Foundations of AI

Northeastern University Khoury College of Computer Sciences

Fall 2024

Instructor: Rasika Bhalerao

r.bhalerao@northeastern.edu

Lectures:

Mondays and Wednesdays in the Aaron Art Center 120

Professor Rasika’s Office Hours:

Mondays and Wednesdays 5:30 - 8:00pm in CPM 200

TA: Jonathan Tarun Rajasekaran

rajasekaran.j@northeastern.edu

Jonathan’s office hours:

Wednesdays 11-12 and Fridays 6-7 on Zoom

Schedule:

Week	Monday	Wednesday	Assignment Due
1		Sept 4 Introduction, Python, Linear algebra
2	Sept 9 Probability, Ethics	Sept 11 Supervised learning
3	Sept 16 Supervised learning	Sept 18 Deep learning	HW1 (Intro review): Sept 16
4	Sept 23 Deep learning	Sept 25 Deep learning	HW2 (Supervised learning): Sept 25
5	Sept 30 Search algorithms	Oct 2 Search algorithms
6	Oct 7 Markov Decision Processes and Reinforcement Learning	Oct 9 Reinforcement learning and Markov Networks	HW3 (Search algorithms): Oct 7, Project statement of interest: Oct 9
7	(Skipped)	Oct 16 Bayesian and Markov networks	HW4 (Reinforcement learning): Oct 21
8	Oct 21 Adversarial games and Minimax	Oct 23 Catch-up Day	HW5 (Hidden Markov Models): Oct 23
9	Oct 28 Constraint satisfaction problems	Oct 30 Natural language processing	HW6 (Minimax): Oct 28
10	Nov 4 Natural language processing	Nov 6 Unsupervised learning and feature engineering	Project proposal: Nov 4
11	(Skipped)	Nov 13 Large language models
12	Nov 18 Special topic presentations	Nov 20 Special topic presentations	HW7 (Unsupervised learning): Nov 18
13	Nov 25 Special topic presentations	(Skipped)	Project checkpoint: Nov 25
14	Dec 2 Ethics	Dec 4 Ethics	HW8 (NLP): Dec 2
15	Dec 9 Final presentations	Dec 11 Final presentations	Final project due: Dec 11

This course will provide a broad, general introduction to many topics in AI. We’ll start by briefly reviewing linear algebra, probability, and ethics, and then visit a large number of topics including supervised machine learning, deep learning, search algorithms, Markov decision processes, reinforcement machine learning, adversarial games, Bayesian networks, unsupervised machine learning, and NLP (finishing up with ChatGPT). Students will also get to select a topic and study it in more depth.

The course will cover basic implementations and advanced libraries in Python. There will be (almost) weekly assignments, a group seminar presentation, and a final project including a programming component, a written report, and a presentation.

Learning Objectives:

A broadened understanding of how AI affects the world
A solid understanding of the basic concepts of artificial intelligence (AI)
Hands-on implementation of basic algorithms in AI
Comfort looking up and using existing AI libraries
Familiarity with the challenges of AI
Build supervised learning models and analyze their challenges
Understand what deep learning is and how it can be used
Define search problems and the differences between them
Analyze Markov decision processes and their applications
Develop reinforcement learning models
Explore variable-based models such as Constraint Satisfaction Problems, Markov Networks, and Bayesian Networks
Understand large language models and the fundamentals of NLP

Resources

Textbook

There is no required textbook for this course. If you would like to pursue more advanced topics or get another perspective on the material, here are some resources:

Russell and Norvig. Artificial Intelligence: A Modern Approach. (A classic, comprehensive reference)
Koller and Friedman. Probabilistic Graphical Models. (Factor graphs and Bayesian networks)
Sutton and Barto. Reinforcement Learning: An Introduction. (Markov decision processes and reinforcement learning, free online)
Hastie, Tibshirani, and Friedman. The Elements of Statistical Learning. (Machine learning from a rigorous statistical perspective, free online)
Tsang. Foundations of Constraint Satisfaction. (Constraint satisfaction problems, free online)

Some of these books use different notation and terminology than what we use in this course, so it may may take some effort to make understand at first.

