10-718 ML in Practice: Spring 2026

• Instructor: William Cohen (wcohen@cmu.edu)
• Times: Tue-Thus 3:30-4:50pm
• Resources:
  • Schedule of meetings
  • Shared GDrive for class
  • Sample datasets for project
  • Piazza: TODO
  • Gradescope: TODO
  • Signup sheet for presentations/discussions: TODO
• Prior versions of this course:
  • Dr. Ghani Fall 2025
  • Dr. Smith Spring 2025
  • Dr. Wilder Fall 2024

Overview

This is a project- and discuss-based course designed to provide students training and experience in solving real-world problems using machine learning, exploring the interface between research and practice. The goal of this course is to give students exposure to the nuance of applying machine learning to the real-world, where common assumptions (like iid and stationarity) break down. Students will learn how to formulate real-world business or policy scenarios as machine learning problems, how to address common challenges which arise in applying ML to such problems (e.g., distribution shift or missingness), how to rigorously evaluate the results of such interventions in practice; and how to present such empirical results orally and in writing. We will place an emphasis throughout on issues related to ethics and fairness in machine learning, and discuss how choices throughout the machine learning pipeline – including problem formulation, outcome definition, data collection, and model training – contribute to the social impact of algorithmic systems.

After completing the course, students should be able to design and evaluate novel combinations of learning algorithms; take real-world questions involving data and evaluate and/or develop appropriate methods to answer these questions; and present technical material clearly, in spoken and written form.

Prerequisites

Students entering the class are expected to have a pre-existing working knowledge of common machine learning methods, as well as implementation in Python. We will focus on how to choose between different machine learning techniques, modify them to address common real-world challenges, and evaluate their performance. We will assume that students are already familiar with the models themselves (e.g., linear regression, decisions trees, ensembles, neural networks), as well as how to train such models in Python.

The core content of this course does not exactly follow any one textbook. We will have required and suggested readings associated with each lecture, which can be found on the course website. Two general references that may be helpful are:

• AI for Social Impact. Edited by Fang, Tambe, and Wilder. Freely available at https://ai4sibook.org/
• Big Data and Social Science. Edited by Foster, Ghani, Jarmin, Kreuter and Lane. Freely available at https://textbook.coleridgeinitiative.org/

Course Components

The requirements of this course consist of two components: participating in in-class discussions, presentating material for class, and completing the course project.

Class discussions

This course emphasizes the process of thinking through real-world problems and how and when they can be addressed using machine learning. Accordingly, our class sessions will rely on student participation to discuss potential scenarios and case studies together. You are highly encouraged to engage actively during class discussions, which will make the course much more exciting for everyone. During such discussions, we expect you to be respectful at all times towards your fellow students. Discussions will loosely follow the role-playing seminar format; for each paper, you will either be assigned a presenter role or complete the non-presenter assignment (described below).

Presenter assignment

You will periodically present a paper in class, taking on one of the following presenter roles.

• Educator: Explain the key ideas in the paper to the class. Keep your presentation to 5-10 minutes maximum.
• Investigator: Investigate one of the paper’s authors. What is their area of expertise? Where have they worked previously? What prior projects might have led to working on this one? Explore what motivated them to write the paper and what biases they may have.
• Reviewer: Discuss both one strength and one weakness of the paper. What did you like about the paper? Do you agree with the paper's stance/findings? Did the paper overlook anything? Is there something that could have strengthened the work?
• Discussion Leader: Prepare three discussion questions to ask the class, and lead the discussion amongst the students when answering these questions.

Non-presenter assignment

If you are not presenting the paper, you must still read the paper and provide at least one discussion question about the paper (e.g., something you're uncertain about or would like to hear discussed).

