Explores equivariant structural representations in atomistic machine learning, emphasizing the importance of representing target properties in the spherical basis.
Covers Multi-Layer Perceptrons (MLP) and their application from classification to regression, including the Universal Approximation Theorem and challenges with gradients.
Explores graphical model learning with M-estimators, Gaussian process regression, Google PageRank modeling, density estimation, and generalized linear models.
Introduces the fundamentals of regression in machine learning, covering course logistics, key concepts, and the importance of loss functions in model evaluation.
