Beginning Deep Learning with TensorFlow: Work with Keras, MNIST Data Sets, and Advanced Neural Networks

© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2022

L. Long, X. ZengBeginning Deep Learning with TensorFlowhttps://doi.org/10.1007/978-1-4842-7915-1_12

12. Autoencoder

Liangqu Long¹   and Xiangming Zeng²

(1)

Shenzhen, Guangdong, China

(2)

State College, PA, USA

 

Suppose machine learning is a cake, reinforcement learning is the cherry on the cake, supervised learning is the icing on the outside, and unsupervised learning is the cake itself.

—Yann LeCun

Earlier we introduced the neural network learning algorithm given the sample and its corresponding label. This type of algorithm actually learns the conditional probability P(y| x) given the sample x. With the booming social network today, it is relatively easy to ...