Data-Driven Latent Representations for Time-Dependent Problems - Lecture 3
Offered By: Centre International de Rencontres Mathématiques via YouTube
Course Description
Overview
Explore a conference talk on data-driven latent representations for time-dependent problems in this recording from the "CEMRACS: Scientific Machine Learning" thematic meeting. Delve into topics such as denoising, minimization, climate downscaling, superresolution, and optimal transport. Learn about the Gold Converter Flow, sampling techniques, and conditional probability. Discover how time conditioning and variability are addressed in this context. Gain insights into the main ideas and applications of these concepts in scientific machine learning. Access additional features like chapter markers, keywords, and enriched content through CIRM's Audiovisual Mathematics Library.
Syllabus
Intro
Denoiser
Minimize
Application
Main idea
Time and downscaling
Climate downscaling
Superresolution
Gold Converter Flow
Sampling
Conditional probability
Optimal transport
Variability
Availability
Methods
Questions
Time conditioning
Taught by
Centre International de Rencontres Mathématiques
Related Courses
Optimal Transport and PDE - Gradient Flows in the Wasserstein MetricSimons Institute via YouTube Crash Course on Optimal Transport
Simons Institute via YouTube Learning From Ranks, Learning to Rank - Jean-Philippe Vert, Google Brain
Alan Turing Institute via YouTube Optimal Transport for Machine Learning - Gabriel Peyre, Ecole Normale Superieure
Alan Turing Institute via YouTube Regularization for Optimal Transport and Dynamic Time Warping Distances - Marco Cuturi
Alan Turing Institute via YouTube