Physics-Informed Neural Networks (PINNs): Neural network models that integrate governing physical laws as constraints during training, enabling efficient solutions to differential equations.

AI is helping scientists solve complex equations in minutes - accelerating discoveries in chemistry, climate, and medicine.

More information: Yingheng Tang et al, Optical neural engine for solving scientific partial differential equations, Nature Communications (2025). DOI: 10.1038/s41467-025-59847-3 ...

University of Utah engineers encode partial differential equations in light and feed them into newly designed optical neural engine, or ONE, to accelerate machine learning.

In 2020, the team solved this by using liquid neural networks with 19 nodes, so 19 neurons plus a small perception module could drive a car. A differential equation describes each node of that system.