ConceptAI & ML
Meta-learning
Learning to adapt more quickly from past experience of solving other tasks.
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.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
5Each in their own terms, from the easiest level.
Sergey Levine
Ashish Vaswani, Lucas Beyer & William Fedus
Learning to predict over multiple data sets so that plugging in a new data set automatically gives predictions on a different data distribution.Richard S. Sutton
Learning to learn, emerging from repetitive experience with continual learning.Sara Beery
The process of learning a model that is good at learning other tasks quickly.Yoshua Bengio
Learning how to learn, enabling a system to acquire new tasks rapidly from very little data.
Lectures that assume it
1Connections
13The lectures that define it or assume it, and the concepts next to it.
Concepts6
Lectures7
- Self Attention and Non-parametric transformers (NPTs)
- The Alberta Plan for AI Research: Continual Reinforcement Learning
- From System 1 to System 2 Deep Learning
- Sequential Decision-Making: Policy Gradients vs. Value-Based Architectures
- Transfer Learning & Meta-Learning
- Transfer Learning: Data