Quiz

Explain computation graphs, reverse-mode autodiff, initialization, learning-rate failure, embedding similarity, tokenization, positional information, attention masks, residual paths, causal objectives, PEFT, quantization, KV caches, ablations, and capability limits.

Evidence and review

Answer 15 prompts closed-book, then demonstrate three answers with code. 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.