From Latent Variable Energy-Based Models to Target Prop to Autoencoder
This tutorial covers LV-EBM to target prop to (vanilla, denoising, contractive, variational) autoencoder and is a part of the Advanced Energy-Based Models module of the the Deep Learning Course at NYU's Center for Data Science. Prerequisites for this course include: Energy-Based Models I, Energy-Based Models II, Energy-Based Models III, Energy-Based Models IV, and an Introduction to Data Science or a Graduate Level Machine Learning course.
Chapters:
00:00 – 2021 edition disclaimer
00:49 – Conditional and unconditional LV EBM
02:08 – Variables' name: x, y, z, h, ỹ
03:34 – LV EBM training recap, warm case
10:54 – LV EBM training recap, zero-temperature limit
11:30 – Today's plan: the missing step
12:08 – Target prop(agation)
19:01 – From target prop to autoencoder
20:54 – Reconstruction costs
21:06 – Loss functional
21:22 – Under and over complete hidden layer
24:40 – Denoising autoencoder
32:00 – Contractive autoencoder
37:50 – Autoencoders recap
38:38 – From autoencoder to variational autoencoder
45:17 – Comparison between variational autoencoder and denoising autoencoder
45:54 – How a variational autoencoder actually works
48:29 – The bubble-of-bubble variational autoencoder interpretation
1:00:08 – And that was it :)