Chapter 09: Auto-Encoders
This chapter first defines the untouched-test-set principle and proceeds to explain the concepts of train-validation-test split and nested resampling.
-
Chapter 09.01: Unsupervised Learning
We explain unsupervised learning tasks and unsupervised representation learning.
-
Chapter 09.02: Manifold Learning
In this section, we explain the manifold hypothesis and manifold learning with AEs.
-
Chapter 09.03: Auto-Encoders
In this section, we will explain task and structure of Auto-Encoder.
-
Chapter 09.03: Regularized Autoencoders
In this section, we explain overcomplete AEs, sparse AEs, denoising AEs and contractive AEs.
-
Chapter 09.05: Specific Autoencoders and Applications
For the image domain, using convolutions is advantageous. Can we also make use of them in AEs? In this section, we answer this question and overview some applications.