ConceptAI & ML
Self-supervised learning
A learning paradigm where systems learn from unlabelled data by predicting missing parts of the input.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Supervised learning4Autoencoder1Empirical risk minimization1Encoders and decoders1Generative model1Machine learning1Machine learning basics1Neural networks1
Opens up
Concepts that name this one as a prerequisite.
Lecturers
4Each in their own terms, from the easiest level.
Phillip Isola
Self-supervised learning uses supervised learning machinery to predict raw data or parts of data instead of human-annotated labels.Steven Feng
A training approach where models learn by corrupting raw data and training to reconstruct the original uncorrupted data to learn general representations.Yann LeCun
Holger Lyre
Learning models of unlabeled data to extract hidden causes and latent variables in order to sample or make inferences about unseen data.
Lectures that assume it
5Connections
19The lectures that define it or assume it, and the concepts next to it.
Concepts9
- Supervised learning
- Autoencoder
- Empirical risk minimization
- Generative model
- Contrastive pre-training
- Denoising auto-encoder
Show 3 moreShow fewer
Lectures10
- Understanding AI: Semantic Grounding in Large Language Models
- Objective-Driven AI: World Models that Learn, Remember, Reason, and Plan
- The Deep Learning Revolution: The Sequel (Turing Award Lecture)
- Representation Learning: Reconstruction-Based
- Overview of Transformers (Stanford CS25: Transformers United V6)
- Self Attention and Non-parametric transformers (NPTs)