Machine Learning with TensorFlow, Second Edition

11 A peek into autoencoders

This chapter covers

• Getting to know neural networks
• Designing autoencoders
• Representing images by using an autoencoder

Have you ever heard a person humming a melody and identified the song? That might be easy for you, but I’m comically tone-deaf when it comes to music. Humming is an approximation of a song. An even better approximation could be singing. Include some instrumentals, and sometimes, a cover of a song sounds indistinguishable from the original.

Instead of songs, in this chapter you’ll approximate functions. Functions are a general notion of relations between inputs and outputs. In machine learning, you typically want to find the function that relates inputs to outputs. Finding the best possible function ...