Get comfortable with the math that powers modern machine learning while building practical modeling skills. We’ll unpack linear algebra, calculus for learning, probability and statistics, and optimization, then connect them to core algorithms like linear/logistic regression, k-means, PCA, decision trees, and introductory neural networks. You’ll implement concepts in Python with NumPy, scikit-learn, and a taste of PyTorch through short lectures, worked examples, and coding labs.

By the end, you’ll know not just which model to use, but why it works and how to make it better. We’ll practice model evaluation with cross-validation and the right metrics, diagnose overfitting, improve generalization and interpretability, and communicate results responsibly. The toolkit transfers to forecasting, fraud detection, recommendations, text understanding, and image analysis—making advanced AI topics feel approachable and useful on the job.

I’m Chang Liu, a teacher for Foundations of Machine Learning and AI math. My work centers on the math behind intelligent systems and how to translate it into reliable, real-world models. I focus on making complex ideas feel natural and actionable, drawing on experience teaching students how probability, linear algebra, calculus, and optimization shape modern machine learning.

In this course, we connect core mathematical tools to the algorithms you’ll actually use—building intuition, solving problems step by step, and practicing with meaningful examples. I’m passionate about creating a supportive, curiosity-driven classroom where you can ask bold questions, test your understanding, and leave with a solid foundation to explore AI with confidence.