AI Glossary Term

What is Continual Learning?

Definition

Training approaches that let a model keep learning from new data without forgetting prior knowledge.

Related terms

Stored key and value tensors from previous tokens that let transformers generate new tokens without recomputing past attention.

How well a model performs on new, unseen data outside the training set.

Knowledge Cutoff

The latest point in time reflected in a model's training data.

Unsupervised Learning

Learning patterns from unlabeled data without explicit target outputs.

Zero-Shot Learning

Solving tasks without task-specific examples by relying on prior general knowledge.

Data Augmentation

Techniques that create modified training examples to improve model generalization.

Learn more in our free guides

Deep Learning Reinforcement Learning Machine Learning Basics Supervised Learning

Browse the full AI Glossary Explore all free AI guides