Florent Gbelidji
Paris, Île-de-France, France
2 k abonnés
+ de 500 relations
Activité
-
Interactive 100m dash explainer from The New York Times is mind-blowing. They used computer vision to track athlete positions every 100ms & calculate…
Interactive 100m dash explainer from The New York Times is mind-blowing. They used computer vision to track athlete positions every 100ms & calculate…
Aimé par Florent Gbelidji
-
In case you missed it, you can use pretty neat Filters to look for datasets on the Hugging Face Hub nowadays: 😍 Filter datasets by: - modalities…
In case you missed it, you can use pretty neat Filters to look for datasets on the Hugging Face Hub nowadays: 😍 Filter datasets by: - modalities…
Aimé par Florent Gbelidji
-
Always an amazing experience to go back to your childhood team Racing Club de Lens with your family, especially when they tie (2-2) against the…
Always an amazing experience to go back to your childhood team Racing Club de Lens with your family, especially when they tie (2-2) against the…
Aimé par Florent Gbelidji
Expérience
Formation
-
CentraleSupélec
-
Activités et associations :President of the Student Sports Union, Member of the rugby team.
Top-ranked French School of Engineering and Applied Science (SEAS) working towards a Master of Science (MSc)
• Expected graduation date : September 2019, -
-
Master of Science in Mathematics, Modeling and Machine Learning.
Key subjects studied: Machine Learning, Optimisation, Stochastic Algorithms, Computer Vision, Inverse Problems, Nonparametric Statistics -
-
Activités et associations :President of the Student Union
• Preparatory classes (Mathematics and Physics section) for the competitive national entrance
examinations to gain entrance into France’s top graduate Schools.
• Key subjects studied : Algebra, Analysis, General Mechanics, Optics, Thermodynamics, Electromagnetism, Fluid Mechanics, General Chemistry, Organic Chemistry, Philosophy. -
-
Publications
-
Deep transform networks for scalable learning of MR reconstruction
Proc. Intl. Soc. Mag. Reson. Med. 27 (2019)
In this work we introduce RadixNet, a fast, scalable, transform network architecture based on the Cooley-Tukey FFT, and use it in a fully-learnt iterative reconstruction with a residual dense U-Net image regularization. Results show that fast transform networks can be trained at 256x256 dimensions and outperform the FFT.
Other authorsSee publication
Brevets
-
Machine-Learned Network for Fourier Transform in Reconstruction for Medical Imaging
Émis le US US20190378311
For low-complexity to learned reconstruction and/or learned Fourier transform-based operators for reconstruction, a neural network is used for the transform operators. The network architecture is modeled on the Cooley-Tukey fast Fourier transform (FFT) approach. By splitting input data before recursive calls in the network architecture, the network may be trained to perform the transform with similar complexity as FFT. The learned operators may be used in a trained network for reconstruction…
For low-complexity to learned reconstruction and/or learned Fourier transform-based operators for reconstruction, a neural network is used for the transform operators. The network architecture is modeled on the Cooley-Tukey fast Fourier transform (FFT) approach. By splitting input data before recursive calls in the network architecture, the network may be trained to perform the transform with similar complexity as FFT. The learned operators may be used in a trained network for reconstruction, such as with a learned iterative framework and image regularizer.
