This part of the book describes the more ambitious and advanced approaches

to deep learning, currently pursued by the research community.

In the previous parts of the book, we have shown how to solve supervised

learning problems—how to learn to map one vector to another, given enough

examples of the mapping.

Not all problems we might want to solve fall into this category. We may wish to

generate new examples, or determine how likely some point is, or handle missing

values and take advantage of a large set of unlabeled examples or examples from

related tasks. Many deep learning algorithms have been designed to tackle such

unsupervised learning problems, but none have truly solved the problem in the

same way that deep learning has largely solved the supervised learning problem

for a wide variety of tasks. In this part of the book, we describe the existing

approaches to unsupervised learning and some of the popular thought about how

we can make progress in this ﬁeld.

Another shortcoming of the current state of the art for industrial applications

is that our learning algorithms require large amounts of supervised data to achieve

good accuracy. In this part of the book, we discuss some of the speculative

approaches to reducing the amount of labeled data necessary for existing models

to work well.

This section is the most important for a researcher—someone who wants to

understand the breadth of perspectives that have been brought to the ﬁeld of

deep learning, and push the ﬁeld forward towards true artiﬁcial intelligence.

371