Appendix A
Linear Regression and Linear Classifiers
This appendix logically follows Chapter 3, “Sigmoid Neurons and Backpropagation.”
As described in the preface, the approach we are taking in this book is to take a fast track to exciting parts of deep learning (DL). As such, we decided to not start the book with a number of traditional machine learning (ML) topics. Inspired by Nielsen (2015), we spent the three first chapters on binary classification problems using perceptrons and multilevel networks. Binary classification involves determining whether the inputs should result in an output belonging to one out of two classes. A more common way to introduce ML is to start with a regression problem, where we predict a real number instead of a ...
Get Learning Deep Learning: Theory and Practice of Neural Networks, Computer Vision, NLP, and Transformers using TensorFlow now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
