🥇 Kick-off of our NeurIPS 2024 #ML4CFD Challenge: "Harnessing #MachineLearning for Computational Fluid Dynamics in #Airfoil Design" Machine learning techniques, physical models and simulations hold no secrets for you? This challenge is tailor-made for you! Building upon the 1st edition held from November 2023 to March 2024, this iteration centers on a task fundamental to a well-established physical application: airfoil design simulation, utilizing our #AirfRANS dataset & #LIPSplatform. 🎯 This contest invites you to evaluate solutions based on various criteria encompassing ML accuracy, computational efficiency, Out-Of-Distribution performance, and adherence to physical principles. This competition represents a pioneering effort in exploring ML-driven surrogate methods aimed at optimizing the trade-off between computational efficiency and accuracy in physical simulations Prizes: 🏆 1st: 4000 € 🥈 2nd: 2000 € 🥉 3rd: 1000 € Special prize: 🎓 Best student solution (including PhD students) : 1000 € 🗓 Timeline: - Kick-off: July, 1st - Warm-up phase: July 1st - August 4th - Development phase: August 4th - October 14th - Final phase: October 15th - October 31st 🔗 Register here: https://lnkd.in/eyKxkiYd 🔗 Read more about the LIPS platform: https://lnkd.in/eXBNaYWW 🤝 This challenge is hosted on #Codabench, as part of the #NeurIPS2024 Competitions track. It is co-organized by IRT SystemX, Ansys, NVIDIA, Sorbonne Université, Inria and Criteo. 👥 Organization team: Mouadh Yagoubi, David DANAN, Milad Leyli abadi, Ahmed MAZARI, Florent Bonnet, Jean-Patrick Brunet, Maroua GMATI, Asma Farjallah, Paola Cinnella, patrick gallinari, Marc Schoenauer
IRT SystemX’s Post
More Relevant Posts
-
🏆 There is still time to join our NeurIPS 2024 #ML4CFD Challenge: "Harnessing #MachineLearning for Computational Fluid Dynamics in #Airfoil Design" Machine learning techniques, physical models and simulations hold no secrets for you? This challenge is tailor-made for you! Building upon the 1st edition held from November 2023 to March 2024, this iteration centers on a task fundamental to a well-established physical application: airfoil design simulation, utilizing our #AirfRANS dataset & #LIPSplatform. 🎯 This contest invites you to evaluate solutions based on various criteria encompassing ML accuracy, computational efficiency, Out-Of-Distribution performance, and adherence to physical principles. This competition represents a pioneering effort in exploring ML-driven surrogate methods aimed at optimizing the trade-off between computational efficiency and accuracy in physical simulations Prizes: 🏆 1st: 4000 € 🥈 2nd: 2000 € 🥉 3rd: 1000 € Special prize: 🎓 Best student solution (including PhD students) : 1000 € 🗓 Timeline: - Kick-off: July, 1st - Warm-up phase: July 1st - August 4th - Development phase: August 4th - October 14th - Final phase: October 15th - October 31st 🔗 Register here: https://lnkd.in/eyKxkiYd 🔗 Read more about our LIPS platform: https://lnkd.in/eXBNaYWW 🤝 This challenge is hosted on #Codabench, as part of the #NeurIPS2024 Competitions track. It is co-organized by IRT SystemX, Ansys, NVIDIA, Sorbonne Université, Inria and Criteo. 👥 Organization team: Mouadh Yagoubi, David DANAN, Milad Leyli abadi, Ahmed MAZARI, Florent Bonnet, Jean-Patrick Brunet, Maroua GMATI, Asma Farjallah, Paola Cinnella, patrick gallinari, Marc Schoenauer
To view or add a comment, sign in
-
Following on from MolFlux, we’re also releasing PhysicsML today: an innovative package for physics-based/related models, providing a standardised and modular interface for handling, building and training 3d models with an emphasis on neural network potentials (NNPs). By providing plugins to popular molecular dynamics engines like OpenMM and ASE, PhysicsML facilitates the journey from a trained model to running simulations with NNPs. PhysicsML is freely available and ships with prominent state-of-the-art architectures (including ANI, MACE, Allegro) and can be easily extended to feature new architectures. We also provide access to commonly used quantum mechanical datasets (such as ANI1x, ANI2x, and SPICE) for model training. You can find all the code and documentation here: https://lnkd.in/eAC-sWcf and we look forward to the community contributing to expand the PhysicsML catalogue. #neuralnetpotentials #quantummechanics #3d
To view or add a comment, sign in
-
