Selective Reading Guide

Full-book reading is not required. Use Dive into Deep Learning for executable derivations, PyTorch docs for exact runtime behavior, Attention Is All You Need for the primary architecture, and LoRA for parameter-efficient adaptation.

Evidence and review

Record which uncertainty each source resolved. Claims must trace to versioned code and artifacts. Screenshots, unexplained generated prose, and a single favorable run do not pass.

Oral defense

Explain the mechanism, identify the most dangerous assumption, interpret one failure from raw evidence, and name the condition that would reverse your decision.

Source backbone

Use Dive into Deep Learning, PyTorch documentation, primary papers, and Designing Data-Intensive Applications selectively.