Applied Mathematics of Machine Learning

Go beyond model.fit() and truly understand how machine learning works. In this intensive, hands-on workshop, you will master the mathematical foundations that power machine learning and data science.

In this course, you’ll learn to train a linear regression model from end to end. Yes, I know: linear regression is not exactly the state-of-the-art. However, we won’t just throw a high-level library at the problem and call a couple of methods. We’ll build everything from scratch! It’s like preparing a full four-course lunch by yourself instead of going to the restaurant. Sure, it’ll take more time, but you’ll learn to be a hell of a cook.

Ultimately, this workshop connects the dots between core theory and practical implementation. You’ll explore the complete conceptual pipeline: from representing and manipulating data, to optimizing models, and quantifying uncertainty. With clear explanations and practical coding sections, you’ll be ready to build, debug, and push the state-of-the-art with a depth of understanding few practitioners possess.

By the end of this workshop, you’ll be able to:

• Understand how vectors, matrices, and linear transformations are used to represent complex data.
• Grasp how derivatives and gradients are used to optimize models via gradient descent.
• Apply core probability rules and distributions to quantify uncertainty and build simple classifiers like naive Bayes.
• Manipulate vectors and matrices in Python using NumPy to implement mathematical concepts directly.
• Translate the mathematical notation found in ML research papers into concrete code and conceptual understanding.
• Gain the essential foundational knowledge needed to tackle advanced ML and deep learning topics with confidence.
  

Who should attend?

• Aspiring Data Scientists & ML Engineers who want to build a rock-solid, fundamental understanding of the models and algorithms they use every day.
• Python Developers & Software Engineers looking to transition into AI/ML roles and understand what's under the hood.
• Data Analysts who want to grasp the 'why' behind the models they use and interpret their outputs correctly.
• Computer Science or STEM Students eager to connect their theoretical math knowledge to practical applications in data science.

This isn’t just a lecture—it’s an intuitive, hands-on learning experience. Here’s what sets it apart:

• Intuition-First Approach. You won’t just memorize formulas, you’ll build a deep, visual, and conceptual intuition for what they are and how they work.
• Machine Learning Before Math. Every mathematical concept is immediately tied to a core machine learning algorithm.
• Code the Concepts. Work directly with Python and NumPy to implement mathematical concepts from scratch, solidifying your understanding far beyond high-level library calls.
• Open the Black Boxes. This course is designed to demystify machine learning, giving you the confidence to read research, debug complex models, and explain your work effectively.