Lecture

Scientific Machine Learning: Introduction to Spin Glass Models

Related lectures (32)

Statistical Physics of Computation: Insights and Applications

Explores the application of statistical physics in computational problems, covering topics such as Bayesian inference, mean-field spin glass models, and compressed sensing.

Unsupervised Learning: Clustering

Explores unsupervised learning through clustering techniques, algorithms, applications, and challenges in various fields.

Decision Making Under Uncertainty

Explores decision-making under uncertainty, focusing on Kilian Schindler's posthumous PhD thesis on scalable stochastic optimization and scenario reduction.

Supervised Learning Overview

Covers CNNs, RNNs, SVMs, and supervised learning methods, emphasizing the importance of tuning regularization and making informed decisions in machine learning.

The Curie-Weiss Model: Overview and Applications

Covers the Curie-Weiss model, discussing its theoretical foundations and practical applications in physical systems.

K-means Algorithm

Covers the K-means algorithm for clustering data samples into k classes without labels, aiming to minimize the loss function.

Partition Functions and Models

Explores partition functions in spin systems, models like Ising and Potts, computational challenges, and the Lee-Yang Theorem.

Statistical Physics of Clusters

Explores the statistical physics of clusters, focusing on complexity and equilibrium behavior.

Clustering: Theory and Practice

Covers the theory and practice of clustering algorithms, including PCA, K-means, Fisher LDA, spectral clustering, and dimensionality reduction.

State Space Models: Expressivity of Transformers

Covers state space models and the expressivity of transformers in sequence copying tasks.

Dimensionality Reduction: PCA and LDA

Covers dimensionality reduction techniques like PCA and LDA, clustering methods, density estimation, and data representation.

Unsupervised Learning: Clustering & Dimensionality Reduction

Introduces unsupervised learning through clustering with K-means and dimensionality reduction using PCA, along with practical examples.

Ferromagnets and the Ising Model

Covers the Ising model, ferromagnetic materials, spins on a lattice, and spin correlations.

Clustering & Density Estimation

Covers clustering, PCA, LDA, K-means, GMM, KDE, and Mean Shift algorithms for density estimation and clustering.

Unsupervised Learning: Dimensionality Reduction and Clustering

Covers unsupervised learning, focusing on dimensionality reduction and clustering, explaining how it helps find patterns in data without labels.

Density of States and Bayesian Inference in Computational Mathematics

Explores computing density of states and Bayesian inference using importance sampling, showcasing lower variance and parallelizability of the proposed method.

Clustering & Density Estimation

Covers dimensionality reduction, PCA, clustering techniques, and density estimation methods.

Reinforcement Learning Concepts

Covers key concepts in reinforcement learning, neural networks, clustering, and unsupervised learning, emphasizing their applications and challenges.

Magnetic Ordering in Materials

Delves into magnetic ordering in materials, covering neglected spin interactions, Curie temperature, Neel temperature, and the Heisenberg Hamiltonian.

Bayesian Inference: Optimal Estimation

Explores optimal Bayesian inference, denoising, scalar estimation, and phase transitions.