Latent Variable Energy Based Models - Inference

This lecture explains inference for latent-variable energy-based models, covering unconditional cases, model manifold generation, indexed energy functions, and free-energy computation across the output space.

Syllabus

– Affine transformation in 2 and 3D by @LeiosLabs James Schloss
– Thanks for sending me a Wacom graphic tablet
– *Inference* for LV EBM we're given a model
– Training samples: one to many mapping
– Let's simplify stuff: the unconditional case
– Untrained model manifold generation
– The Energy Function, tadaaa
– Indexing energy function by picking individual training samples
– The 23rd energy U shaped
– The 10th energy ~ shaped
– The Free Energy definition and the 10th example
– The 23rd free energy
– Computing the free energy for the entire space
– That was it :