Other resources:

Lecture slides (and assignments) will be linked in the schedule above
Microsoft Teams will be used for virtual office hours, one-on-one meetings, and quick messaging
Canvas will be used to collect grades and send announcements
Gradescope will be used for assignment submission

Grades

15% In-class assignments
40% ~ weekly homework assignments
10% Special topic presentation
35% Final project
- 2% Statement of interest
- 5% Proposal
- 8% Checkpoint draft
- 10% Presentation
- 10% Final paper

Final grades will be assigned based on the overall percentage calculated using the weightings listed above (no curving). The minimum overall percentage to get each letter grade will be:

A: 93%
A-: 90%
B+: 87%
B: 83%
B-: 80%
C+: 77%
C: 73%
C-: 70%
D: 60%

Assignment submission and late days

Assignments will be submitted on Canvas/Gradescope.

For homework assignments, each student gets eight free, no-questions-asked late days for the term. The purpose of late days is to make the extension process fair and transparent by getting the instructors out of the extension-granting business entirely. Instead, when you need an extension, you can take one (provided you have a late day remaining).

We will keep track of your late days - you do not need to email us to use them. Each late day provides a penalty-free, additional 24-hours to submit the assignment.

Only three late days may be used on any given assignment. Late days cannot be divided fractionally. Late days can only be used on individual homework projects (not group projects, presentations, or in-class assessments).

Attendance

All classes are on ground, and students should anticipate attending in person. Students who are registered for the in-person section must request permission if they need to attend class online for a small number of lectures (due to an emergency such as sickness). There will be small in-class exercises.

According to the official Northeastern University Attendance Requirements, students have the right to a limited number of excused absences, including absences due to specific university-sponsored activities, religious holidays, military deployment, and jury duty.

Respect for diversity

Classrooms full of computing students from diverse backgrounds and perspectives are crucial for us to make progress in our field.

It is my intent that diverse students will be successful in this course, that each student’s learning needs are addressed both in and out of class, and that the diversity that each student brings to this class is viewed as a resource, strength, and benefit. I expect you to feel challenged and sometimes outside of your comfort zone in this course, but it is my intent to present materials and activities that are inclusive and respectful of all persons, no matter their gender, sexual orientation, disability, age, socioeconomic status, ethnicity, race, culture, perspective, and other background characteristics. We should all strive for these principles both inside and outside of the classroom.

The course meetings are on Tuesdays. If a class meeting conflicts with your religious observances, please let me know in the first two weeks of the class so that we can make other arrangements. Northeastern University respects the religious practices of its students, faculty, and staff and is committed to ensuring that all students are able to observe their religious beliefs without academic penalty.

Class rosters are provided to each instructor with each student’s legal name. I will gladly honor your request to address you by an alternate name and/or pronoun. Please advise me of this early in the semester so that I may make appropriate changes to my records.

Twice during the semester, you will be asked to provide feedback on this course via TRACE (Teacher Rating and Course Evaluation). I use these evaluations to make this course better.

Feedback

We consider fair, prompt, and clear grading to be important, and students are encouraged to contact the appropriate instructor if they do not understand feedback or point removal.

Any requests for regrading must be submitted no more than 7 days after the feedback was released. Students should make regrade requests if they do not understand why they lost points or think they may have been misgraded according to the instructor’s rubric. They should not make regrade requests to argue that a mistake or omission of theirs should not have been penalized.

Students are expected to promptly read feedback on graded assignments. If the feedback includes a request to meet with the instructor, students may be penalized (or referred to OSCCR if there was an academic integrity issue) for not doing so.

Global Learner Support

Northeastern University’s Global Learner Support (GLS) offers “language, cultural, and academic support while promoting the development of intercultural competence and global understanding.” They offer tutoring, workshops, and much more. Visit https://gls.northeastern.edu/ Links to an external site.to learn more.

Academic accommodations

If you have a documented disability, please register with Disability Access Services (DAS) so you get the accommodations to which you are entitled. Please do this even if you are unsure whether you will need accommodations, since there may be a delay if you decide you need them later. Please do not wait until it has seriously impacted your work.

DAS works with students and faculty to provide students who qualify under the Americans With Disabilities Act with accommodations that allow them to participate fully in the activities at the university. Ordinarily, students receiving such accommodations will deliver teacher notification letters at the beginning of the semester. Students have the right to disclose or not disclose their disabilities to their instructors. For more information about the DAS, go to https://disabilityaccessservices.sites.northeastern.edu/.

Mental health issues are real and can prevent you from doing your best work. Your Khoury advisor is your primary contact for accessing University resources. You can also directly access University Health and Counseling Services.

Collaboration and academic honesty

Computer science, both academically and professionally, is a collaborative discipline. In any collaboration, however, all parties are expected to make their own contributions and to generously credit the contributions of others. In our class, therefore, collaboration on homework and programming assignments is encouraged, but you as an individual are responsible for understanding all the material in the assignment and doing your own work. Always strive to do your best, give generous credit to others, start early, and seek help early from both your professors and classmates.

