Syllabus

Introduction to Machine Learning

Course Information

Course Title: Introduction to Machine Learning
Instructor: Md Abu Hanif
Course Level: Upper-Division Undergraduate
Semester: TBD
Credits: 3
Department: Computer and Information Science
Institution: Brooklyn College, City University of New York

Download the Syllabus (PDF)

Syllabus_Introduction_to_Machine_Learning_Fall_2026Download

Course Description

This course introduces the core principles and techniques of machine learning, with an emphasis on conceptual understanding, practical implementation, and responsible use. Students will study supervised and unsupervised learning methods, model evaluation, and the role of data in algorithmic decision-making.

The course is taught using open educational resources (OER) and emphasizes hands-on learning through open-source software and publicly available datasets. Students will gain experience building, testing, and interpreting machine learning models while reflecting on ethical, social, and historical dimensions of machine learning systems.

Learning Objectives

By the end of the course, students will be able to:

  1. Explain foundational concepts and algorithms in machine learning
  2. Implement machine learning models using Python and open-source libraries
  3. Apply supervised and unsupervised learning techniques to real-world datasets
  4. Evaluate and compare models using appropriate performance metrics
  5. Communicate technical results clearly through code, visualizations, and written analysis
  6. Demonstrate ethical awareness in data selection, model design, and deployment

These objectives align with undergraduate computer science learning outcomes and prepare students for advanced coursework or applied work in data-driven fields.

Prerequisites

  • Programming experience in Python (CISC 1115 or equivalent)
  • Linear Algebra (recommended but not strictly required)

Students without the recommended background should consult the instructor early in the semester.

Required Course Materials (Zero Textbook Course)

There is no required commercial textbook.
All materials used in this course are freely available and openly licensed.

Open Textbooks

  • Understanding Machine Learning: From Theory to Algorithms—Open Access
  • Dive Into Deep Learning (D2L)—Open textbook

Software & Programming Tools

  • Python (open-source)
  • NumPy, Pandas, Scikit-learn
  • Matplotlib
  • PyTorch or TensorFlow

All software used in this course is open-source and available at no cost.

Datasets

  • UCI Machine Learning Repository
  • OpenML
  • NYC Open Data
  • Selected open datasets curated by the instructor

Course Structure and Pedagogy

The course combines:

  • Lectures focused on conceptual understanding
  • Coding labs emphasizing experimentation and iteration
  • Scaffolded assignments that build toward a final project
  • Discussion of ethical, social, and interpretive issues in machine learning

Assignments are designed to help students gradually develop confidence with both theory and implementation.

Assessment Philosophy

Assessment in this course prioritizes:

  • Understanding over memorization
  • Reproducible and well-documented code
  • Clear explanation of modeling choices and results
  • Responsible and ethical use of data

Students are encouraged to view mistakes and unexpected results as part of the learning process.

Academic Integrity

Students are expected to adhere to all CUNY academic integrity policies.
Although this course uses open resources, all sources must be cited appropriately, and all submitted work must represent the student’s own understanding and effort. Collaboration is encouraged where explicitly permitted, but submitted assignments must be original.

Accessibility and Accommodations

Brooklyn College is committed to providing reasonable accommodations for students with documented disabilities. Students who require accommodations should contact the Center for Student Disability Services and inform the instructor as early as possible.

Open Education Statement

This course is designated as a Zero Textbook Course (ZTC). All instructional materials are available at no cost to students and are shared under an open license whenever possible.

License

All original instructional materials created for this course are licensed under:
Creative Commons Attribution 4.0 International (CC BY 4.0)