training

Catastrophic Forgetting

The tendency of neural networks to completely lose previously learned information when trained on new data. Catastrophic forgetting is a major challenge in continual learning, where models need to acquire new knowledge without losing old skills.

In practice

A model fine-tuned on medical text might forget how to write poetry if catastrophic forgetting is not addressed.

Fine-tuning
The process of further training a pre-trained model on a specific dataset to specialize it for a particular task or domain. Fine-tuning adjusts the model's weights using task-specific data, typically requiring far less data and compute than training from scratch.
Transfer Learning
A technique where knowledge gained from training on one task is applied to a different but related task. Transfer learning enables models to achieve strong performance on new tasks with limited data by leveraging patterns learned from large-scale pre-training.
Overfitting
When a model learns the training data too well, including its noise and outliers, resulting in poor performance on new, unseen data. Overfitting occurs when the model memorizes specific examples rather than learning generalizable patterns.

Briefings

Catastrophic Forgetting

Further reading