Advanced -> Machine Learning Algorithms¶

Textbook-breadth algorithmic ML taught first through the perceptron update rule on linearly separable binary data.

Microtopics¶

Source	Type
Stanford CS229 materials	`Course`
Stanford CS229 notes: Perceptron	`Course`
MIT OCW 6.867 lec2	`Course`

Material	Type
Machine Learning hot sheet	`quick reference`
Perceptron Classification Benchmark	`flagship note`
Online Algorithms tutorial	`compare point`
Template Library exact starter route	`starter route`

Problem	Source	Difficulty	Context	Style	Prerequisites	Tags	Why it fits
Perceptron Classification Benchmark	`Stanford CS229`	`Theory`	Machine Learning, Perceptron	Theory Benchmark; Online Update Rule	Dot Product; Signs And Margins; Basic Online Updates	Binary Classification; Linear Separability; Mistake-Driven Update	The cleanest first algorithmic ML benchmark for this repo because the update rule is tiny, explicit, and honest about the separability boundary.

Problem	Source	Difficulty	Context	Style	Prerequisites	Tags	Why it fits
Perceptron, convergence, and generalization	`MIT OCW 6.867`	`Theory`	Machine Learning, Margins	Lecture Notes; Theory Breadth	Perceptron; Linear Separability	Perceptron; Convergence; Generalization	A strong follow-up once the repo benchmark is clear and you want the surrounding theory without widening the lane into full modern ML.

Code	Title	Fit	Difficulty	Pattern	Note	Solution
`PERCEPTRONCLASSIFICATION`	Perceptron Classification Benchmark	`primary`	`medium`	-	Note	Code

python3 scripts/generate_problem_catalog.py