# Sajil C. K.

I am an inquisitive person with interests falling at the intersection of mathematics, programming, and research. I like to understand concepts to the core by building things from scratch.

## Gaussian Distribution Explained Visually

Gaussian distribution appears in various parts of science and engineering. Apart from a distribution often appear in nature, it has got important properties such as its relation to Central Limit Theorem (CLT). The figure above shows one-dimensional Gaussian distributions of various mean and variance values. Libraries like NumPy provide functions that can return Gaussian distribution …

## Coding a Simple Markov Decision Process

This is a quick tutorial on how to implement a two-state Markov Decision Process (MDP). It has only two states: state 1 and state 2. Applications MDPs often appear in machine learning and reinforcement learning. At any stage, the agent can take any of the two actions. The actions are to stay or switch. The …

## Reinforcement Learning Resources

Following is a list (in progress) of resources on Reinforcement Learning and allied topics. Though not comprehensive, it includes University lectures, YouTube playlists, MOOCs, blogs, etc. Hope this would be useful to someone getting started in reinforcement learning. UC Berkely CS 285 at UC Berkeley Deep Reinforcement Learning (23) Deep RL Bootcamp (15) CS 294: …

## What does it mean to say orthogonal?

In this article, let us explore what is meant by the concept of orthogonality. Orthogonal or orthogonality is often introduced from a mathematical perspective. In general, most resources explains it in terms of linear algebra and vectors. One such example is when we learn about right-angled triangles the two sides are drawn as perpendicular or …

## Small parts of curves are nearly straight line

“Small parts of curves are nearly straight line“ I heard this first-time years back in one of MIT’s OpenCourseWare calculus classes. Little did I know it is going to be a life-long lesson to me at that time. This concept is going to be one of the first principles we will be dealing with in …

## Mathematics for Machine Learning Resources

Every day, computational fields like machine learning, artificial intelligence, neuroscience, cryptography, etc. are making great progress. Anyone pursuing a career in all such fields might be looking for a solid foundation. If we dig deeper, we often trace back to the Queen of Science- Mathematics. A solid foundation of the math concepts will be useful …

## An Intuitive Explanation of Naive Bayes Classifier

Introduction In this post, let’s take a look at the intuition behind Naive Bayes Classifier used in machine learning. Naive Bayes classifier is one of the basic algorithms often encountered in machine learning applications. If linear regression was based on concepts from linear algebra and calculus, naive Bayes classifier mostly backed up by probability theory. …

## A Curated List of Undergraduate Courses

A strong foundation flags off a voyage to knowledge and success. I am curating a list of free undergraduate courses. All of them are freely available on YouTube. This list particularly focuses on math-oriented courses. The reason for that is because most of the underlying concepts in various fields can be explained using mathematical principles. …

## Book summary: The Art Of Thinking Clearly by Rolf Dobelli

Hello, world, In this post, I summarize the book The Art Of Thinking Clearly by Rolf Dobelli. This book has some interesting observations about thinking clearly. I have listed out the main ideas in bold, its summary from respective chapters, along with my thoughts and view points. Introduction to Thinking Clearly Failure to think clearly …

## Nine key papers in Distributional Reinforcement Learning Literature

In this post, I am going to give a summary of nine key papers from the distributional reinforcement learning (DRL) area. Paper 001 : A Distributional Perspective on Reinforcement LearningÂ  This is the seminal paper in this area. The key idea ofÂ  the paper is the argument that the value distribution is important in reinforcement …