Course project

Students will complete a semester-long course project that explores the application of machine learning to a problem of practical interest. Students may work in groups of two or three people. Each group will select a dataset, which _cannot_ be one commonly used in machine learning research. Over a series of assignments, each group will define a problem to be addressed using the dataset, clean and explore the data, develop baselines and machine learning models, and explore the impact of additional desiderata on their pipeline (e.g., fairness, privacy, interpretability, or model efficiency). Students can either select their own dataset for the project (which cannot be a commonly used ML benchmark dataset) or select one from the set of examples provided.

Grading

Discussion participation

• Presenter assignments: 3 over the course of the semester, 5 points each. 15 total points
• Non-presenter assignments: 15 over the course of the semester (out of 16 possible sessions), 1 point each
• You are allowed to miss one non-presenter assignment without penalty.
• This format may be adjusted as needed during the semester.

Course project

• Assignment 0: 5 points
• Assignment 1: 20 points
• Assignment 2: 20 points
• Assignment 3: 20 points
• Assignment 4: 20 points
• Final presentation: 15 points

Other policies

Regrade requests

Late homeworks

• All homework submissions are electronic, and lateness will be determined by the latest timestamp of any part of your submission.
• Once you have exhuasted your late days any submission up to 24 hours late will recieve a 50% penalty. Any work submitted after 24 hours will be graded but will not be eligible for any credit.

Extensions

• Medical Emergencies: If you are sick and unable to complete an assignment or attend class, please go to University Health Services. For minor illnesses, we expect grace days or our late penalties to provide sufficient accommodation. For medical emergencies (e.g. prolonged hospitalization), students may request an extension afterwards and should include a note from University Health Services.
• Family/Personal Emergencies: If you have a family emergency (e.g. death in the family) or a personal emergency (e.g. mental health crisis), please contact your academic adviser or Counseling and Psychological Services (CaPS). In addition to offering support, they will reach out to the instructors for all your courses on your behalf to request an extension.
• University-Approved Absences: If you are attending an out-of-town university approved event (e.g. multi-day athletic/academic trip organized by the university), you may request an extension for the duration of the trip. You must provide confirmation of your attendance, usually from a faculty or staff organizer of the event.

Audit Policy

Pass/Fail Policy

Accommodations for Students with Disabilities

Academic Integrity Policies

Collaboration among Students

• Group project: Students are expected to collaborate with their groupmates on the project and implementation, and this collaboration need not be reported: it is assumed.
• Collaborations outside the group project: Studying the material in groups is encouraged. It is also allowed to seek help from other students in understanding the material needed to solve a particular homework problem, provided no written notes (including code) are shared, or are taken at that time, and provided learning is facilitated, not circumvented. The actual solution must be done by each student alone.
• The presence or absence of any form of help or collaboration, whether given or received, must be explicitly stated and disclosed in full by all involved. Specifically, each assignment solution must include a collaboration section.
• If you gave help after turning in your own assignment and/or after answering the collaboration section, you must update your answers before the assignment’s deadline, if necessary by emailing the course staff or a Piazza post.
• Collaboration without full disclosure will be handled severely, in compliance with CMU’s Policy on Academic Integrity. All violations (even first one) of course policies will always be reported to the university authorities (your Department Head, Associate Dean, Dean of Student Affairs, etc.) as an official Academic Integrity Violation and will carry severe penalties. The penalty which will be recommended by the Professor for violation of the academic integrity policy is failure in the course. For repeat offenders, violoation of academic integrity policies can even lead to dismissal from the university.
• While students are encouraged to use generative AI tools as resources or as collaborators on a course project, use of generative AI to produce any part of an assignment (project or presentation) should be documented in the collaboration section.
• At the instructor's discretion, any assignments or presentations may also be supplemented with an oral quiz in a small group, or one-on-one with the instructor. One reason for doing this to verify that generative AI has not be over-used, i.e., used to the extent that a student does not fully understand some material that he/she has presented or turned in.
• Students are responsible for proactively protecting their work from copying and misuse by other students. If a student’s work is copied by another student, the original author is also considered to be at fault and in violation of the course policies.

Previously used assignments