Autoencoders
In the previous chapters (in particular, Chapter 3, Introduction to Semi-Supervised Learning and Chapter 4, Advanced Semi-Supervised Classification on semi-supervised learning), we discussed how real datasets are very often high-dimensional representations of samples that lie on low-dimensional manifolds (this is one of the semi-supervised pattern's assumptions, but it's generally true).
As the complexity of a model is proportional to the dimensionality of the input data, many techniques have been analyzed and optimized in order to reduce the actual number of valid components. For example, PCA selects features according to their relative explained variance, while ICA and generic dictionary learning techniques look for basic atoms that can be combined to rebuild the original samples. In this chapter, we're going to analyze a family of models based on a slightly different approach, but whose capabilities are dramatically increased by the...