Part III - Methods for large scale machine learning

Summary

In the following two chapters we describe two general sets of tools for dealing with large scale data. First, in Chapter 8, we introduce advanced gradient methods which extend the standard gradient descent scheme first described in Chapter 2. These techniques help us to deal with very large datasets directly by making use of more efficient algorithms. In Chapter 9, on the other hand, we introduce general techniques for significantly reducing the size of datasets prior to performing regression or classification.