A code-free guide to Artificial Intelligence

Image for post
Image for post
Photo by Lukas on Unsplash

So about a year ago, I read this fantastic article by Trask.

If you didn’t click the link, do it now.

Did you? Ok, good.

Now here’s the thing — The article requires you to know a little bit of python, which you probably do.

Image for post
Image for post
A Neural Network in 11 Lines of Code

On the off-chance that you’re interested in Neural Networks (if that phrase sounds utterly foreign to you, watch this YouTube playlist) and haven’t learned python yet, congratulations, you’re in the right spot.

But regardless of where you are in the vast landscape of deep learning, I think that once in a while, it’s nice to go back to the basics and revisit the fundamental mathematical ideas that brought us Siri, Alexa, and endless hours of Netflix binge-watching. …

Image for post
Image for post
Photo by Jens Johnsson on Unsplash

How do companies like Amazon and Netflix know precisely what you want? Whether it’s that new set of speakers that you’ve been eyeballing, or the next Black Mirror episode — their use of predictive algorithms has made the job of selling you stuff ridiculously efficient.

But as much as we’d all like a juicy conspiracy theory, no, they don’t employ psychics.

They use something far more magical — mathematics. Today, we’ll look at an approach called collaborative filtering.

What exactly is collaborative filtering?

As Jeremy Howard mentions in his awesome deep learning course at fast.ai, structured deep learning models don’t get much love these days.

Probably because you wouldn’t get to see stuff like…

To anyone, anywhere, anytime.

This is not an exaggeration.

The internet has provided us instant communication across the globe, yet very few students that I know have tapped into its potential to provide an expansive community of learners who are ready for their daily dose of knowledge.

Until now, teaching has been an art left to the masters — the ones who have attained such a high level of proficiency in their field that it is now their sacred responsibility to propagate this wisdom to the next generation

Teaching can be one of the most rewarding experiences that one can possibly ever have. The sleepless nights spent preparing quality material and re-re-revising material to ensure absolute perfection, the endless pondering on how to break down an idea into simpler and more intuitive ones, and the look on a student’s face when the puzzle pieces come into place are all moments that everyone must experience at least once in their lives. …

This article is based on the book “Reinforcement Learning: An Introduction” by Richard S. Sutton and Andrew G. Barto


Before we start, you might want to check out this excellent article by Thomas Simonini to get a good idea on what reinforcement learning is all about.

An interesting problem to solve with reinforcement learning is the multi arm bandit problem. Without any lengthy and boring descriptions, let’s cut to the actual problem statement:

An agent is given a choice of k different actions, each with a certain value associated. …

This is my public commitment to the #100DaysOfCode challenge, started by Alexander Kallaway. I’ve been hearing a lot about this challenge recently, and I thought I’d give it a try.I’m using this post both as a form of public commitment and a weekly log to track my progress.Here is my formal commitment on twitter:

And my fork of the 100-days-of-code repo on GitHub:

In this article (which will be updated on a weekly basis from today- 4th July 2018 till I complete the challenge), I’ll be sharing my experience, thoughts, goals, plans, accomplishments, courses and tutorials used, and progress from the challenge. …

Image for post
Image for post
Photo by Diana Măceşanu on Unsplash


From my experience as a time traveller, I can confidently say that autonomous driving is/was/will be all the craze. Mathematically, the hype around computer vision grows exponentially as a function of the index of plank time iterations. Just kidding.

Anyways, in this post, we’ll dive into some of the more recent developments in computer vision with deep learning, and eventually build up to a model called “Mask R-CNN”. This post should be fairly intuitive, but I expect you to know some of the more basic models for computer vision. If you think you’re ready, let’s begin.

Object detection vs. Semantic segmentation vs. Instance segmentation

In this post, I’m assuming that you are comfortable with basic deep learning tasks and models specific to computer vision, such as convolutional neural networks (CNN), image classification etc. If these terms sound like jargon to you, go ahead and read this post. …


Ajay Arasanipalai

Student at HLC International school. Member of the human race.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store