Back to basics — coding neural network using NumPy alone — Recently I was explaining the concept of the neural network to my mother; I couldn’t go beyond the usual trope of inputs, hidden layers, outputs etc. …

Lessons from client-facing Data Science and ML consulting — Computing and tech are the centres of the key domains, such as Data Science, Machine Learning, AI, AGI, Quantum systems etc, is a common narrative, when in fact, all of them have come to the forefront in our lives as they impact or potentially impact the way we think, live…

The lifecycle of Machine Learning and Data Science projects — In my experience, ML projects come in all shapes and sizes and vary greatly in their complexity. In the initial 2000/10s, the emphasis was on the model-centric approach which I always found a little bizarre as I heard umpteen times about the fancier models than the results(well, it was a…

The connection between turbulence and art — The Cypress tree, the sleepy village, the luminescent sky, and the rolling hills- that’s how we see Van Gogh’s The Starry Night. …

Step by step approach for reading technical papers — Ok, I won’t try to convince you why you need to read technical and research papers. Almost all the algorithms that you use in daily life came from the technical literature but are present ubiquitously in the form of tutorials or easier walkthroughs. …

Data exploration of attacks in Afghanistan — The Present The first time I read about Afghanistan was in a story named — Kabuliwalah, a story about a nomadic businessman from Kabul who sells dry fruits in India. He develops filial affection for a little five-year-old girl named Minnie, who reminds him of his own daughter back home. …

Building a simple intuition for Bayesian optimization for Machine Learning — I gifted you a sophisticated and hypothetical coffee machine and asked you to brew the best coffee for yourself by modulating the thousands of dials that are there on the machine. You are an intelligent fellow and quickly realise that it is an optimization problem. You have two options: Change…

Design principles for creating data-based graphics and visuals — This is a carte figurative. It was created by Charles Joseph Minard to show Napolean’s Russian campaign of 1812–13. Modern information scientists say that it is the best statistical graph ever produced in the history of mankind. Minard’s graph tells a rich, coherent story from multivariate data and depicts the…

The difference between a proficient and average data scientist is not what you think of! — I have interviewed many data scientists who are at the various stages of their careers and one question I ask all of them is how do they keep themselves abreast with the fast-paced changing world of AI and deep learning.