探花直播 of Cambridge - Miles Cranmer

New datasets will train AI models to think like scientists

sc604 — Mon, 02 Dec 2024 15:59:08 +0000

探花直播initiative, called Polymathic AI, uses technology like that powering large language models such as OpenAI鈥檚 ChatGPT or Google鈥檚 Gemini. But instead of ingesting text, the project鈥檚 models learn using scientific datasets from across astrophysics, biology, acoustics, chemistry, fluid dynamics and more, essentially giving the models cross-disciplinary scientific knowledge.

鈥淭hese datasets are by far the most diverse large-scale collections of high-quality data for machine learning training ever assembled for these fields,鈥� said team member Michael McCabe from the Flatiron Institute in New York City. 鈥淐urating these datasets is a critical step in creating multidisciplinary AI models that will enable new discoveries about our universe.鈥�

On 2 December, the Polymathic AI team released two of its open-source training dataset collections to the public 鈥� a colossal 115 terabytes, from dozens of sources 鈥� for the scientific community to use to train AI models and enable new scientific discoveries. For comparison, GPT-3 used 45 terabytes of uncompressed, unformatted text for training, which ended up being around 0.5 terabytes after filtering.

探花直播full datasets are available to download for free on HuggingFace, a platform hosting AI models and datasets. 探花直播Polymathic AI team provides further information about the datasets in two papers accepted for presentation at the NeurIPS machine learning conference, to be held later this month in Vancouver, Canada.

鈥淛ust as LLMs such as ChatGPT learn to use common grammatical structure across languages, these new scientific foundation models might reveal deep connections across disciplines that we鈥檝e never noticed before,鈥� said Cambridge team lead聽Dr Miles Cranmer from Cambridge鈥檚 Institute of Astronomy. 鈥淲e might uncover patterns that no human can see, simply because no one has ever had both this breadth of scientific knowledge and the ability to compress it into a single framework.鈥�

AI tools such as machine learning are increasingly common in scientific research, and were recognised in two of this year鈥檚 Nobel Prizes. Still, such tools are typically purpose-built for a specific application and trained using data from that field. 探花直播Polymathic AI project instead aims to develop models that are truly polymathic, like people whose expert knowledge spans multiple areas. 探花直播project鈥檚 team reflects intellectual diversity, with physicists, astrophysicists, mathematicians, computer scientists and neuroscientists.

探花直播first of the two new training dataset collections focuses on astrophysics. Dubbed the Multimodal Universe, the dataset contains hundreds of millions of astronomical observations and measurements, such as portraits of galaxies taken by NASA鈥檚 James Webb Space Telescope and measurements of our galaxy鈥檚 stars made by the European Space Agency鈥檚 Gaia spacecraft.

探花直播other collection 鈥� called the Well 鈥� comprises over 15 terabytes of data from 16 diverse datasets. These datasets contain numerical simulations of biological systems, fluid dynamics, acoustic scattering, supernova explosions and other complicated processes.聽Cambridge researchers played a major role in developing both dataset collections, working alongside PolymathicAI and other international collaborators.

While these diverse datasets may seem disconnected at first, they all require the modelling of mathematical equations called partial differential equations. Such equations pop up in problems related to everything from quantum mechanics to embryo development and can be incredibly difficult to solve, even for supercomputers. One of the goals of the Well is to enable AI models to churn out approximate solutions to these equations quickly and accurately.

鈥淏y uniting these rich datasets, we can drive advancements in artificial intelligence not only for scientific discovery, but also for addressing similar problems in everyday life,鈥� said Ben Boyd, PhD student in the Institute of Astronomy.

Gathering the data for those datasets posed a challenge, said team member Ruben Ohana from the Flatiron Institute. 探花直播team collaborated with scientists to gather and create data for the project. 鈥� 探花直播creators of numerical simulations are sometimes sceptical of machine learning because of all the hype, but they鈥檙e curious about it and how it can benefit their research and accelerate scientific discovery,鈥� he said.

探花直播Polymathic AI team is now using the datasets to train AI models. In the coming months, they will deploy these models on various tasks to see how successful these well-rounded, well-trained AIs are at tackling complex scientific problems.

鈥淚t will be exciting to see if the complexity of these datasets can push AI models to go beyond merely recognising patterns, encouraging them to reason and generalise across scientific domains,鈥� said Dr Payel Mukhopadhyay from the Institute of Astronomy. 鈥淪uch generalisation is essential if we ever want to build AI models that can truly assist in conducting meaningful science.鈥�

鈥淯ntil now, haven鈥檛 had a curated scientific-quality dataset cover such a wide variety of fields,鈥� said Cranmer, who is also a member of Cambridge鈥檚 Department of Applied Mathematics and Theoretical Physics. 鈥淭hese datasets are opening the door to true generalist scientific foundation models for the first time. What new scientific principles might we discover? We're about to find out, and that's incredibly exciting.鈥�

探花直播Polymathic AI project is run by researchers from the Simons Foundation and its Flatiron Institute, New York 探花直播, the 探花直播 of Cambridge, Princeton 探花直播, the French Centre National de la Recherche Scientifique and the Lawrence Berkeley National Laboratory.

