An international team of scientists, including from the University 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.
The team launched the initiative, called Polymathic AI earlier this week, alongside the publication of a series of related papers on the arXiv open access repository.
“This will completely change how people use AI and machine learning in science,” said Polymathic AI principal investigator Shirley Ho, a group leader at the Flatiron Institute’s Center for Computational Astrophysics in New York City.
The idea behind Polymathic AI “is similar to how it’s easier to learn a new language when you already know five languages,” 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’t obviously relevant to the problem at hand.
“It’s been difficult to carry out academic research on full-scale foundation models due to the scale of computing power required,” said co-investigator Miles Cranmer, from Cambridge’s Department of Applied Mathematics and Theoretical Physics and Institute of Astronomy. “Our 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—it’s exciting.”
“Polymathic AI can show us commonalities and connections between different fields that might have been missed,” said co-investigator Siavash Golkar, a guest researcher at the Flatiron Institute’s Center for Computational Astrophysics.
“In 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 specialized, 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.”
“Despite 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,” said co-investigator Francois Lanusse, a cosmologist at the Center national de la recherche scientifique (CNRS) in France.
“This 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.”
Polymathic AI’s 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. The project will “connect many seemingly disparate subfields into something greater than the sum of their parts,” said project member Mariel Pettee, a postdoctoral researcher at Lawrence Berkeley National Laboratory.
“How far we can make these jumps between disciplines is unclear,” said Ho. “That’s what we want to do—to try and make it happen.”
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’s 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. The 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. “We want to make everything public. We want to democratize AI for science in such a way that, in a few years, we’ll 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.”
More information: Michael McCabe et al, Multiple Physics Pretraining for Physical Surrogate Models, arXiv (2023). DOI: 10.48550/arxiv.2310.02994
Siavash Golkar et al, xVal: A Continuous Number Encoding for Large Language Models, arXiv (2023). DOI: 10.48550/arxiv.2310.02989
Francois Lanusse et al, AstroCLIP: Cross-Modal Pre-Training for Astronomical Foundation Models, arXiv (2023). DOI: 10.48550/arxiv.2310.03024
News
COVID-19 viral fragments shown to target and kill specific immune cells
COVID-19 viral fragments shown to target and kill specific immune cells in UCLA-led study Clues about extreme cases and omicron’s effects come from a cross-disciplinary international research team New research shows that after the [...]
Smaller Than a Grain of Salt: Engineers Create the World’s Tiniest Wireless Brain Implant
A salt-grain-sized neural implant can record and transmit brain activity wirelessly for extended periods. Researchers at Cornell University, working with collaborators, have created an extremely small neural implant that can sit on a grain of [...]
Scientists Develop a New Way To See Inside the Human Body Using 3D Color Imaging
A newly developed imaging method blends ultrasound and photoacoustics to capture both tissue structure and blood-vessel function in 3D. By blending two powerful imaging methods, researchers from Caltech and USC have developed a new way to [...]
Brain waves could help paralyzed patients move again
People with spinal cord injuries often lose the ability to move their arms or legs. In many cases, the nerves in the limbs remain healthy, and the brain continues to function normally. The loss of [...]
Scientists Discover a New “Cleanup Hub” Inside the Human Brain
A newly identified lymphatic drainage pathway along the middle meningeal artery reveals how the human brain clears waste. How does the brain clear away waste? This task is handled by the brain’s lymphatic drainage [...]
New Drug Slashes Dangerous Blood Fats by Nearly 40% in First Human Trial
Scientists have found a way to fine-tune a central fat-control pathway in the liver, reducing harmful blood triglycerides while preserving beneficial cholesterol functions. When we eat, the body turns surplus calories into molecules called [...]
A Simple Brain Scan May Help Restore Movement After Paralysis
A brain cap and smart algorithms may one day help paralyzed patients turn thought into movement—no surgery required. People with spinal cord injuries often experience partial or complete loss of movement in their arms [...]
Plant Discovery Could Transform How Medicines Are Made
Scientists have uncovered an unexpected way plants make powerful chemicals, revealing hidden biological connections that could transform how medicines are discovered and produced. Plants produce protective chemicals called alkaloids as part of their natural [...]
Scientists Develop IV Therapy That Repairs the Brain After Stroke
New nanomaterial passes the blood-brain barrier to reduce damaging inflammation after the most common form of stroke. When someone experiences a stroke, doctors must quickly restore blood flow to the brain to prevent death. [...]
Analyzing Darwin’s specimens without opening 200-year-old jars
Scientists have successfully analyzed Charles Darwin's original specimens from his HMS Beagle voyage (1831 to 1836) to the Galapagos Islands. Remarkably, the specimens have been analyzed without opening their 200-year-old preservation jars. Examining 46 [...]
Scientists discover natural ‘brake’ that could stop harmful inflammation
Researchers at University College London (UCL) have uncovered a key mechanism that helps the body switch off inflammation—a breakthrough that could lead to new treatments for chronic diseases affecting millions worldwide. Inflammation is the [...]
A Forgotten Molecule Could Revive Failing Antifungal Drugs and Save Millions of Lives
Scientists have uncovered a way to make existing antifungal drugs work again against deadly, drug-resistant fungi. Fungal infections claim millions of lives worldwide each year, and current medical treatments are failing to keep pace. [...]
Scientists Trap Thyme’s Healing Power in Tiny Capsules
A new micro-encapsulation breakthrough could turn thyme’s powerful health benefits into safer, smarter nanodoses. Thyme extract is often praised for its wide range of health benefits, giving it a reputation as a natural medicinal [...]
Scientists Develop Spray-On Powder That Instantly Seals Life-Threatening Wounds
KAIST scientists have created a fast-acting, stable powder hemostat that stops bleeding in one second and could significantly improve survival in combat and emergency medicine. Severe blood loss remains the primary cause of death from [...]
Oceans Are Struggling To Absorb Carbon As Microplastics Flood Their Waters
New research points to an unexpected way plastic pollution may be influencing Earth’s climate system. A recent study suggests that microscopic plastic pollution is reducing the ocean’s capacity to take in carbon dioxide, a [...]
Molecular Manufacturing: The Future of Nanomedicine – New book from Frank Boehm
This book explores the revolutionary potential of atomically precise manufacturing technologies to transform global healthcare, as well as practically every other sector across society. This forward-thinking volume examines how envisaged Factory@Home systems might enable the cost-effective [...]
