 2023 to learn all about training neural architectures at scale, and come present your work! We have a stellar set of invited speakers who will tackle the various aspects of scaling up in practice: ▪️ Bryan Catanzaro from NVIDIA

Come to #WANT NeurIPS Conference on Dec'16 want-ai-hpc.github.io to discuss tips and tricks for efficient training! Share your thoughts and insights by filling out the poll forms.gle/mdvA14reSdhjYF… ! Stats will be posted during the workshop! #AI #HPC #EfficientTraining

Dans le cadre de la conférence #NeurIPS2023, participez à une collecte de statistiques sur la façon dont les #réseaux #neuronaux sont entrainés 👉 docs.google.com/forms/d/e/1FAI… Les résultats seront partagés et discutés lors de l'atelier #WANT NeurIPS Conference le 16 décembre.

#WANT NeurIPS Conference workshop want-ai-hpc.github.io is happening now! Join for talks and panel on efficient training at room 243-245 or at neurips.cc/virtual/2023/w…. Next poster session is at 5-5.30pm (GMT+6) offline and in Gather Town. See you there!

Learning a lot about AI for physical sciences at the GAP workshop in Grenoble today ✅PINNs with Emmanuel de Bézenac ✅Neural ODEs & DL training with Julia Gusak gap2024.sciencesconf.org

[EVENT 📣] The end 😥 The Grenoble #ArtificialIntelligence for Physical Sciences workshop is now over ! Thanks to all speakers and attendees, we hope you've enjoyed these times of sharing 🤝 👋 Dr. Chris Rackauckas Emmanuel de Bézenac Gilles Louppe Julia Gusak Marylou Gabrié