Kernel Functions For Machine Learning

You must have heard the term ‘kernel’ floating around quite a few times. People from many different backgrounds use it in different contexts. The thing is that this term has been applied to different things in different domains. When we talk about operating systems, we talk about which kernel is being used. Kernel is also used extensively in parallel computing and in the GPU domain, where it is the function which is called repetitively on a computing grid. It has a few other meanings in different hardware related programming fields. But in this post, I will discuss kernels as applied to machine learning. Kernels are used in machine learning to transform the data so that the classification becomes easier. One common thing in all these different definitions of the term ‘kernel’ is that it is being used as a bridge between two things. In operating systems, it is the bridge between hardware and software. In GPU domain, it is the bridge between the geometric grid and the programmer. In machine learning, it is the bridge between linearity and non-linearity. I will discuss the underlying mathematical structure in this post. So readers beware, this is a technical deep-dive.   Continue reading

Support Vector Machines

In machine learning, we have supervised learning on one end and unsupervised learning on the other end. Support Vector Machines (SVMs) are supervised learning models used to analyze and classify data. We use machine learning algorithms to train the machines. Once we have a model, we can classify unknown data. Let’s say you have a set of data points and they belong one of the two possible classes. Now our task is to find the best possible way to put a boundary between the two sets of points. When a new point comes in, we can use this boundary to decide whether it belongs to class 1 or class 2. In real life, these data points can be a set of observations like images, text, characters, protein sequences etc. How can we achieve this in the most optimal way?   Continue reading