TensorFlow Basics
Rahul Bhalley · Apress eBooks · 2021
This short practical chapter is designed to introduce some deep learning–specific features of Swift for TensorFlow. Section 4.1 introduces the concept of tensor data structure which is essentially what neural networks make prediction from. After reading this chapter, you will be able to load the datasets (Section 4.2), write your own neural networks (Section 4.3), and train your model and test its accuracy (Section 4.4). In addition to all of this, in Section 4.5, you will also learn how to implement your own new layer, activation function, loss function, and optimizer. This will help in prototyping your research code or implementing the advanced building blocks of deep learning algorithms. This chapter requires some understanding of machine learning. We recommend you to refresh your concepts by reading Chapter 1 .