ConceptAI & ML
Langevin dynamics
A stochastic process combining gradient updates with added Gaussian noise to model the trajectory of weights in noisy optimization.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
3Each in their own terms, from the easiest level.
Stefano Ermon
An MCMC algorithm that samples from a distribution by following the gradient of the log-density while adding Gaussian noise to explore the space.Hugo Touchette
A stochastic differential equation describing the motion of a particle subject to deterministic forces like drag and spring forces, alongside random noise.
Lectures that assume it
1Connections
9The lectures that define it or assume it, and the concepts next to it.