# Conceptual

## A World of small things: Introduction to Nanotechnology

Nanotechnology deals with the science of building small, but why do we talk about such small things? Well, they ultimately constitute the world we live in and we can explore fascinating things with them, literally, it can shape the world around us. Properties of materials change due to quantum effects when they are made small, …

## Hacking the Bivariate Gaussian Distribution

In one of our earlier posts, we have seen how we can visually relate the parts of the one-dimensional Gaussian distribution equation. In this post, we will follow the same strategy to understand the terms that comes up with a Multivariable Gaussian distribution. We will focus on the Bivariate Gaussian distribution as distributions of higher-order …

## Visualizing MinMax Scaling

This article explains the minmax scaling operation using visual examples. Normalization of vectors, an array of values, signals is often used as a preprocessing step before many algorithms. For example, in machine learning, some types of algorithms are prone to different inherent scales of features. In such situations normalization is done to give the same …

## 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

A Markov Decision Process (MDP) is a mathematical framework used to model decision-making situations where the outcome of a decision depends on both the current state of the system and the actions taken by the decision maker. In an MDP, the decision maker is represented as an agent, and the system is represented as a …

## 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 …

## 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. …

## 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 …