I'm a student obsessed with understanding how AI actually works — not just using it, but building it from the ground up. No black boxes. No shortcuts. Just Python, math, and curiosity.
When everyone else imports a library, I write the math myself.
- Neural Networks from scratch — perceptrons, multi-layer networks, backpropagation, all by hand
- ML without libraries — understanding what TensorFlow and PyTorch are actually doing under the hood
- Game Dev — exploring how AI and interactivity meet
| Project | What It Does |
|---|---|
| perceptron-from-scratch | A single neuron that learns AND, OR & NOR logic — zero ML libraries |
| weather-neural-network-python | Multi-layer network predicting rainfall using raw backpropagation |
"If I can't build it from scratch, I don't understand it yet."
I believe the best way to learn AI isn't to use it — it's to build it. Every project here is a step deeper into understanding how machines actually think.
Always learning. Always building.