Writing on machine learning, engineering, and the systems behind AI products.
Tutorials, experiments, and implementation notes written to be directly useful.
Station Rules
Clear explainers
Complex topics are broken into steps, examples, and implementation notes.
Practical bias
Most posts tie theory back to code, tooling, or product decisions.
Galton-Watson Process
In this post, we outline the Galton-Watson Process.
Browse the remaining stops on the line.
Check if an agent is doing the right thing with Policy Evaluation Methods
Reinforcement learning is about an agent learning to make better decisions through trial and error to maximize long-term rewards. What does that entail in practice?
In this blog I will focus on the ways in which I set up a backend and frontend to do rapid prototyping of full stack applications.
A practical implementation of gradient descent for logistic regression, including numerical-stability considerations.
In this blog post I explain how the Maximum Likelihood Estimator is used in Machine Learning.
Get hands-on experience with deploying Large Language Models (LLMs) at scale using NVIDIA's Triton Inference Server.
Learn what TF and IDF measure and how TF-IDF can be used to process text for machine learning.
Encode and compare question pairs from the Quora Question Pairs dataset at practical scale.
Learn the math behind text-vector similarity using NumPy, PyTorch, and Sentence Transformers.
An interactive introduction to how D3.js works with SVG elements, data joins, charts, and maps.