Few-Shot Learning
The ability of AI models to learn new tasks with only a small number of training examples.
Detailed Definition
Few-shot learning is an important capability in machine learning where AI models can learn to perform new tasks or recognize new categories after being exposed to only a few (typically 1-10) training examples. This contrasts with traditional supervised learning that requires large amounts of labeled data. Large language models often demonstrate strong few-shot learning capabilities, enabling them to quickly adapt to new scenarios. This ability is achieved through pre-training on diverse datasets that help models learn general patterns and representations that can transfer to new tasks. Few-shot learning is particularly valuable in scenarios where labeled data is scarce or expensive to obtain, such as specialized domains or rare conditions.
Learning MethodsMore in this Category
Fine-tuning
A post-training technique to specialize a trained model on specific data for a particular task.
Post-training
Additional steps taken after a model's initial training is complete to make it more useful.
RLHF (reinforcement learning from human feedback)
A post-training technique to align AI models with human preferences using feedback.
Training/Pre-training
The process by which an AI model learns by analyzing massive amounts of data.
Supervised learning
A type of machine learning where a model is trained on labeled data with correct answers provided.
Unsupervised learning
A type of machine learning where a model is given unlabeled data to find patterns on its own.