In this chapter, you learned three different types of autoencoders: basic, Additive Gaussian Noise, and Sparse. We understood the use cases where they can be useful. We ran them against the MNIST dataset and also compared the cost of the three autoencoders. We also plotted the weights as well as the approximate output.
Summary
Get Neural Network Programming with 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.
