Writing in Data Science can have a transformative effect not only in your journey but also in your career.
I appeared on the FastBook Reading Sessions organised by Weights & Biases to discuss about the benefits of writing in Data Science. I wrote this piece to summarize what I covered there. This article was originally published on their forums but I’m sharing a somewhat edited version here as well…
PASS: An ImageNet replacement for self-supervised pretraining without humans
ImageNet is one of the most widely used datasets in Computer Vision applications. However, studies have shown biases prevalent in this dataset based on the collection methodology and the types of images present. In this respect, a team of researchers at the Visual Geometry Group, the University of Oxford, have…
Analyzing the 2021 Russian Grand Prix with the Fast F1 library
What’s behind you doesn’t matter — Enzo Ferrari
The 72nd season of the Formula One World Championship or F1 is underway. Fierce battles are being witnessed between the ten teams for the ultimate title. Nevertheless, the races are not without their fair share of drama, anticipation, sweat, tears, and emotions…
Hands-on Tutorials
A look into matplotlib backends that enable interactivity
Good charts effectively convey information. Great charts enable, inform, and improve decision making.” — Dante Vitagliano
Interactive charts are loved by all as they can tell a story more effectively. The same is true in data science and allied fields. Exploratory data analysis is an essential step in the data…
Breaking down the idea of L¹, L², L∞, and the Lᵖ norms
Note:
1. All images are by the author except where stated otherwise.
2. There are two typos in the article. However, I am unable to rectify them as I don’t have permission to edit the images post article’s publication. …
A dataset containing tweets exhibiting six different emotions.
You’ll just never know…so many emotions I choose not to show you
Emotion Recognition is a common classification task. For instance, given a tweet, you create a model to classify the tweet as being either positive or negative. However, human emotions consist of myriad emotions and cannot be constrained to…
A library to build tree-based models with Tensorflow and Keras
In their paper, Tabular Data: Deep Learning is Not All You Need, the authors argue that while deep learning methods have shown tremendous success in the image and text domains, traditional tree-based methods like XGBoost still continue to shine when it comes to tabular data. …
Machine learning pitfalls, cutecharts, Github features, and more…
Every month I send out a newsletter that summarises my writing activity in the past month along with some interesting stuff that I encounter in the machine learning space. This month I am also sharing the newsletter here. …
Resources for finding datasets suitable for your needs.
While going through the list of the articles that I have written to date, I discovered that quite a few were related to the concept of acquiring datasets for data science tasks. Some of those articles are targeted at finding good dataset websites, while others look at ways to create…
In conversation with Kunhao Yeh: A Data Scientist and Kaggle Grandmaster
In these series of interviews, I present the stories of established Data Scientists and Kaggle Grandmasters at H2O.ai, who share their journey, inspirations, and accomplishments. These interviews are intended to motivate and encourage others who want to understand what it takes to be a Kaggle Grandmaster.
