Contrastive Learning is a machine learning technique where the model learns by comparing similar and dissimilar examples to understand what makes things alike or different. A model is trained to put similar items (like two photos of cats) closer together in its internal representation while move dissimilar items (like a photo of a cat and a photo of a toaster) farther apart.
Explore Similar Terms:
Self-Supervised Learning | Unsupervised Learning | Embeddings
Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.
Sign Up For Latest News

AI4All participant Anandita Mukherjee shares her experience in an immersive two-week AI learning experience.
AI4All participant Anandita Mukherjee shares her experience in an immersive two-week AI learning experience.
