Artificial intelligence is changing how complex problems are addressed in materials science, with applications ranging from computation and design to data analysis. This talk will provide a brief introduction to machine learning and will use a series of representative case studies to show how these methods can support both theoretical and experimental research.
The examples will include surrogate models that significantly accelerate numerical simulations, inverse-design strategies for nanophotonic structures, neural-network approaches to quantum many-body problems, and data-driven methods for denoising microscopy images and spectral datacubes.