Members of the Polymathic AI team from the 探花直播 of Cambridge include PhD students, postdoctoral researchers and faculty across four departments: the Department of Applied Mathematics and Theoretical Physics, the Department of Pure Mathematics and Mathematical Statistics, the Institute of Astronomy and the Kavli Institute for Cosmology.

What can exploding stars teach us about how blood flows through an artery? Or swimming bacteria about how the ocean鈥檚 layers mix? A collaboration of researchers, including from the 探花直播 of Cambridge, has reached a milestone toward training artificial intelligence models to find and use transferable knowledge between fields to drive scientific discovery.

Alex Meng, Aaron Watters and the Well Collaboration

A mosaic of simulations included in the Well collection of datasets

探花直播text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright 漏探花直播 of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways 鈥� on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Scientists begin building AI for scientific discovery using tech behind ChatGPT

sc604 — Fri, 13 Oct 2023 10:55:15 +0000

While ChatGPT deals in words and sentences, the team鈥檚 AI will learn from numerical data and physics simulations from across scientific fields to aid scientists in modelling everything from supergiant stars to the Earth鈥檚 climate.

探花直播team launched the initiative, called Polymathic AI earlier this week, alongside the publication of a series of related scientific papers on the arXiv.org open access repository.

鈥淭his will completely change how people use AI and machine learning in science,鈥� said Polymathic AI principal investigator Shirley Ho, a group leader at the Flatiron Institute鈥檚 Center for Computational Astrophysics in New York City.

探花直播idea behind Polymathic AI 鈥渋s similar to how it鈥檚 easier to learn a new language when you already know five languages,鈥� said Ho.

Starting with a large, pre-trained model, known as a foundation model, can be both faster and more accurate than building a scientific model from scratch. That can be true even if the training data isn鈥檛 obviously relevant to the problem at hand.

鈥淚t鈥檚 been difficult to carry out academic research on full-scale foundation models due to the scale of computing power required,鈥� said co-investigator Miles Cranmer, from Cambridge鈥檚 Department of Applied Mathematics and Theoretical Physics and Institute of Astronomy. 鈥淥ur collaboration with Simons Foundation has provided us with unique resources to start prototyping these models for use in basic science, which researchers around the world will be able to build from 鈥� it鈥檚 exciting.鈥�

鈥淧olymathic AI can show us commonalities and connections between different fields that might have been missed,鈥� said co-investigator Siavash Golkar, a guest researcher at the Flatiron Institute鈥檚 Center for Computational Astrophysics. 鈥淚n previous centuries, some of the most influential scientists were polymaths with a wide-ranging grasp of different fields. This allowed them to see connections that helped them get inspiration for their work. With each scientific domain becoming more and more specialised, it is increasingly challenging to stay at the forefront of multiple fields. I think this is a place where AI can help us by aggregating information from many disciplines.鈥�

探花直播Polymathic AI team includes researchers from the Simons Foundation and its Flatiron Institute, New York 探花直播, the 探花直播 of Cambridge, Princeton 探花直播 and the Lawrence Berkeley National Laboratory. 探花直播team includes experts in physics, astrophysics, mathematics, artificial intelligence and neuroscience.

Scientists have used AI tools before, but they鈥檝e primarily been purpose-built and trained using relevant data. 鈥淒espite rapid progress of machine learning in recent years in various scientific fields, in almost all cases, machine learning solutions are developed for specific use cases and trained on some very specific data,鈥� said co-investigator Francois Lanusse, a cosmologist at the Centre national de la recherche scientifique (CNRS) in France. 鈥淭his creates boundaries both within and between disciplines, meaning that scientists using AI for their research do not benefit from information that may exist, but in a different format, or in a different field entirely.鈥�

Polymathic AI鈥檚 project will learn using data from diverse sources across physics and astrophysics (and eventually fields such as chemistry and genomics, its creators say) and apply that multidisciplinary savvy to a wide range of scientific problems. 探花直播project will 鈥渃onnect many seemingly disparate subfields into something greater than the sum of their parts,鈥� said project member Mariel Pettee, a postdoctoral researcher at Lawrence Berkeley National Laboratory.

鈥淗ow far we can make these jumps between disciplines is unclear,鈥� said Ho. 鈥淭hat鈥檚 what we want to do 鈥� to try and make it happen.鈥�

ChatGPT has well-known limitations when it comes to accuracy (for instance, the chatbot says 2,023 times 1,234 is 2,497,582 rather than the correct answer of 2,496,382). Polymathic AI鈥檚 project will avoid many of those pitfalls, Ho said, by treating numbers as actual numbers, not just characters on the same level as letters and punctuation. 探花直播training data will also use real scientific datasets that capture the physics underlying the cosmos.

Transparency and openness are a big part of the project, Ho said. 鈥淲e want to make everything public. We want to democratise AI for science in such a way that, in a few years, we鈥檒l be able to serve a pre-trained model to the community that can help improve scientific analyses across a wide variety of problems and domains.鈥�

An international team of scientists, including from the 探花直播 of Cambridge, have launched a new research collaboration that will leverage the same technology behind ChatGPT to build an AI-powered tool for scientific discovery.

Yuichiro Chino via Getty Images

Network and data connection on a dark blue background.

探花直播text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright 漏探花直播 of Cambridge and licensors/contributors as identified.聽 All rights reserved. We make our image and video content available in a number of ways 鈥� as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes