Data-Driven Latent Representations for Time-Dependent Problems - Lecture 3

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.

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