Thoughts on data science, statistics and machine learning.
Book Review: To a God Unknown - John Steinbeck
In Journal of a Novel: The East of Eden Letters, Steinbeck wrote that reading books is like driving a wedge in your life. The larger the wedge, the harder it is for parts to come together once the wedge is removed. The longer the book, the harder it is to close the mental gap around it. Steinbeck wrote this for East of Eden - his magnum opus. Surprisingly, this happens even with Steinbeck’s much shorter books.
Book Review: Treasure Island - R L Stevenson
There are stories you know well but you never really read well. Captain Flint (the man and the parrot), Jim Hawkins, Long John Silver and Billy Bones, the Old Sea Dog are immortal characters, without a touch of age upon them or their story. Treasure Island was perhaps the first classic I actually skimmed through many times in my childhood. I didn’t read it in earnest until now, and I did that because the final season of Black Sails is about to end.
Rabies, Laziness & Privilege
It was the night of the recent 5-state assembly elections. One of my company’s clients is a major news channel, and I was at the studio late into the night, until the election commission announced that they had cancelled their press conference which was supposed to make an announcement about the final vote counts in Madhya Pradesh. A colleague offered to drop me home, and I got off at the gate of my colony, not wanting to subject my colleague to navigating the labyrinth that is any gated colony in South Delhi.
Weighted Loss Functions for Instance Segmentation
This post is a follow up to my talk, Practical Image Classification & Object Detection at PyData Delhi 2018. You can watch the talk here: and see the slides here. I spoke at length about the different kinds of problems in computer vision and how they are interpreted in deep learning architectures. I spent a fair bit of time on instance and semantic segmentation (for an introduction to these problems, watch Justin Johnson’s lecture from the Stanford CS231 course here).
Book Review: In Dubious Battle - John Steinbeck
I have a pretty good Steinbeck collection, but this wasn’t a book I was going to read anytime soon. But I recently came across the movie adaptation and decided that other Steinbeck titles could wait. James Franco and John Steinbeck is a very attractive combination. First of all, this book is not about communism. The eponymous battle is not a battle of the classes. It’s more of a battle men fight with themselves.
How Not to Ask Questions After a Talk
Dedicated to the memory of Mrutyunjay Mishra (M2). He was a torrent of ideas. He encouraged me to write this post because as much as he talked endlessly without pausing to breathe, he hated wasteful discourse. New Delhi, January 2024 PyCon India 2017 ended last weekend in Delhi. The conference escaped the infamous winter smog-storm by a whisker. In the last few years, PyCon India has grown to become the largest PyCon outside of North America, with over a thousand participants attending from all over the country.
Book Review: The View from the Cheap Seats - Neil Gaiman
I can’t think of a single fantasy character that would be Neil Gaiman. I’m tempted to think that he’s like Santa Claus, but he’s not the sort who’d care if someone was being naughty. He’s not Dumbledore or Gandalf either - he’d rather be your friend than your mentor. He’s not even the Dream of the Endless, since he’s not aware of how powerful he is. Reading Gaiman’s nonfiction is like meditation that clears and even expands your mind.
Playing With the Konmari Method
I heard about the bestseller The Life-Changing Magic of Tidying Up at a SciPy talk about deculttering your data science project. The speakers admitted they hadn’t read it - they were simply trying to point out that tidying up your space and tidying up your software project are both similar. I’ve been married and living with my wife for about a year now. After we moved into “our own home” last year, we have both undergone major role reversals when it comes to tidying up.
On the Linearity of Bayesian Classifiers
In his book, Neural Networks - A Comprehensive Foundation, Simon Haykin has an entire section (3.10) dedicated to how perceptrons and Bayesian classifiers are closely related when operating in a Gaussian environment. However, it is not until the end of the section that Haykin mentions that the relation is only limited to linearity. What is interesting about this is that a Perceptron can produce the same classification “model” as a Bayesian classifier, provided that the underlying data is drawn from a Gaussian distribution.
A Geometric Proof of the Perceptron Convergence Theorem
The last time I studied neural networks in detail was five years ago in college. I did touch upon backpropagation when Andrew Ng’s machine learning MOOC was offered on Coursera for the first time, but beyond that I’ve only dabbled with them through keras. Then recently, when I read about Coursera’s imminent decision to pull down much of their freely available material (you can read a rant about it here), I went on a downloading spree (many thanks to the wonderful coursera-dl).