Techniques & Methods
Transfer Learning
Transfer learning enables AI models to apply knowledge gained on large general datasets to specialized tasks with limited data. Instead of training from scratch, a pre-trained model is fine-tuned on task-specific data, dramatically reducing the data and compute required.
It underpins modern AI development: all major LLMs are pre-trained on broad data then fine-tuned for specific applications. Transfer learning made high-quality NLP accessible to organizations without massive compute resources.
Authority Links
Related Terms
Techniques & Methods
Fine-Tuning
Continuing the training of a pre-trained foundation model on a smaller, curated dataset to specialize its behavior, style, or domain expertise without losing its general capabilities.
Techniques & Methods
Pre-training
Initial phase where a model learns general representations from large datasets before task-specific fine-tuning.
Model Components
Foundational Model
Large versatile model trained on broad data that serves as a base for diverse downstream applications.
Techniques & Methods
Supervised Fine-Tuning
Refining a pre-trained model's performance on a specific task using labeled example data.