All the articles with the tag "deep-learning".
A practitioner's guide to distributed training frameworks — the memory formulas, parallelism strategies, and failure-mode reasoning that ML infra interviews actually test. Covers DDP, FSDP, DeepSpeed ZeRO, 3D parallelism, and fault tolerance.
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.
Pre-training gives a model knowledge; post-training gives it behavior. A practitioner's breakdown of SFT, LoRA/QLoRA, DPO, and GRPO — with the memory math, concrete configs, and interview reasoning that separates candidates who've done this from candidates who've read about it.
A complete derivation of backpropagation for MLPs — from chain rule intuition to delta propagation, with a worked numerical example showing exactly how errors flow backward through a network.
A narrative-first walkthrough of reinforcement learning, starting with everyday intuition and ending with the math behind Q-learning and DQN.
A high level view on how modern vision-language models connect pixels and prose, from CLIP and BLIP to Flamingo, MiniGPT-4, Kosmos, and Gemini.