AI-driven scientific discovery

Can Neural Networks become scientists? Imagine a future where machines, equipped with the ability to autonomously extract governing equations from empirical data, can catalyze breakthroughs in fields like climate science, quantum mechanics, and drug discovery. In this project you will make a tiny step in this direction by training neural networks to discover equations governing natural phenomena, such as waves, weather, diffusion and others from observational data. During the course of this work you will leverage so called Physics-Informed Neural Networks and Genetic Algorithms to not only predict outcomes but also deduce the underlying physical laws governing those systems.

Join us in pushing the boundaries of artificial intelligence and empower neural networks to become the scientists of the future.

Supervisor: Andrzej Dulny