Quantum Machine Learning: Theory and Applications

This lecture, co-designed by the instructor and their postdoc, delves into the realm of quantum machine learning, exploring the interplay between machine learning theory and quantum physics. The lecture covers the journey from data to information, knowledge, and wisdom, emphasizing the importance of both inductive and deductive reasoning. Various representations of molecules, such as Coulomb Matrix and Spectrum of Lennard-Jones or Taylor, are discussed, along with the use of kernel regression to address non-linearity. The lecture also touches upon the challenges of injectivity in representations and the significance of covariant kernels in incorporating physics into machine learning models.