5 YouTube Recommendations

It's been a while since my last blogpost here so I wanted to hop on here to share some updates. Lately I have been exploring video form of content creation because it allows me to connect better with you all. If you are following this blog, chances are that you will enjoy and benefit from...

BERT Explained: A Complete Guide with Theory and Tutorial

Unless you have been out of touch with the Deep Learning world, chances are that you have heard about BERT —  it has been the talk of the town for the last one year. At the end of 2018 researchers at Google AI Language open-sourced a new technique for Natural Language Processing (NLP) called BERT...

12 Key Lessons from ML researchers and practitioners

Machine learning algorithms come with the promise of being able to figure out how to perform important tasks by learning from data, i.e., generalizing from examples without being explicitly told what to do. This means that the higher the amount of data, the more ambtious problems can be tackled by these algorithms. However, developing successful machine...

Deep Learning Series, P3: Understanding Recurrent Neural Networks

1. Why RNNs?Your smartphone predicting your next word when you are typing, Alexa understanding what you are saying or tasks like making stock market predictions, understanding movie plots, composing music, language translation and human learning: can you tell what is the common theme in this list? These are examples where sequence of information is crucial.For...

Deep Learning Series, P1: Basics of Neural Networks and Understanding Gradient Descent

This post consists of the following two sections: Section 1: Basics of Neural Networks Section 2: Understanding Backward Propagation and Gradient Descent Section 1 Introduction For decades researchers have been trying to deconstruct the inner workings of our incredible and fascinating brains, hoping to learn to infuse a brain-like intelligence into machines. For example, when...

How great products are made: Rules of Machine Learning by Google, a Summary

Google recently published some nuggets of ML wisdom, i.e., their best practices in ML Engineering. I believe that everyone should know about such best practices, so let's look at them. Please read the following statement a couple of times before moving on: Do machine learning like the great engineer you are, not like the great...

AI, Drones and Game Theory For Smart Wildlife Conservation

Background As the human population keeps booming, our actions are pushing life on our shared planet towards mass extinction. Human activity is causing extinctions at the rate of centuries versus the millions of years that take for natural extinctions. Poaching is playing a huge role in this human lead devastation and the numbers for some species...

Time Series Forecasting, the easy way! Let’s analyze Microsoft’s stocks

Introduction Time series forecasting and understanding time based patterns have many important applications. However, it is a territory often left unexplored, especially by ML practitioners, because of its relative complexity. To help people with domain knowledge, but without much expertise in creating statistical forecasting model, Facebook decided to come to rescue. And we will see...

Click-Through Rate (CTR) Prediction using Decision Trees

1. Introduction In this tutorial, we will try to predict click-through rate of ads with the Decision Tree algorithm we learnt in the last post. Before continuing, I would recommend you to first read that post for a theoretical understanding of Decision Trees. What does Click-Through Rate Prediction mean? Let's assume that you are designing...

Understanding Decision Trees

Tree based algorithms are among the most common and best supervised Machine Learning algorithms. Decision Trees follow a human-like decision making approach by breaking the decision problem into many smaller decisions.  As opposed to black-box models like SVM and Neural Networks, Decision Trees can be represented visually and are easy to interpret. How is decision...