Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Course

PHYS-467: Machine learning for physicists

Lectures in this course (130)

Diffusion Models

Explores diffusion models, focusing on generating samples from a distribution and the importance of denoising in the process.

Generalized Linear Model: Optimization and Approximation

Discusses the unified formulation of the generalized linear model and the optimization of loss functions.

Introduction to Neural Networks

Introduces neural networks, focusing on multilayer perceptrons and training with stochastic gradient descent.

Committee Machine: Statistical Physics Approach

Explores hidden variables, graphical models, and computational gaps in neural network learning.

Graphical Models: Joint Probability Distribution

Covers the concept of graphical models and joint probability distributions.

Linear Regression: Theory and Applications

Covers the theory and practical applications of linear regression.

Probability Distribution and Entropy

Explains probability distribution, entropy, and Gibbs free entropy, along with the Weiss model.

Linear Regression: Statistical Inference Perspective

Explores linear regression from a statistical inference perspective, covering probabilistic models, ground truth, labels, and maximum likelihood estimators.

Linear Regression: Statistical Inference and Regularization

Covers the probabilistic model for linear regression and the importance of regularization techniques.

Variational Methods in Statistical Physics

Explores variational methods in statistical physics and the Bethe Parisi Mézard approach.

Random Field Ising Model

Covers the Random Field Ising Model, discussing the concept of disorder and the process of finding the ground state.

Linear Classification: Variants and Stochastic Gradient Descent

Explores the variants of gradient descent, with a focus on stochastic gradient descent and linear classification.

Self-Organization in Complex Systems

Discusses self-organization in complex systems and emergent properties.

Logistic Regression

Covers logistic regression for linear classification and unsupervised dimensionality reduction techniques.

Belief Propagation: Key Methods and Analysis

Covers Belief Propagation, a key method for both analysis and algorithm.

Bethe Free Entropy

Covers the computation of Bethe free entropy and the interpretation of messages between variables and factors.

Machine Learning: Basics and Applications

Covers the basics of machine learning, including supervised and unsupervised learning, regression, classification, and clustering.

Linear Regression

Covers linear regression for estimating train speed using least squares and regularization.

Singular Value Decomposition

Explores Singular Value Decomposition and its role in unsupervised learning and dimensionality reduction, emphasizing its properties and applications.

Principal Components Analysis

Covers Principal Components Analysis, a technique for dimensionality reduction and gene type analysis.