Machine Learning,
from the inside out.

See the model. Stress the assumptions. Understand the behavior.

NOTEBOOKS → VISUAL EXPERIMENTS → PROJECTS → QUESTIONS

---

This repository is Ming Jin's workshop floor for ECE 4424 / CS 4824: Machine Learning. The notebooks favor experiments, visual explanations, and real systems over long stretches of passive theory. Curiosity is required; advanced mathematics is not.

Tip

Looking for the polished course experience? Visit the course site. Looking to tinker? Pick a notebook below and make something behave strangely.

Course map

Arc	#	Topic	Notebook	Companion material
Let's predict	00	Environment setup	open	setup guide
	01	What is machine learning?	open	course page · notes
	02	k-Nearest Neighbors	open	course page · notes
	03	Linear Regression	open	course page · environment
	04	Gradient Descent & Optimization	open	course page · teaching notes
	05	Probabilistic Classification	open	course page
Let's understand	06	Evaluation Pitfalls & Data Visualization	open	course page
	07	Regularization & Generalization	open	course page · environment
	08	Modern Decision Trees	open	course page
	09	Ensemble Methods	open	course page
	10	Kernel Methods & Gaussian Processes	open	course page
Let's discover	11	K-Means Clustering	open	course page
	12	PCA & Dimensionality Reduction	open	course page · quickstart
	13	Neural Network Architecture	open	course page
	14	Understanding Transformers	open	course page
Let's see & chat	15	Convolutional Neural Networks	open	course page
	16	Recurrent Neural Networks	open	course page
	17	LLM Agents & Tool Use	open	course page
	18	Vision-Language Models	open	course page

Build something that bites back

Three projects, three ways to make a model reveal what it is doing.

01 · KNN Music Recommender Search a real music catalog, define what “similar” means, and listen critically when nearest neighbors get strange. Brief · Notebook · Live demo

02 · Neural Archaeology Excavate hidden states layer by layer, find the geometry of a concept, and test whether it can predict—or change—behavior. Brief · Notebook

03 · Thought Cascade Give a small language model tools and feedback, then measure when a reasoning-and-action loop actually repairs broken code. Brief · Notebook

Enter the lab

git clone https://github.com/jinming99/learn-ml-by-building.git
cd learn-ml-by-building

python3 -m venv ml_lectures_env
source ml_lectures_env/bin/activate
python -m pip install --upgrade pip
python -m pip install -r requirements.txt

jupyter notebook

For platform-specific help, begin with the environment setup guide. Basic Python, high-school mathematics, and a willingness to poke at models are enough to start.

---

_{These materials were directed, reviewed, and validated by the instructor. AI-assisted tools were used during development to model transparent, modern technical practice. Released under the MIT License.}