Machine learning for inverse design in physics, tutorial by Timo Gahlmann, AMOLF

This talk introduces how neural networks can be used as design tools in physics. After a brief overview of the basic concepts, viewers learn how neural networks are structured and trained, following small, live-executed code examples that show how they learn from data in practice. The talk then links these ideas to inverse design in nanophotonics, demonstrating how neural networks can be used to automatically propose nanostructures with desired optical properties.