AI engineering glossary · ML fundamentals
What is transfer learning?
Transfer learning: Reusing a model trained on one task or dataset as the starting point for a different but related task. It saves data, time and compute because the model already knows general patterns, and only needs adapting to the new problem.
Transfer learning: an example
A network trained on millions of general photos is fine-tuned on 800 photos of Indian crop diseases.
Related terms
More ML fundamentals terms
- True risk
- Underfitting
- Unsupervised learning
- Validation curve
- Validation set
- VC dimension
- Weak supervision
- Ablation study
Where you learn it
Transfer learning is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.