▶️ See it in action: AI Physics Powered by NVIDIA on Rescale - Explore the first turnkey, full-stack AI-accelerated R&D platform! In the dynamic field of computational science and engineering, AI plays a pivotal role by automating critical tasks like data collection, model development, optimization, and design exploration. The integration of neural networks is particularly exciting, offering efficient approximations for complex simulations through streamlined algorithms and GPU acceleration. Rescale’s AI Physics platform, powered by NVIDIA, seamlessly merges applied AI Physics with cutting-edge NVIDIA technologies. From weather predictions to Molecular Dynamics, Biomechanics simulations, Cardiovascular CFD, Heat Exchanger Optimization, and Turbomachinery flows. In this demo video, see how users gain access to optimized infrastructures via a straightforward workflow submission process. #AIPhysics #AI #NVIDIA #Engineering
To view or add a comment, sign in
-
🏁 Revving Up Innovation: GM Motorsports Takes the Lead with AI Physics on Rescale! 🏁 Exciting times ahead for motorsports enthusiasts! GM Motorsports is redefining the game with groundbreaking AI-accelerated aerodynamics optimization. 🚗💨 In the high-stakes world of Formula One racing, where every millisecond counts, the Andretti Cadillac team is leveraging AI Physics on Rescale, powered by NVIDIA, to fine-tune chassis aerodynamics like never before. By harnessing the latest technologies from NVIDIA, Microsoft Azure, and Navasto, GM is not just speeding up cars on the track but also accelerating R&D decision-making with unprecedented efficiency and performance. 🌐🔬 Interested in learning how this innovative solution can accelerate your organization's R&D? Reach out or DM me to schedule a demo or a 1-on-1 meeting to explore the possibilities! #GMMotorsports #AIInnovation #Rescale #FormulaOne #NVIDIA #MicrosoftAzure #Navasto #Aerodynamics #EngineeringExcellence
📈 More Traffic, Leads & Deals for Agencies, Consultants, Service Providers & Experts | 🚀 Mechanical Engineer | 🧠 AI in Marketing
AI Physics Powered by NVIDIA 🧠 How AI Physics powered by NVIDIA on Rescale can transform your engineering processes👇 - 1000X+ Faster Simulations: Utilise trained AI Physics models to run inference in milliseconds, drastically reducing traditional simulation times and speeding up design optimisation from weeks to hours. - High Accuracy & Efficiency: Achieve over 98% accuracy compared to traditional CFD simulations and improve computing resource efficiency by 85%. 🌎 Read more: https://lnkd.in/eV9yEzec 📥 Latest newsletter: https://lnkd.in/d7B7fqA #engineeredmind #science #technology #engineering #mechanicalengineering #physics #mathematics #cfd #simulation
To view or add a comment, sign in
-
Hallucinations don’t just plague LLM adoption. The incorrect prediction of machine learning models also plague efforts to leverage machine learning in science. Hallucinations are particularly insidious in physics based simulations because small errors compound into large errors and infrequent but large errors derail simulations. At Physics Inverted Materials (PHIN), our breakthrough uncertainty quantification allows us to eliminate hallucinations in our machine learning models making them indistinguishable from density functional theory (DFT). PHIN Materials believes that only by creating trustable machine learning models can we leverage the significant performance benefits of ML, paving the way for #DigitizingMaterialsDevelopment. Read more about our state of the art technology, PHIN-atmoic, at our latest blog post ➡ https://lnkd.in/eFzJM-wP #machinelearning #materialsdevelopment #RandD #ai4science #PHINMaterials
To view or add a comment, sign in
-
🎉 Exciting News! 🎉 Just upgraded my toolkit with an RTX3090 GPU! 💻 If you or someone in your circle needs virtual screening assays, molecular docking, or MD simulations📊 to complement your experimental findings, I'm here to help!🤝 🚀 Beyond that, if you share a passion for bioinformatics and are ready to embark on impactful research initiatives, I invite you to connect with me! Let's collaborate and drive innovation together. 🌟💡 #Bioinformatics #Research #Innovation #Science #Collaboration #VirtualScreening #MolecularDocking #MDSimulation #RTX3090 #GPU #Networking
To view or add a comment, sign in
-
Learn about BITS: Bi-Level Imitation for Traffic Simulation from the #NVIDIA Research team. BITS is a bi-level imitation learning model that captures the complexity of real world traffic with incredibly fidelity while outperforming previous modeling methods. BITS improved coverage and diversity in traffic scenarios over the next best-performing model by 64% and 118%, respectively, and lowered failure rates by 36%, in a trial conducted for the paper.
