Articles and learning paths are published. Corrections are welcome in the comments.
Master the basics of probability for machine learning. Explore sample spaces, expected values, variance, and the Central Limit Theorem with practical real-world analogies and pure Python implementations from …
The maths modern AI leans on, derived step by step and checked against clean NumPy. Dense layers, regression, cross-entropy gradients, backprop, PCA and SVD, Adam, numerical stability and …
Build a Vision Transformer from first principles in PyTorch, work out its parameters and FLOPs by hand, then shrink it with ONNX, INT8 and TensorRT so it runs …
A first-principles tour of Polars: Arrow memory, SIMD, Rust threads and the lazy query optimiser, then a runnable pandas-versus-Polars pipeline, a migration cheat-sheet, Rust tooling (DuckDB, uv, Ruff, …
Learn how LoRA and QLoRA let you fine-tune a 7B model on a single consumer GPU, from the memory arithmetic and low-rank math to NF4 quantisation in NumPy, …
Build an agent from scratch in 60 lines of Python, compare the main agent architectures, watch the raw JSON-RPC messages of the Model Context Protocol, write an MCP …
Your feedback has been received and we'll review it soon.
