Course notes, derivations, and personal analysis from the MAI program at University of Auckland.
Writing here aims to go beyond lecture summaries — each post tries to extract the core insight, expose the underlying math, and connect ideas across courses.
| Course | Focus |
|---|---|
| COMPSCI 713 | AI Fundamentals — probabilistic models, soft computing, bio-inspired AI |
| COMPSCI 714 | AI Architecture — transformers, LLMs, deep learning systems |
COMPSCI 713 · AI Fundamentals This course covers the theoretical and biological foundations of AI — including evolutionary computation, fuzzy logic, probabilistic reasoning, and biologically-inspired architectures such as protein structure prediction. Notes here focus on: the mathematical intuition behind classical AI methods connections between biological systems and computational models understanding why algorithms work, not just how to apply them
COMPSCI 714 · AI Architecture and Design This course focuses on the design and implementation of modern AI systems — transformer architectures, large language models, training dynamics, and system-level considerations in deep learning. Notes here focus on: architectural reasoning: why design choices are made, not just what they are implementation-level understanding — building models from scratch to expose internals connecting theory to real systems (GPT-2, attention mechanisms, tokenization)