Artificial Intelligence
313 views
In-Context Learning
Quick Definition
LLMs learning new tasks from prompt examples without weight updates
Full Definition
The ability of LLMs to learn new tasks from examples provided in the prompt without updating model weights.
Examples
few-shot classification, task adaptation
Related Terms
few-shot-learning
large-language-model
More Artificial Intelligence Terms
Reinforcement Learning
Learning through trial and error with reward feedback
Style Transfer
Applying artistic style of one image to another using neural networks
Anomaly Detection
Identifying unusual patterns that deviate from expected behavior
Federated Learning
Distributed ML training without sharing raw data
Few-Shot Learning
Learning to perform tasks from a small number of examples
Generative AI
AI systems that create new content