↓Skip to main content
Neural Odyssey

Writing

Writing on Machine Learning, Systems, and Engineering

This page collects the blog’s tutorials, implementation notes, and debugging lessons on machine learning, systems work, and engineering tradeoffs.

If you are new here, start with one of the guided paths below. If you already know what you want, use the archive to browse everything by date.

Read In Order

Choose a good entry point

Browse By Focus

Follow the path that matches your interest

Foundations

Posts that build intuition and explain how the core ideas fit together.

Implementation

Walkthroughs that focus on workflow, setup, and turning an idea into code.

Debugging

Posts focused on evaluation mistakes, failure modes, and what breaks in practice.

Archive

All posts in chronological order

Forget the intimidating equations for a moment. Let's build a genuine understanding of how neural networks actually work, from the ground up. No hand-waving, no magic—just clear explanations and practical intuition.

Machine learning tutorials make everything look smooth and polished. Reality is messier. Here are the painful lessons I learned the hard way, complete with the mistakes, the debugging nightmares, and what actually fixed them.

Forget toy examples with perfect data. Let's build a real ML model from scratch—complete with messy data, actual decisions you'll have to make, and code that you can run today. This is what building ML actually looks like.

Welcome to Neural Odyssey, a blog about machine learning, systems engineering, CUDA, and the debugging lessons behind real AI work.