About
The FAIR Universe project is a collaboration between the
Lawrence Berkeley National Laboratory
,
Université Paris-Saclay
,
University of Washington
, and
ChaLearn
.
The project is funded by the
Department of Energy
.
The collaboration is building a large-compute-scale AI platform for the hosting of large scientific datasets, models, and machine learning competitions to drive forward discoveries in high energy physics and cosmology. The initial focus is on discovering and minimizing systematic uncertainties in High Energy Physics through a sequence of challenges that will bring together researchers across physics and machine learning.
The collaboration includes scientists from Lawrence Berkeley National Laboratory, Université Paris-Saclay, the University of Washington, and ChaLearn, a non-profit that organizes challenges to stimulate research in machine learning.
Goals
We are building an open, large-compute-scale AI ecosystem for sharing datasets, training large models, fine-tuning those models, and hosting challenges and benchmarks. Hosting of all these datasets and benchmarks will be achieved by interfacing the
NERSC
HPC center to
Codabench
, a recently developed open-source platform, to provide a next generation reproducible-science AI ecosystem. This project will build the essential pieces of such an ecosystem through deployment of:
- Three HEP systematic uncertainty datasets and tasks, of increasing sophistication, tailored for studies of systematic-uncertainty aware AI techniques, in particle physics and cosmology.
- A set of HEP-AI challenges and long-lived task and algorithm benchmarks addressing compelling questions about the impact of systematic effects in AI models.
- An HPC-enabled AI benchmark platform capable of hosting datasets and models; producing new simulated datasets; applying new AI algorithms on existing datasets; and applying uploaded AI algo- rithms on new datasets.
The collaboration with Codabench and NERSC will ensure that the project platform, benchmarks and a portfolio of algorithms will be curated and made accessible, and therefore continue to benefit the HEP community, as well as other sciences and the machine learning research community well beyond the end of the project. The research community will benefit from being exposed to well-established, empirical UQ approaches for estimation that experimenters have deployed on problems with hundreds of systematic effects. The develop- ment of principled methodologies to quantify the impact of systematic effects in the training and inference of ML models, will increase the trust of the scientific community on AI methods applied to experimental high-energy physics and beyond. The progressive structure of our challenges will bring together activity across particle physics and cosmology. Finally, both the methods and platform developed in this project will serve as a foundation for future AI challenges and benchmarks in high-energy physics, scientific and industrial applications.
News
FAIR Universe – NeurIPS 2024 Higgs Uncertainty Challenge launched on Codabench
October 01, 2024We have launched the "FAIR Universe – NeurIPS 2024 Higgs Uncertainty Challenge" on Codabench.
FAIR Universe – the challenge of handling uncertainties in fundamental science @ NeurIPS 2024
June 10, 2024Our new challenge "FAIR Universe – the challenge of handling uncertainties in fundamental science" is accepted at NeurIPS 2024 Competition Track.
HiggsML Uncertainty Pilot Competition
March 12, 2024We have launched the pilot version of HiggsML Uncertainty Competition today! Join the competition here:
FAIR Universe @ ACAT 2024
March 07, 2024Wahid Bhimji, FAIR Universe Project Principal Investigator, will deliver a talk about Fair Universe - HiggsML Uncertainty Challenge. Join us at the event:
Particle Physics challenge trial
November 29, 2023We hosted a hackathon at the Artificial Intelligence and the Uncertainty Challenge in Fundamental Physics workshop on Wednesday November 29, 2023. We released a tiral version of a challenge using detailed physics simulations of accelerator data.
First toy challenge
October 2, 2023We have designed and released our first toy challenge on the Codabench platform. This challenge is designed to test the platform and provide a simple example for the community to follow. We have developed a toy dataset to illustrate the types of analyses performed on real data from particle accelerators.
Project Announcement
November 27, 2022The FAIR Universe project received funding as part of a $6.4 million DoE spend on AI in high energy physics: