Completed
– Reconstruction energies
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Unsupervised Learning - Autoencoding the Targets
Automatically move to the next video in the Classroom when playback concludes
- 1 – 2021 edition disclaimer
- 2 – Unsupervised learning and generative models
- 3 – Input space interpolation
- 4 – Latent space interpolation
- 5 – Conditional generative networks
- 6 – Style transfer
- 7 – Super resolution
- 8 – Inpainting
- 9 – Caption to image Dall-e
- 10 – Definitions: x, y, z
- 11 – Recap: conditional latent variable EBM
- 12 – Recap: energy function
- 13 – Softmin training recap → autoencoder via amortised inference
- 14 – Reconstruction energies
- 15 – Loss functional
- 16 – Under and over complete hidden layer
- 17 – Denoising autoencoder
- 18 – Nearest neighbourhood denoising autoencoder
- 19 – Sparse autoencoder
- 20 – Final remarks
