Une renaissance scientifique dans le monde de l’intelligence artificielle

Le système a démontré sa coupure sur la troisième loi de Kepler sur le mouvement planétaire, la loi d’Einstein sur la dilatation relativiste du temps et l’équation d’absorption de gaz de Langmuir.

AI-Descartes, le nouveau scientifique de l’IA, a reproduit avec succès le travail lauréat du prix Nobel en utilisant le raisonnement logique et la régression symbolique pour trouver des équations exactes. Le système est efficace avec des données du monde réel et de petits ensembles de données, avec des objectifs futurs, notamment l’automatisation de la construction de théories de fond.

En 1918, le chimiste américain Irving Langmuir a publié un article qui étudiait le comportement des molécules de gaz adhérant à une surface solide. Guidé par les résultats d’expériences minutieuses, ainsi que par sa théorie selon laquelle les solides fournissent des sites d’emballage séparés pour les molécules de gaz, il a proposé une série d’équations décrivant la quantité de gaz qui collerait, compte tenu de la pression.

Aujourd’hui, près de cent ans plus tard, le « monde de l’intelligence artificielle » développé par des chercheurs d’IBM Research, de Samsung AI et de l’Université du Maryland, comté de Baltimore (UMBC) a reproduit une partie essentielle des travaux de Langmuir, lauréat du prix Nobel. Le système – une intelligence artificielle (IA) agissant comme un scientifique – a redécouvert la troisième loi du mouvement planétaire de Kepler, qui peut calculer le temps qu’il faut à un objet spatial pour orbiter autour d’un autre compte tenu de la distance qui les sépare, et a produit une bonne approximation du temps relatif d’Einstein – la loi d’échelle, qui montre que le temps Il ralentit pour les objets en mouvement rapide.

La recherche a été soutenue par la Defense Advanced Research Projects Agency (DARPA).[{ » attribute= » »>DARPA). A paper describing the results will be published today (April 12) in the journal Nature Communications.

A machine-learning tool that reasons

The new AI scientist—dubbed “AI-Descartes” by the researchers—joins the likes of AI Feynman and other recently developed computing tools that aim to speed up scientific discovery. At the core of these systems is a concept called symbolic regression, which finds equations to fit data. Given basic operators, such as addition, multiplication, and division, the systems can generate hundreds to millions of candidate equations, searching for the ones that most accurately describe the relationships in the data.

AI-Descartes offers a few advantages over other systems, but its most distinctive feature is its ability to logically reason, says Cristina Cornelio, a research scientist at Samsung AI in Cambridge, England who is first author on the paper. If there are multiple candidate equations that fit the data well, the system identifies which equations fit best with background scientific theory. The ability to reason also distinguishes the system from “generative AI” programs such as ChatGPT, whose large language model has limited logical skills and sometimes messes up basic math.

“In our work, we are merging a first-principles approach, which has been used by scientists for centuries to derive new formulas from existing background theories, with a data-driven approach that is more common in the machine learning era,” Cornelio says. “This combination allows us to take advantage of both approaches and create more accurate and meaningful models for a wide range of applications.”

The name AI-Descartes is a nod to 17^th-century mathematician and philosopher René Descartes, who argued that the natural world could be described by a few fundamental physical laws and that logical deduction played a key role in scientific discovery.

Suited for real-world data

The system works particularly well on noisy, real-world data, which can trip up traditional symbolic regression programs that might overlook the real signal in an effort to find formulas that capture every errant zig and zag of the data. It also handles small data sets well, even finding reliable equations when fed as few as ten data points.

One factor that might slow down the adoption of a tool like AI-Descartes for frontier science is the need to identify and code associated background theory for open scientific questions. The team is working to create new datasets that contain both real measurement data and an associated background theory to refine their system and test it on new terrain.

They would also like to eventually train computers to read scientific papers and construct the background theory themselves.

“In this work, we needed human experts to write down, in formal, computer-readable terms, what the axioms of the background theory are, and if the human missed any or got any of those wrong, the system won’t work,” says co-author Tyler Josephson, assistant professor of Chemical, Biochemical and Environmental Engineering at UMBC. “In the future,” he says, “we’d like to automate this part of the work as well, so we can explore many more areas of science and engineering.” 

This goal motivates Josephson’s research on AI tools to advance chemical engineering. 

Ultimately, the team hopes their AI-Descartes, like the real person, may inspire a productive new approach to science. “One of the most exciting aspects of our work is the potential to make significant advances in scientific research,” Cornelio says.

Reference: “Combining Data and Theory for Derivable Scientific Discovery with AI-Descartes” 12 April 2023, Nature Communications.
DOI: 10.1038/s41467-023-37236-y

Funding: Defense Advanced Research Projects Agency