Dive into Deep Learning
Table Of Contents
Dive into Deep Learning
Table Of Contents

3. Linear Neural Networks

This chapter introduces the basics of deep learning. This includes network architectures, data, loss functions, optimization, and capacity control. In order to make things easier to grasp, we begin with very simple concepts, such as linear functions, linear regression, and stochastic gradient descent. This forms the basis for slightly more complex techniques such as softmax regression (introduced here) and multilayer perceptrons, (introduced in the next chapter).