Reflections on 2025
Looking back at a year of open source, career changes, and the rise of AI agents.
dhruv's space
Recent content on dhruv's space
Latest posts
Keeping up with dependency updates
How I stay on top of the never-ending cycle of dependency updates for my projects.
Feature Preview Deployments for the Front-end
Adding support for feature previews for a front-end application
Knowing What You're Shipping
Getting more visibility in what software you're shipping as a team
Getting pytest results into Neovim's quickfix list
Getting pytest results into Neovim's quickfix list
Binary Search Trees
Lecture notes on Binary Search Trees. Based on Josh Hug's lectures from UC Berkeley's CS61B.
Disjoint Sets
Lecture notes on disjoint sets and the problem of dynamic connectivity. Implementations discussed include Quick Find and Weighted Quick Union. Based on Josh Hug's lectures from UC Berkeley's CS61B.
ML Basics #4: Replace Negatives with Zeros!
This is the fourth post in this series on the basics of Machine Learning. These posts are intended to serve as companion pieces to this zine on binary classification. In the last one, we learnt how adding hidden layers to a Multilayer Perceptron helps it learn increasingly complex decision boundaries. The MLPs used till now made use of the sigmoid function as the activation function. In this post,…
ML Basics #3: More Layers!
This is the third post in this series on the basics of Machine Learning. In the last one, we learnt how a Multilayer Perceptron can be trained to non-linearly segment a dataset. We also saw how a simple artificial neuron forms the building block of a Multilayer Perceptron — or a neural network in general — which can learn much more complicated decision boundaries. Let’s move on to datasets…
ML Basics #2: Multilayer Perceptron
This is the second post in this series on the basics of Machine Learning. The last post detailed the functioning of an artificial neuron, and how it can be trained to linearly segment a dataset. However, most real world datasets are not linearly separable, which begs the question: What is the point of learning about a neuron? Well, by the end of this post, we’ll see that a bunch of neurons,…
ML Basics #1: Start With A Neuron
This is the first post in this series on the basics of Machine Learning. My aim here is to create a comprehensive catalogue of ML concepts so that I can quickly refer to them in the future, as well as be of help to anybody in a position similar to mine. This post complements the first segment in the zine: Linear Binary Classification. The idea is to have the content here supplement that in the…
Takeaways from Naval Ravikant's JRE episode
Naval Ravikant recently made an appearance on The Joe Rogan Experience. An entrepreneur and an angel investor — he’s invested in more than 100 companies, including Uber, Twitter, Yammer, and many others — Naval is a co-author of Venture Hacks , and a co-maintainer of AngelList . In their two-hour long conversation, he and Joe discuss a wide array of topics — namely philosophy, knowledge gathering,…
Understanding the A star algorithm
Understanding the A star algorithm
Summary Notes: Bayes' Theorem
Summary notes for Bayes' theorem
Visualizing inputs that maximally activate feature maps of a convnet
Understanding workings of convnets by visualizing inputs that maximally activate individual feature maps of a ResNet-34.
Generating artistic images using Neural Style Transfer
Generating artistic images using Neural Style Transfer and fastai
Understanding Object Detection Part 4: More Anchors!
Part 4 of series on object detection. Details creating anchor boxes of various shapes, focal loss, and non max suppression.
Understanding Object Detection Part 3: Single Shot Detector
Part 3 of series on object detection. Includes basics of multiple object detection by using a single shot detector. Includes basics of anchor boxes.
Understanding Object Detection Part 1: The Basics
Part 1 of series on object detection. Sets up the basics for classifying and localizing objects in images.
Understanding Object Detection Part 2: Single Object Detection
Part 2 of series on object detection. Details working of a single object detector using a single deep neural network.
Evolution of Grad-CAM heat-maps along a ResNet-34
Evolution of Grad-CAM heat-maps along a ResNet-34
Generating class discriminative heat-maps using Grad-CAM
Generating class discriminative heat-maps using Grad-CAM.
Understanding ResNets
Understanding ResNets.
Summary Notes: GRU and LSTMs
Summary Notes on GRU and LSTMs
Word Embeddings and RNNs
Word Embeddings and RNNs
Summary Notes: Basic Recurrent Neural Networks
Summary Notes on Recurrent Neural Networks
Visualizing Convolutions
Summary Notes on Recurrent Neural Networks
Visualizing Optimisation Algorithms
Visualizing Optimisation Algorithms
Summary Notes: Forward and Back Propagation
Summary Notes for forward and back propagation
Writing a decision tree from scratch
Writing a decision tree from scratch
Booking Wonder Woman tickets with a twist
Booking Wonder Woman tickets with a twist
Learnings
Learnings Catalogue of MOOCs/courses I’ve taken over the years; listed in reverse chronological order: The Missing Semester Offered By: MIT The Missing Semester teaches computing ecosystem literacy. CS61B: Data Structures Offered By: UC Berkeley IntelliJ IDEA Community Edition Essential Training Offered By: LinkedIn Completed: April, 2020 Certificate APIs and Microservices Certification…