Training models that learn how to learn — after training on many tasks, they can quickly adapt to new tasks with very little data.
Training models that learn how to learn — after training on many tasks, they can quickly adapt to new tasks with very little data. Also called 'learning to learn.' The goal is to build AI systems that are as sample-efficient as humans, who can learn a new concept from just one or two examples.
The ability of a model to learn a new task from just a handful of examples, often provided in the prompt itself.
Using knowledge learned from one task to improve performance on a different but related task.
A mathematical function applied to a neuron's output that introduces non-linearity into the network.
An optimization algorithm that combines the best parts of two other methods — AdaGrad and RMSProp.
Artificial General Intelligence.
The research field focused on making sure AI systems do what humans actually want them to do.
Browse our complete glossary or subscribe to our newsletter for the latest AI news and insights.