PHYS-467: Machine learning for physicists

About
Privacy
Disclaimer

Graph Chatbot

Lectures in this course (130)

Bayesian Estimation: Unsupervised Learning & MCMC

Explores Bayesian estimation for unsupervised learning and MCMC, using a Spin Glass Card game example.

Probabilistic Estimation in Spin Glass Card Game

Explores probabilistic estimation in the Spin Glass Card game, emphasizing room splitting based on a given parameter.

Gibbs Sampling: Simulated Annealing

Covers the concept of Gibbs sampling and its application in simulated annealing.

Expectation Maximization and Clustering

Covers the Expectation Maximization algorithm and clustering techniques, focusing on Gibbs Sampling and detailed balance.

Clustering: k-means

Explains k-means clustering, assigning data points to clusters based on proximity and minimizing squared distances within clusters.

Kernel Regression

Covers the concept of kernel regression and making data linearly separable by adding features and using local methods.

Kernel Methods and Regression

Covers kernel methods, kernel regression, RBF kernel, and SVM for classification.

Kernel Methods: Neural Networks

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

Linear and Ridge Regression

Covers linear and ridge regression, overfitting, hyperparameters, and test sets.

Multilayer Neural Networks: Deep Learning

Covers the fundamentals of multilayer neural networks and deep 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.

Transfer Learning with CNNs

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

Deep Learning: Overparameterization and Generalization

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

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.

Modern Architectures: Working and Solving Complex Tasks

Explores modern system internals and how they solve complex tasks.

Generative Neural Networks: Sampling and Training

Covers generative neural networks, focusing on sampling, training, and noise addition.

Probabilistic Linear Regression

Explores probabilistic linear regression, covering joint and conditional probability, ridge regression, and overfitting mitigation.

Probabilistic Models for Linear Regression

Covers the probabilistic model for linear regression and its applications in nuclear magnetic resonance and X-ray imaging.

LASSO Regression: Sparse Signal Induction

Explores LASSO regression for inducing sparsity in signals through gradient descent.

Page 6 of 7