Lecture 3 - Zero-shot, Few-shot and Unsupervised Learning
Teacher: Benjamin Devillers (ANITI)
Contents
- Zero-shot learning: learning without per-instance labels.
- Few-shot learning: learning with a few training examples.
- Unsupervised learning: learning without labels. Differences with zero-shot learning.
- Auto-encoders, contrastive learning
- Generative models: GANs, VAEs
Slides
Access the lecture slides here
Notebook
Access the collab notebook here