Simulating Traffic Behavior with a Bi-Level Imitation Learning AI Model
share.nvidia.com
To view or add a comment, sign in
-
Great read! I especially loved this quote: "While I bow down to our supreme AI overlords in pursuit of this future, we are not there yet." It seems like the file format really matters here, correct? Most of the text-to-3D frameworks I've seen are generating meshes or STL/OBJs. Would it not make more sense to use a 3D data structure that's more workable with an LLM? Like a JSON or YAML file of a CSG tree? Correct me if I'm wrong here. I assume they are using meshes due to the abundance of data to train on. Additionally, it feels like vision capabilities are a must for the future of this workflow. Whether it's used to define a part's bounding area, constraints, or other specific requirements - it would be much easier and faster for an engineer to provide those reqs via an image, rendering, or diagram rather than via text description. You did link to an interesting paper about VLMs for engineering design -- I still need to read it. Either way, very interesting write up. And it's really cool how you used this tool in an unintended way to explore possibilities for engineering. I'm super excited to see where this is heading.
https://lnkd.in/gWrAX4Nu Experimenting with the latest LLM and VLM to engineer parts can be fun, but is it useful, yet? Misusing NVIDIA and Shutterstock's Edify-3D to help frame the discussion around 'Generative Engineering' and 'AI Driven Design' and where the work lies in making anything close to expectations meet reality. Many of the speakers at CDFAM - Computational Design Symposium in Berlin are experts in this space so if you would like a deeper dive than my morning with Edify, register to attend. https://lnkd.in/ebW6rEXp
To view or add a comment, sign in
-
🚀 Advanced Helmet and Glasses Detection System🚀 I'm thrilled to share a cutting-edge computer vision project I've been working on with my talented friend M. Abdullah at Disruptive AI. We've developed a sophisticated system for detecting helmets and glasses in video streams, pushing the boundaries of real-time object detection and segmentation. 🔍 Key Features: - Utilized Ultralytics SAM2 and FastSAM models for precise segmentation - Implemented Ultralytics YOLOv10 nano models fine-tuned on custom helmet and glasses datasets - Achieved real-time processing through multi-threading and optimization techniques 🎥 Video Demo: I've just uploaded a video showcasing our system using the SAM2 model. Stay tuned for another demo with FastSAM results coming soon! We're currently fine-tuning the FastSAM model to improve its accuracy for our specific use case. 💡 Technical Insights: - SAM2 model: Designed for processing entire videos as frame sequences, stored in its architecture's memory block. While this approach yields high-quality results, it posed challenges for real-time applications. We optimized performance by processing every 10th frame. - FastSAM: A promising alternative we're exploring for improved real-time performance. 🧠 Challenges Overcome: 1. Data scarcity: Sourcing high-quality, relevant datasets was a significant hurdle. 2. Dataset enhancement: We manually updated and annotated additional data to improve model performance for our specific use case. 3. Real-time processing: Balancing speed and accuracy required innovative solutions, including multi-threading for parallel processing. ⚡ Performance Note: While my NVIDIA GeForce GTX 1060 doesn't support bfloat16 quantization, users with Turing or Ampere architecture GPUs should see even faster and better performance! Github: https://lnkd.in/dAAk3Did #ComputerVision #DeepLearning #ObjectDetection #AI #Safety #Innovation
To view or add a comment, sign in
-
Real-time Physics simulations and Machine Learning convergence is the next big thing in industrial AI and the productive metaverse. Working on it at MYWAI IM me if you have any interest on the topic. https://lnkd.in/djkZeEnX
Real-time Physics Simulations and Machine Learning
seyedhn.medium.com
To view or add a comment, sign in
6,999 followers
CEO at Holbrook Aerospace
1moNvidia is about the size of 4% of the US economy, and they are hosting a contest like this, with a prize pool this small? My suggestion to anyone considering this; If you come up with something good enough to win 1st, these kinds of companies will pay 10-50x the first prize pool for it. 🤷♂️