Other inventors -
Langues
-
Anglais
Capacité professionnelle générale
-
Français
Bilingue ou langue natale
-
Espagnol
Compétence professionnelle limitée
-
Russe
Notions
Plus d’activités de Florent
-
Today we release our first foundation model at pleias: OCRonos-Vintage is a 124 million parameters model pretrained end-to-end on 18 billion tokens…
Today we release our first foundation model at pleias: OCRonos-Vintage is a 124 million parameters model pretrained end-to-end on 18 billion tokens…
Aimé par Florent Gbelidji
-
Both are good options. However, LLMs have become so affordable that LLM chunking is usually superior and cost-effective for datasets up to tens of…
Both are good options. However, LLMs have become so affordable that LLM chunking is usually superior and cost-effective for datasets up to tens of…
Aimé par Florent Gbelidji
-
Excited to announce “llm-sagemaker” a new Terraform module to easily deploy open LLMs from Hugging Face to Amazon Web Services (AWS) SageMaker…
Excited to announce “llm-sagemaker” a new Terraform module to easily deploy open LLMs from Hugging Face to Amazon Web Services (AWS) SageMaker…
Aimé par Florent Gbelidji
-
Do you want to learn about quantization? Here are five free resources to get started 1. A Visual Guide to Quantization. Very clear and intuitive by…
Do you want to learn about quantization? Here are five free resources to get started 1. A Visual Guide to Quantization. Very clear and intuitive by…
Aimé par Florent Gbelidji
-
🚀 Huge news in AI! Black Forest Labs just dropped FLUX.1, a groundbreaking text-to-image model suite! 🎨 The results are amazing! 🔥 FLUX.1 comes…
🚀 Huge news in AI! Black Forest Labs just dropped FLUX.1, a groundbreaking text-to-image model suite! 🎨 The results are amazing! 🔥 FLUX.1 comes…
Aimé par Florent Gbelidji
-
LE LYCEE MILITAIRE AUX JO DE PARIS 🗼 En ce moment, les élèves du Lycée militaire d’Autun sont aux Jeux olympiques de Paris 2024 ! 🙂…
LE LYCEE MILITAIRE AUX JO DE PARIS 🗼 En ce moment, les élèves du Lycée militaire d’Autun sont aux Jeux olympiques de Paris 2024 ! 🙂…
Aimé par Florent Gbelidji
-
Very important new enterprise feature to unlock safe AI collaboration by Sylvestre Bouchot & team: Orgs on Hugging Face can now…
Very important new enterprise feature to unlock safe AI collaboration by Sylvestre Bouchot & team: Orgs on Hugging Face can now…
Aimé par Florent Gbelidji
-
𝗟𝗹𝗮𝗺𝗮-𝟯.𝟭 𝗺𝗼𝗱𝗲𝗹𝘀 𝗳𝗶𝗻𝗮𝗹𝗹𝘆 𝗴𝗲𝘁 𝘁𝗵𝗲𝗶𝗿 𝗖𝗵𝗮𝘁𝗯𝗼𝘁 𝗔𝗿𝗲𝗻𝗮 𝗿𝗮𝗻𝗸𝗶𝗻𝗴 🎖️ Given the impressive benchmarks…
𝗟𝗹𝗮𝗺𝗮-𝟯.𝟭 𝗺𝗼𝗱𝗲𝗹𝘀 𝗳𝗶𝗻𝗮𝗹𝗹𝘆 𝗴𝗲𝘁 𝘁𝗵𝗲𝗶𝗿 𝗖𝗵𝗮𝘁𝗯𝗼𝘁 𝗔𝗿𝗲𝗻𝗮 𝗿𝗮𝗻𝗸𝗶𝗻𝗴 🎖️ Given the impressive benchmarks…
Aimé par Florent Gbelidji
-
Premier jour d'ouverture hier et les tribunes du Champions Park étaient déjà pleines 😍 Défilé des médaillés, démonstrations sportives, dj set et…
Premier jour d'ouverture hier et les tribunes du Champions Park étaient déjà pleines 😍 Défilé des médaillés, démonstrations sportives, dj set et…
Aimé par Florent Gbelidji
-
Qu'elles sont belles ces images ! On pouvait pas rêver mieux 😍 chapeau mesdames Sara Balzer et Manon Apithy-Brunet !
Qu'elles sont belles ces images ! On pouvait pas rêver mieux 😍 chapeau mesdames Sara Balzer et Manon Apithy-Brunet !
Aimé par Florent Gbelidji
-
Serverless Inference with Hugging Face and NVIDIA NIM! Excited to announce the latest update on our collaboration between Hugging Face and NVIDIA!…
Serverless Inference with Hugging Face and NVIDIA NIM! Excited to announce the latest update on our collaboration between Hugging Face and NVIDIA!…
Aimé par Florent Gbelidji
-
Merci Mathieu Lehanneur d'avoir imaginé cette vasque volante qui s'élève tous les soirs à 60m de haut et merci EDF de lui donner vie grâce à une…
Merci Mathieu Lehanneur d'avoir imaginé cette vasque volante qui s'élève tous les soirs à 60m de haut et merci EDF de lui donner vie grâce à une…
Aimé par Florent Gbelidji
-
Super proud to announce my new book: the LLM Engineer's Handbook 👷 I think we've built something special with Paul Iusztin and Alex Vesa, focused…
Super proud to announce my new book: the LLM Engineer's Handbook 👷 I think we've built something special with Paul Iusztin and Alex Vesa, focused…
Aimé par Florent Gbelidji