Transfer learning is the process of transferring the knowledge gained in one task in a specific domain to a related task in a similar domain. In the deep learning paradigm, transfer learning generally refers to the reuse of a pre-trained model as the starting point for another problem. The problems in computer vision and natural language processing require a lot of data and computational resources, to train meaningful deep learning models. Transfer learning has gained a lot of importance in the domains of vision and text, since it alleviates the need for a large amount of training data and training time. In this chapter, we will use transfer learning to solve a healthcare problem.
Some key topics related to transfer learning that we will touch upon in this chapter are as follows:
- Using transfer learning to detect diabetic retinopathy conditions in the human...
