Unsupervised Learning - Autoencoding the Targets

This course explains unsupervised learning and generative modeling through autoencoders. It covers reconstruction objectives, hidden-layer capacity, denoising and sparse autoencoders, and applications including interpolation, inpainting, and super-resolution.

Syllabus

– 2021 edition disclaimer
– Unsupervised learning and generative models
– Input space interpolation
– Latent space interpolation
– Conditional generative networks
– Style transfer
– Super resolution
– Inpainting
– Caption to image Dall-e
– Definitions: x, y, z
– Recap: conditional latent variable EBM
– Recap: energy function
– Softmin training recap → autoencoder via amortised inference
– Reconstruction energies
– Loss functional
– Under and over complete hidden layer
– Denoising autoencoder
– Nearest neighbourhood denoising autoencoder
– Sparse autoencoder
– Final remarks