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…

Building interpretable Boosting Models with IntepretML — As summed up by Miller, interpretability refers to the degree to which a human can understand the cause of a decision. A common notion in the machine learning community is that a trade-off exists between accuracy and interpretability. This means that the learning methods that are more accurate offer less…

Analyzing the 2021 Abu Dhabi Grand Prix with the Fast F1 library — # First published on Oct 15, 2021. Edited on March 20, 2022 What’s behind you doesn’t matter — Enzo Ferrari The 73rd season of the Formula One World Championship or F1 commenced in Bahrain on 20th March 2022. Fierce battles are being witnessed between the ten teams for the ultimate…

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…

An interview with Christoph Molnar, author of the book- Interpretable Machine Learning — A series of interviews highlighting the incredible work of writers in the space of data science and their path of writing. “If you don’t see the book you want on the shelf, write it” — Beverly Cleary In an endeavor to bring such notable work to the forefront, I started…

An open-source package for decision tree visualization and model interpretation — Data visualization is the language of decision-making. Good charts effectively convey information. Great charts enable, inform, and improve decision making: Dante Vitagliano Decision trees can be visualized in multiple ways. Take, for instance, the indentation nodes where every internal and leaf node is depicted as text, while the parent-child relationship…

An interview with Radek Osmulski, author of the book- Meta Learning: How To Learn Deep Learning And Thrive In The Digital World — A series of interviews highlighting the incredible work of writers in the space of data science and their path of writing. “So long as you write what you wish to write, that is all that matters; and whether it matters for ages or only for hours, nobody can say.” ―…

Explore the geospatial data with interactive visualizations — If geography is prose, maps are iconography : Lennart Meri The word geospatial is composed of two distinct terms. Geo means Earth, and Spatial means relating to or occupying space. Together it refers to the time-based data pertaining to a specific location on the Earth’s surface. GeoPandas is a popular…

So that you do not get lost in the sea of papers. — If I have seen further, it is by standing on the shoulders of Giants— Isaac Newton. The above quote first made its appearance in a letter that Newton wrote to Robert Hooke in 1675. Since then, the statement has been used to symbolize scientific progress and advancements. It is often…