CS1675: Intro to Machine Learning (Spring 2026)

Course Description

This course on machine learning provides an in-depth exploration of theoretical foundations and algorithmic innovations of machine learning. The course emphasizes mathematical intuition, algorithmic efficiency, and the ability to absorb cutting-edge research in the field. Machine learning as a subject has evolved dramatically over the past decades. Topics covered by this class include deep learning, reinforcement learning, generative AI, and their applications to real-world social impact problems.

Prerequisites

Formal prerequisites include linear algebra, probability, algorithms, and proficiency in at least one programming language. A high level of mathematical maturity will be helpful. Please see the instructor if you are unsure whether your background is suitable for the course.

Textbooks

This course does not exactly follow any textbook. Most lectures will have some optional reading to help you better understand the material or see a different presentation/perspective.

Course Schedule (Subject to Change)

Course Project

The course includes a semester-long project aimed at developing practical and conceptual understanding of machine learning through implementation and experimentation. You may choose one of the two project options below. Both options are equally valid and will be graded using the same standards of rigor, clarity, and insight.

General Expectations (All Projects)

• Clearly define the problem or question being addressed
• Use appropriate baselines and evaluation metrics
• Follow a sound experimental protocol (e.g., proper train/validation/test splits)
• Include analysis and interpretation of results, not just performance numbers
• Discuss limitations and failure cases

You will work in groups of 3-4 people on a course project related to machine learning. The progress of projects will be checked through the Project Proposal, Project Progress Report, Project Presentation, and Final Project Report. The proposal and progress reports will be peer-reviewed and graded by the instructor. The presentation and the final report will be evaluated by the instructor directly.

Proposal due: February 13th
Progress report due: March 20th
Oral presentations: April 21st
Final report due: April 28th

Option 1: Applied Machine Learning Project

You will identify a real-world problem and dataset, apply existing machine learning methods, and evaluate their effectiveness.

Requirements

• Select a dataset and clearly define the task (e.g., classification, sequential decision making)
• Implement and evaluate:
  • At least one simple baseline
  • At least one more advanced model
• Use appropriate validation and evaluation procedures
• Include error analysis or diagnostic analysis (e.g., learning curves, feature importance)

Note: Performance alone is not sufficient; the emphasis is on understanding why methods work or fail.

Option 2: Reproduction + Extension Project

You will reproduce results from an existing machine learning research paper and propose a small, well-motivated extension.

Requirements

• Select a research paper (subject to instructor approval)
• Reproduce at least one main experimental result
• Propose one modest extension (e.g., architectural change, training variation, new dataset)
• Evaluate the extension using controlled experiments and compare it to the reproduced baseline

Note: The extension does not need to improve performance; careful analysis is sufficient.

Quizzes and Final Exam

There will be two quizzes and a final exam. The quizzes will be on Canvas and open-book, featuring multiple choice and fill in the blank questions. You will have two attempts for each quiz, and the higher score will be recorded. In addition, you will be required to submit a document describing your approach to solving the quiz questions. The final exam will be in-class and closed-book.

Problem Sets and Recitations

There will be a light problem set every 2 weeks. Problem sets are posted to Canvas on Friday. Problem sets are due on Canvas on Tuesdays 11 days later. Each problem set contains 2-3 problems. In the weeks after each problem set is posted, during the recitation the TAs will walk through the problems. In other weeks ("off-weeks"), recitation will be used as TA office hours for students to ask questions about lectures, problem sets, or projects.

Grading

Course Policies

Grading

• Late-submission policy: You have a total of 4 grace days on problem sets and quizzes. Grace days are incurred in full days – no partial days are given. No grace days are allowed for project-related assignments. Beyond the permitted grace days, the instructor reserves the right not to grade the assignments, except for the following situations:
  • Medical Emergencies: If you are sick and unable to complete an assignment or attend class, please go to Student 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 and/or University Counseling Center.
  • University-Approved Travel: If you are traveling out-of-town to a university approved event or an academic conference, you may request an extension for any time lost due to traveling. For university approved absences, you must provide confirmation of attendance, usually from a faculty or staff organizer of the event or via travel/conference receipts.
  For any of the above situations, you may request an extension by emailing me. The email should be sent as soon as you are aware of the conflict, and at least 3 days prior to the deadline. Extension requests received after this date will not be considered. In case of an emergency, no advanced request is needed. This is reserved for truly emergent situations.
• Re-grading policy: To request a re-grade, please write an email to the instructor titled “Re-grade request from [Student's Full Name]” within one week of receiving the graded assignment.

Collaboration

• For the course project, you may collaborate with others outside the class (including students, faculty members, and domain experts) with approval from the instructor. You are still expected to take the leading role in the project. If you have external collaborators, you need to give proper credits to all parties involved, and report the contributions of each contributor in the proposal, progress report, final report, and presentations, which will be considered in the grading.

Academic Integrity

• For reproduction projects, you may use code released by the original authors. However, simply running existing code is not sufficient. Students must demonstrate understanding of the method, reproduce at least one main result, and implement a substantive extension that requires modifying the code. Extensions that only enable existing options or parameters will not receive full credit.
• For projects, you may use LLM to help with ideation, debugging, and code generation. However, you must clearly document any use of LLM in your write-ups. You are responsible for verifying the correctness and appropriateness of any content generated by LLM.
• Plagiarism in any submitted assignments is strictly prohibited. There are serious consequences. All academic integrity violations are reported to the university. Please consult the University Guidelines on Academic Integrity.
  • First violation: 0% on the assignment.
  • Second violation: Failure in the course and possible disciplinary actions from the university.

Accommodations for Students with Disabilities

If you have a disability for which you are or may be requesting an accommodation, you are encouraged to contact both your instructor and Disability Resources and Services (DRS), 140 William Pitt Union, (412) 648-7890, drsrecep@pitt.edu, (412) 228-5347 for P3 ASL users, as early as possible in the term. DRS will verify your disability and determine reasonable accommodations for this course.

Statement on Student Wellness

As a student, you may experience a range of challenges that can interfere with learning, such as strained relationships, increased anxiety, substance use, feeling down, difficulty concentrating and/or lack of motivation. These mental health concerns or stressful events may diminish your academic performance and/or reduce your ability to participate in daily activities. Pitt services are available, and participation in services does work. You can learn more about confidential mental health services available on campus here. Support is always available (24/7) from University Counseling Center: 412-648-7930.