Week 12 Part III · Architectures & Representation Learning
Autoencoders and latent representations; contrastive and self-supervised methods.
Curated, free, canonical references for this week: a course or lecture, a book chapter, a video, and an authoritative blog post or official tutorial. Each opens in a new tab.
Stanford lecture on pretext tasks, contrastive learning, and self-supervised representations.
The standard free chapter on autoencoders and their role in learning latent representations.
A focused walkthrough of SimCLR: augmentation views, the contrastive loss, and the projection head.
A deeply-cited survey of contrastive and self-supervised methods (SimCLR, MoCo, BYOL, SwAV).