Artificial Intelligence (Spring 2026)

Computers are incredibly dumb. However, they can be programmed to appear incredibly clever using some fancy mathematics.
This introductory course on Artificial Intelligence covers:

  • search, planning, constraint-satisfaction problems and games
  • how to work with uncertainty in the environment
  • ML, reinforcement learning, NLP and recent developments
  • ethical questions about the use of AI


Instructor

Raj Venkat
Office: Meserve 303
r.venkatesaramani@northeastern.edu

Office Hours: Wed, 10:00 am - 12:00 pm
To request appointments outside of office hours, click here.
If you decide to swing by on a whim, and my office door is open, feel free to bug me.

Syllabus

Click here to download the syllabus.

When & Where

Lectures Richards 458
Tue & Fri, 9:50 - 11:30 am
Hurtig 130
Tue & Fri, 1:35 - 3:15 pm
Hurtig 130
Tue & Fri, 3:25 - 5:05 pm

Class Forum Campuswire (Group join code - 3161)

Student Expectations

Required Background

Students are expected to have strong programming foundations, preferably in Python 3, which will be extensively used in this course. Prior formal coursework in algorithms is advisable. We will also rely on fundamentals of linear algebra, probability, and some preliminary calculus. While these are not formal prerequisites, students without prior experience should expect to spend additional time outside of lectures/assignments to build these foundations within the first 2 weeks, with the help of provided resources.

Attendance Policies

I do not normally record attendance. However, attendance will be mandatory for the mid-term exam, the last 3 lectures of the semester before finals week, which will be devoted to in-class final project presentations, and the final exam. For exact dates, please refer to the course syllabus. Attendance is mandatory for all students on these dates; it will be recorded and will impact your grade. Please plan all your travel and other commitments accordingly. Travel plans for any of these dates that were booked prior to the start of the semester are not a valid reason to request an exemption to this policy; if such travel is unavoidable, students are advised to take this course in a later semester, when they are able to be present in Boston for the entire duration of the course. Exceptions will only be granted for genuine and unforeseen emergencies.

Rigor, Engagement & Support

The material presented in this course is inherently mathematical and often quite complex, and the best way to learn is to engage with me during lectures and take detailed notes. While I do not record attendance during the rest of the semester, students are strongly advised to regularly attend class. Past iterations of this course have shown that students who regularly attend lectures and office hours, and engage deeply with the final project, achieve positive outcomes in terms of course performance and satisfaction, as well as offers for internships/co-ops in AI/ML related roles.

In addition to being your instructor, I hope you also think of me as an advisor/mentor whom you can freely talk to for any reason[1]. I am open to questions about anything that has to do with your education, even if it does not strictly fall within the scope of the course. I strive to foster a nonjudgmental learning environment at all times, and I am never inconvenienced by a student reaching out for support.

Time Management, Grading, Regrade Requests

A college degree is as challenging as it is rewarding. You are bound to have conflicting deadlines from multiple courses and co-op related activities, but a crucial part of your learning experience is figuring out a time-management strategy that allows you to deliver on all fronts. University education also places significant emphasis on the precision of writing and a student's ability to follow all instructions, and meet broader course expectations.

Requests for extensions to submissions due to poor time management will be denied. Choosing to prioritize a different course, or co-op applications and interviews, etc. is your prerogative, but you do so with the understanding that no additional flexibility will be provided outside of course policies, except in genuine emergency situations. I also expect students to read and adhere to any provided assignment instructions, and expectations communicated through course announcements throughout the semester.

Regrade requests are intended to address potential grading errors, not to serve as an avenue for negotiation. Rubrics are designed with expected outputs and writing quality in mind, developed in close collaboration with the TA team to reflect both course standards and student perspectives. These rubrics are applied fairly and consistently across the class. While effort is valuable, it is inherently subjective and varies greatly among students. There is no way for me to evaluate effort objectively. If you believe there was an oversight in grading—such as missing points for a rubric item that your answer addressed, or if something was overlooked — please feel free to submit a regrade request.

Please note that submitting a regrade request may result in the entire question being regraded from scratch by me. While I strive for fairness and consistency, my experience often allows me to identify more nuanced mistakes that may have been overlooked during the initial grading by the TA team. As a result, a regrade could lead to an increase in your score, but it could also result in a decrease if additional errors are found. I encourage you to carefully review your submission and the rubric before deciding to request a regrade.

Late Joiners

Please note that by joining the course late, you knowingly accept the responsibility of catching up on missed material and should not expect any preferential treatment or adjustments to deadlines[2]. For any assignments due before the add deadline, you will have 5 days from your join date to submit them. For any assignments released on or after the add date, no additional extensions will be provided. You will need to work on multiple submissions in parallel if you join late.

Please stop by my office hours, or book an appointment with me, and I will be more than happy to briefly review content (provided you go over the relevant class notes first) and point you to the right resources. TA office hours will prioritize assignment-related questions over content review for late joiners.


[1] You should be aware that faculty are mandatory reporters at Northeastern. See campus resources.

[2]If you are an international student whose visa process was delayed due to recent events, please follow University guidance closely. Note that certain interactions with course material (such as submitting any assignments/quizzes on Canvas) prior to your arrival in Boston may constitute a violation of your visa status.

