All the articles with the tag "machine-learning".
Backpropagation answers one question: when a network's prediction is wrong, how much should each weight change? Here's the idea, the three equations that do the work, and a tiny network you can trace by hand.
A model that doesn't fit on one GPU has to be split across many. A map of where training memory goes, how DDP, ZeRO and FSDP divide it, when to add tensor and pipeline parallelism, and how big runs survive failures.
Pre-training gives a model knowledge; post-training gives it behavior. A map of the main steps (supervised fine-tuning, LoRA, preference tuning, and reinforcement learning with checkable rewards), following one model as it becomes a SQL assistant.
GPU utilization is a lagging indicator — the real battle is in the data pipeline. A practitioner's deep dive into PyTorch DataLoader internals, zero-copy data pumps, WebDataset streaming, and the exact questions this gets you in ML system design interviews.
The hardest problem in AV: predicting human irrationality. From physics-based Kalman Filters to Joint Autoregressive Distributions, Generative Motion Diffusion, and World State Propagations.
A deep dive into XGBoost — how second-order Taylor approximations and sophisticated regularization make it the dominant algorithm for structured data, bridging mathematical rigor with system engineering excellence.