Front Matter
FM.3: Course Syllabi

Course B: Undergraduate Research

Prerequisites

Python programming. Calculus (derivatives, chain rule, gradients). Linear algebra (eigenvalues, matrix decomposition). Probability and statistics (Bayes' theorem, distributions). Recommended: one introductory ML course.

Course B: Undergraduate Research

Focus: Architecture internals, training methods, interpretability. Students leave with a deep understanding of how LLMs work and how to study them. This pathway trades breadth for depth: it covers the same foundations as Course A but then dives into pre-training, scaling laws, PEFT, and alignment. The reasoning is that future researchers need to understand the training pipeline end to end, since that is where novel contributions happen.

14-Week Syllabus

WeekTopicsLab / Assignment
1ML and PyTorch FoundationsBuild and train an image classifier in PyTorch
2NLP, Text Representation, Tokenization (Ch 01 through 02)Compare tokenizer vocabulary coverage across languages
3Sequence Models and AttentionImplement attention from scratch, visualize attention weights
4The Transformer ArchitectureBuild a minimal transformer (encoder + decoder)
5Decoding StrategiesImplement nucleus sampling, measure diversity vs. quality
6Pre-training and Scaling LawsReproduce a scaling law curve on a small model
7Modern LLM Landscape and Reasoning Models (Ch 07 through 08)Compare model architectures (paper reading assignment)
8Inference OptimizationBenchmark KV-cache and quantization effects
9Synthetic Data GenerationGenerate and validate a synthetic training dataset
10Fine-Tuning and PEFT (Ch 14 through 15)Compare full fine-tuning vs. LoRA on the same task
11Alignment (RLHF, DPO)Implement DPO training on a preference dataset
12InterpretabilityProbe internal representations with logit lens
13Emerging Architectures and AI and Society (Ch 34 through 35)Write a research proposal on an open problem
14Final project presentationsResearch paper replication or extension (individual project)
Recommended Appendices

What Comes Next

Return to the Course Syllabi overview to explore other courses and reading tracks, or proceed to FM.4: How to Use This Book for a quick orientation on conventions and callout types.