In this chapter, we look at autoencoders. This chapter is a theoretical one, covering the mathematics and the fundamental concepts of autoencoders. We discuss what they are, what their limitations are, the typical use cases, and then look at some examples. We start with a general introduction to autoencoders, and we discuss the role of the activation function in the output layer and the loss function. We then discuss what the reconstruction error is. Finally, we look at typical applications, such as dimensionality reduction, classification, denoising, and anomaly ...
9. Autoencoders
Get Applied Deep Learning with TensorFlow 2: Learn to Implement Advanced Deep Learning Techniques with Python 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.