Evaluating Kernel Learning

In machine learning, pattern finding is an area that is being explored to the hilt. There are many methods and algorithms that can drive this kind of work and analysis. However, in this chapter, we will try to focus on how kernels are making a significant difference to the whole machine learning outlook. The application of kernel learning doesn't have any boundaries: starting from a simple regression problem to a computer vision classification, it has made its presence felt everywhere. Support vector machine (SVM) is one of those algorithms that happens to make use of kernel learning.

In this chapter, we will be focusing on the following concepts:

• Concepts of vectors, linear separability, and hyperplanes
• SVM
• Kernel tricks
• Gaussian process
• Parameter optimization