Normalizing Flows

Related lectures (28)

Page 1 of 3

Introduces multivariate statistics, covering normal distribution properties and characteristic functions.

Covers the multivariate normal distribution, properties, and sampling methods.

Covers linear applications, matrices, transformations, and the principle of superposition.

Explores injective and surjective linear transformations, kernel, image, and matrix operations.

Introduces multivariate statistics, focusing on uncovering associations between components in data in vector form.

Covers linear transformations using matrices, focusing on linearity, image, and kernel.

Covers Gaussian random variables, affine transformations, and linear systems driven by Gaussian noise in multivariable control.

Covers elliptical distributions, including properties, applications, and risk management implications.

Explores Lorentz transformations, covariant tensors, rotational invariance, and linear transformations in vector spaces.

Explores isometries in Euclidean spaces, including translations, rotations, and linear symmetries, with a focus on matrices.