Deep Generative Modeling

 The latest 2021 lectures from the MIT Introduction to Deep Learning class are trickling out into the known universe.  And we have a great one to watch today.  Ava Soleimary will school us on all things generative.  Well not all things, but it's pretty good overview.

    She covers VAE architecture, and i was struck by her description of how it works and LeCun's Energy Model unified field theory of generative models.  Its fascinating to compare the 2 descriptions.

    And regularization is all about centering the mean while regularizing the variance.  And when you think about it that way it seems a lot more straightforward than you might have thought at first.

    Then we get into the latent space, latent perturbation and disentanglement, GANs, a really great intuition description of how GANs are transforming one distribution into another distribution, StyleGan, CycleGAN, etc.


Popular posts from this blog

Simulating the Universe with Machine Learning

CycleGAN: a GAN architecture for learning unpaired image to image transformations

Pix2Pix: a GAN architecture for image to image transformation