Welcome to Machine Learning!!
Data and algorithms are increasingly shaping our world. In this class, Introduction to Machine Learning, we will explore how machines learn from data and how those learning processes influence science, technology, and everyday life. We will study the foundational ideas behind machine learning models and work hands-on with real datasets and code. It will be challenging, practical, and (I hope) intellectually exciting.
Throughout the semester, we will move across different approaches to machine learning, including supervised and unsupervised learning. We will build models, test them, break them, and reflect on what they do well—and where they fail. Along the way, we will discuss how machine learning systems interact with society, ethics, and human decision-making. Expect a mix of coding, problem-solving, discussion, and critical thinking.
You will learn how to talk and write about machine learning using appropriate technical terminology without losing your own voice or curiosity. We will spend time understanding not just how algorithms work, but why they behave the way they do and what assumptions they make about the world. Assignments are scaffolded to help you build skills gradually, leading up to a final project where you apply machine learning techniques to an open dataset of your choice.
Machine learning workflow showing data collection, preprocessing, model training, evaluation, prediction, and iterative refinement.
An Important Note
Machine learning is not a collection of formulas to memorize or code snippets to copy. It is a way of thinking about data, uncertainty, and decision-making. This course asks you to slow down, experiment, and reflect. You will sometimes feel confused when a model performs poorly or behaves unexpectedly—and that frustration is part of the learning process.
You are encouraged to test ideas, ask questions, revisit concepts, and learn from mistakes. Careful experimentation and thoughtful interpretation matter more than perfect results. Through active engagement with the material, I hope you will become a more confident programmer, a more critical analyst of algorithms, and a more responsible user of machine learning technologies.
Overall, aim to work carefully, think critically, and remain curious.
Essentials
Course Title: Introduction to Machine Learning
Institution: Brooklyn College, City University of New York
Course Level: Upper-Division Undergraduate
Semester Length: 14 Weeks
Course Designation: Zero Textbook Course (ZTC)
Course Format:
Lectures, coding labs, assignments, discussions, and a final project
Required Materials:
There is no required textbook. All materials used in this course are openly licensed or freely available online.
About This Course Site
This site was created on the CUNY Academic Commons as part of the Open Knowledge Fellowship (13th Cohort, Winter 2026). The course is shared publicly under an open license to support equitable access to education and reuse by other instructors.
Open License
All original course materials on this site are licensed under:
Creative Commons Attribution 4.0 International (CC BY 4.0)
