Overview
Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This course examines latent variable energy-based models, focusing on free-energy formulations, temperature-dependent training, loss functionals, conditional models, learned manifolds, and decoder design. It also uses PyTorch notation and discusses selecting the latent size.
Syllabus
– Welcome to class
– Zero Temperature Limit ZTL free energy recap
– warmer Free energy
– Infinite Temperature Limit
– Free energy, example y = Y[23]
– Free energy, example y = Y[10]
– Free energy, example y = 0, 0
– Nomenclature and PyTorch
– Training!
– Loss functionals
– ZTL vs. varmer temperature training
– Conditional case
– Untrained model manifold
– Energy function Ex, y, z
– Trained model manifold
– Learning the Decoder
– Choosing the latent size
– And that was it
Taught by
Alfredo Canziani