The following rules are intended to help you get the most out of your education and to clarify the line between honest and dishonest work. The professor reserves the right to ask you to verbally explain the reasoning behind any answer or code that you turn in and to modify your project grade based on your answers. It is vitally important that you turn in work that is your own and follow the guidelines for academic honesty. The minimum penalty for an academic integrity violation is a zero on the assignment and a report to the Office of Student Conduct and Conflict Resolution (OSCCR).

If you have had a substantive discussion of any homework or programming solution with a classmate (or anyone else), then be sure to cite them in your report. Here are some example citations:

“I had no idea how to approach Question 3 until classmate Husky Huskington explained how I could break it down into smaller parts.”
“Joseph Aoun and I bounced ideas off each other for Question 4, although we both did our own coding.”
“I didn’t remember how to convert a string to an int, so I asked Google Bard. It also showed me how to handle an exception if the string couldn’t be converted.”

If you are unsure of what constitutes “substantive”, then ask us or err on the side of caution. You will not be penalized for working together. You must not copy answers or code by hand, electronically, or in any other manner. Another way to think about it is that you should be talking English (or another natural language) with one another, not Python.

The following rules apply to anything you hand in for a grade.

You may not copy anyone else’s code or text under any circumstances. This includes online sources.
You may not permit any other student to see any part of your assignment.
You may not permit yourself to see any part of another student’s assignment.
You may not publicly post your assignment in a chat or discussion where another student can see or copy it.
You may consult online resources as part of your course work, but you may not copy code or text from online sources, books, etc. If you get an idea of how to solve a problem from an online source or another person, include a short citation. You are not required to cite course materials (including Piazza) or help from a TA (although we are always happy to hear when a TA was helpful).
AI tools such as ChatGPT should be treated like another person. Asking it to generate code or text for you is equivalent to asking another person to generate code or text for you. The same policies that apply to collaborating with people will also apply to collaborating with AI. You may consult it about syntax, our provided code, or general approaches. You may not ask it to generate assignment solutions. Cite it if it is helpful.

The university’s academic integrity policy discusses actions regarded as violations and consequences for students, which are severe.

If you have a question about what is considered a violation of this policy, please ask an instructor.

If you feel that cheating is your only choice, please ask for help.

Other Resources

Technology Assistance

Canvas is Northeastern University’s Learning Management System (LMS). For technology issues, please call the Northeastern HELP desk (617-373-4357) or email them at help@northeastern.edu. For Canvas Help, visit https://canvas.northeastern.edu/support-and-resources/.

International Tutoring Center

The International Tutoring Center (ITC) provides current Northeastern University international and non-native English speaking students with free, comprehensive English language and academic support. The ITC includes student centered one-on-one tutoring sessions, Reading, Language and Culture, and Writing Workshops. For more information on available workshops and tutoring opportunities please visit https://cps.northeastern.edu/academic-resources/global-student-success/international-tutoring.

WeCare

WeCare is a program operated through the Office for Student Affairs. The mission is to assist students experiencing unexpected challenges to maintaining their academic progress. WeCare works with students to coordinate among university offices and to offer appropriate on and off campus referrals to support successfully resolving the issue. WeCare also provides information to faculty and staff to identify Northeastern resources and policies to help students succeed.

For more information see https://studentlife.northeastern.edu/we-care/. Call 617.373.4384 or email wecare@northeastern.edu.

Mental Health Resources

Northeastern offers Find@Northeastern, which is a “24/7 mental health support” and can be reached at 1-877-233-9477. For more information see https://www.northeastern.edu/uhcs/find-at-northeastern/. The service also makes available 5 free counseling sessions per Fall and Spring semester.

Title IX Protections and Resources

Title IX of the Education Amendments of 1972 protects individuals from sex or gender-based discrimination, including discrimination based on gender-identity, in educational programs and activities that receive federal funding.

Any NU community member who has experienced such discrimination, sexual assault, relationship violence, stalking, coercion, and/or sexual harassment, is encouraged to seek help. Confidential support and guidance can be found through University Health and Counseling Services staff and the Center for Spiritual Dialogue and Service clergy members. For reporting options and clarity on confidential and non-confidential options, please see Reporting Options.

Faculty members are considered “responsible employees” at Northeastern University, meaning they are required to report all allegations of sex or gender-based discrimination to the Title IX Coordinator. For additional information and assistance please see the Title IX page.