There is a fundamental difference between the way humans learn and the way machines learn. A clear advantage for humans is our ability to transfer knowledge between different domains. So far, we have only explored techniques that make our models learn tasks, such as image recognition. In this chapter, we will see how it's possible to generalize learning and use a model trained for another task to solve different problems. We will also explore a code example of transfer learning, in PyTorch.
Following are the topics that will be covered in this book:
- Transfer learning theory
- Implementing multi-task learning
- Feature extraction
- Implementation in PyTorch
