contrastive-learning
2 free lessons tagged contrastive-learning across AI. Each one is a short sequence of focused steps with narration and a five-question quiz at the end — take them in any order, no signup required.
Contrastive Learning
The first family to make joint-embedding self-supervised learning work: pull together two views of the same image, push apart different images. This lesson covers the InfoNCE loss, SimCLR and its reliance on large batches, MoCo's momentum encoder and queue, why negatives block collapse, and the practical costs that motivated negative-free methods.
Why Predict Representations, Not Pixels
Self-supervised learning has three families: reconstruct the input, contrast augmented views, or predict in a learned embedding space. This lesson explains why the third, the joint-embedding predictive approach behind JEPA, sidesteps both wasted capacity on unpredictable pixels and hand-crafted augmentation biases.