PHYS-467: Machine learning for physicists

About
Privacy
Disclaimer

Graph Chatbot

Lectures in this course (106)

Unsupervised Learning: Principal Component Analysis

Covers unsupervised learning with a focus on Principal Component Analysis and the Singular Value Decomposition.

Kernel Methods: Neural Networks

Covers the fundamentals of neural networks, focusing on RBF kernels and SVM.

Belief Propagation in Stochastic Block Models

Covers the application of Belief Propagation in Stochastic Block Models, focusing on simplifying the process and solving it step by step.

Bayesian Inference: Posterior Computation

Covers the computation of posterior distributions in Bayesian inference.

Unsupervised Learning: Movie Recommendation

Covers unsupervised learning for movie recommendation using singular value decomposition.

Multilayer Neural Networks: Deep Learning

Covers the fundamentals of multilayer neural networks and deep learning.

Optimal Detection in Spinodal Systems

Explores optimal detection in spinodal systems, discussing stability analysis and phase transitions.

Gradient Descent: MNIST Dataset and Logistic Loss

Focuses on implementing gradient descent with the MNIST dataset and logistic loss in machine learning.

Neural Networks: Multilayer Learning

Covers the fundamentals of multilayer neural networks and deep learning, including back-propagation and network architectures like LeNet, AlexNet, and VGG-16.

Dense Graphs: From Theory to Applications

Explores the transition from sparse to dense graphs and their real-world applications.

Transfer Learning with CNNs

Explores transfer learning with CNNs, fine-tuning, and network depth impact.

Gradient Descent: Early Stopping and Stochastic Gradient Descent

Explains gradient descent with early stopping and stochastic gradient descent to optimize model training and prevent overfitting.

Spin Glasses and Bayesian Estimation

Covers the concepts of spin glasses and Bayesian estimation, focusing on observing and inferring information from a system closely.

Spin glass models

Covers the Spin Glass Game, belief propagation, and message passing algorithms.

Deep Learning: Overparameterization and Generalization

Explores overparameterization, generalization, overfitting, underfitting, and implicit regularization in deep learning models.

Markov Chain Monte Carlo

Explains the Markov Chain Monte Carlo method and the Metropolis-Hastings algorithm for sampling.

Graph Coloring: Random vs Symmetrical

Compares random and symmetrical graph coloring in terms of cluster colorability and equilibrium.

Generative Models: Boltzmann Machine

Covers generative models, focusing on Boltzmann machines and constrained maximization using Lagrange multipliers.

Generative Models: Self-Attention and Transformers

Covers generative models with a focus on self-attention and transformers, discussing sampling methods and empirical means.

Principal Component Analysis: Eigenfaces

Covers the application of Principal Component Analysis in facial recognition using a famous faces dataset.

Page 4 of 6