Lecture

Replica computation and machine learning

Related lectures (31)

Random Field Ising Model: Overview and Analysis

Provides an in-depth analysis of the Random Field Ising Model, covering model description, free entropy, and mean field algorithm.

Machine learning in atomistic simulations: from reaction pathways to phase diagrams

Explores machine learning applications in atomistic simulations, focusing on water modeling, neural network potentials, and structure recognition.

Statistical Physics of Learning

Offers insights into the statistical physics of learning, exploring the relationship between neural network structure and disordered systems.

Machine Learning in Molecular Dynamics

Explores machine learning in molecular dynamics simulations, addressing the curse of dimensionality, neural network representation, and force-field estimation.

Curie Weiss Model

Covers the Curie-Weiss model in Statistical Physics, including magnetization probability, free entropy, and the cavity method.

Statistical Physics in Machine Learning: Understanding Deep Learning

Explores the application of statistical physics in understanding deep learning with a focus on neural networks and machine learning challenges.

Applications of GAMP

Delves into applying the GAMP algorithm to simplify the lasso problem and analyze optimization challenges in neural networks.

Spike Wigner Model

Explores the Spike Wigner model, Bayesian denoising, state evolution, and spectral methods in matrix analysis.

Replica and Symmetry Breaking

Explores the Nobel Prize-winning discovery of replica and cavity methods in complex systems, focusing on the random energy model and the application of probability theory.

Neural Networks: Two Layers Neural Network

Covers the basics of neural networks, focusing on the development from two layers neural networks to deep neural networks.

Brain Intelligence: Continual Learning of Representational Models

Delves into the continual learning of representational models after deployment, highlighting the limitations of current artificial neural networks.

Neural Networks: Training and Optimization

Explores the training and optimization of neural networks, addressing challenges like non-convex loss functions and local minima.

Understanding Machine Learning: Exactly Solvable Models

Explores the statistical mechanics of learning, focusing on neural networks' mysteries and computational challenges.

Nonlinear Supervised Learning

Explores the inductive bias of different nonlinear supervised learning methods and the challenges of hyper-parameter tuning.

Financial Time Series Analysis

Covers stylized facts of asset returns, summary statistics, testing for normality, Q-Q plots, and efficient market hypothesis.

Machine Learning for Solving PDEs: Random Feature Method

Explores the Random Feature Method for solving PDEs using machine learning algorithms to approximate high-dimensional functions efficiently.

Understanding Machine Learning: Exactly Solvable Models

Explores machine learning through solvable models, covering sample complexity, neural networks, and computational gaps.

Deep Learning Fundamentals

Introduces deep learning fundamentals, covering data representations, neural networks, and convolutional neural networks.

Machine Learned Interatomic Potentials

Delves into machine learned interatomic potentials, showcasing their accuracy and cost-effectiveness in predicting chemical properties.

Machine Learning and Modern AI: SWOT Analysis

Covers a SWOT analysis of Machine Learning and Artificial Intelligence, exploring strengths, weaknesses, opportunities, and threats in the field.