Building Self-Attention and Transformer Engines: Architecture, Internals, and Best Practices A deep dive into deep learning — Query-Key-Value projection matrices, Scaled Dot-Product Softmax math, Multi-Head Attention (MHA), R…
How to Implement Gradient Boosting from Scratch A mathematical and practical deep dive into Gradient Boosting Decision Trees (GBDT) and XGBoost — Taylor series expansions, gradient/Hessian optimization, split gain formulas, a…
Understanding Support Vector Machines: A Deep Dive for Developers A machine learning developer's systems guide to SVMs — covering margin maximization geometry, soft margins, Lagrange dual formulations, the kernel trick, a…