Textbook, Resources & Software

This course does not have a required textbook, and my course content is curated from several different sources, many of them not textbooks. However, you will find the following texts useful. Except for the first book in this list, the remaining are made freely available online by the respective authors.

Artificial Intelligence: A Modern Approach, Pearson
Artificial Intelligence 3E: Foundations of Computational Agents, Cambridge University Press, free online version
Mathematics for Machine Learning, Cambridge University Press, free online version
Dive into Deep Learning, Forthcoming at Cambridge University Press, free online version


Software

We will use Python 3 for all programming assignments. These resources may be useful: If you have limited or no Python or GitHub experience, please reach out to the TAs or the instructor early in the semester. This will enable us to work with you and provide additional guidance in a timely manner.

Slides & Readings

Topic Readings
Intro, Course Logistics, History & Vocabulary Notes: Introduction
AIMA: Ch. 1
ArtInt3E: Ch. 1
Search Notes: Search
Notes: Informed Search
AIMA: Ch. 3.1-3.6
ArtInt3E:Ch. 3.1-3.6
Informed Search Notes: Informed Search
AIMA: Ch. 3.1-3.6
ArtInt3E:Ch. 3.1-3.6
Local Search Notes: Local Search
AIMA: Ch. 4.1-4.2
ArtInt3E:Ch. 4.6-4.7
Game Playing, Adversarial Search Notes: Games and Adversarial Search
AIMA: Ch. 5
ArtInt3E:Ch. 14.1-14.3
Adversarial Search - Dr. Mark Humphrys
Constraint Satisfaction Problems Notes: Constraint Satisfaction problems
AIMA: Ch. 6
ArtInt3E:Ch. 4.1-4.3
Reasoning with probability - Expectiminimax, Markov Models Seeing Theory - A Visual Intro to Probability
A Probability Primer - Dr. Scott Bierman
Notes: Expectiminimax
Notes: Markov Models
Markov Models. Ch. 8.1-8.9 [Stats 325 - Univ of Auckland, Dr. Rachel Fewster]
Hidden Markov Models Notes: Hidden Markov Models
AIMA: Ch 14.3
Hidden Markov Models, CMU, 2017
Markov Decision Processes Notes: Markov Decision Processes
AIMA: Ch. 17
ArtInt3E:Ch. 12.5
Intro to Reinforcement Learning Notes: Reinforcement Learning
AIMA: Ch. 22
ArtInt3E:Ch. 13
Gradient Descent (no slides) Notes: Gradient Descent
ArtInt3E:Ch. 4.8
Machine Learning Notes: Machine Learning
AIMA: Ch. 19, Ch. 20
ArtInt3E:Ch. 7
ArtInt3E:Ch. 10.3
Gradient Descent for Linear Regression
Maximum Margin Classifiers
Neural Networks Notes: Neural Networks
AIMA: Ch. 21
ArtInt3E:Ch. 8
Notes: Mathematics of Neural Networks (Sec. 1, Sec. 2.1 and Sec. 2.4)
Deep Q Nets, Computer Vision, Deep RL AIMA: Ch. 22.4, 22.5
ArtInt3E:Ch. 13.9
Adversarial ML, Ethics TBA
NLP and LLMs TBA

Grading

Grades will be based on the following split over course load:

  • Group Project: 20%
    (presentation (5%), project tracking and summary sheet (5%), modular and documented code
    in GitHub repo (5%), proposal + check-in (3%), presentation attendance (2%))

  • Programming Assignments: 30%
    (PA1: 35 points, PA2 & PA3: 45 points each) - total normalized to 30%

  • Problem Sets: 20%
    (PS1: 35 points, PS2 & PS3: 45 points each) - total normalized to 20%

  • Assignment 0 + Labs: 5%
    (graded on completion)

  • Exams: 25%
    (Midterm: 10%, Final: 15%)

  • With the instructor’s permission, students have the option to substitute the group project requirement with a research-intensive evaluation worth 20%, consisting of two parts: (a) a research paper implementation and accompanying seminar-style presentation worth 15%, and (b) a viva voce - a one-on-one, whiteboard-interview-style oral examination including, but not limited to, lecture content and provided materials, worth the remaining 5%. This pathway is designed to be significantly more challenging, and will require reading broadly beyond provided course materials in preparation. This pathway is intended to serve students considering or interested in pursuing a Ph.D. in the future, but is open to anyone up for a challenge! Successfully completing the research pathway will allow me to write a very strong letter of recommendation for you, should you choose to apply to graduate programs. For more details, refer to the course syllabus, section 1.10 (ii).

    Final grades will be assigned based on the following scale (note open and closed intervals):

    A [93, 100]
    A- [90, 93)
    B+ [87, 90)
    B [82, 87)
    B- [80, 82)
    C+ [77, 80)
    C [72, 77)
    C- [70, 72)
    D+ [67, 70)
    D [62, 67)
    D- [60, 62)
    F [0, 60)
    Natural rounding will be used, i.e., percentages $\ge x.5$ get rounded up
    to the next integer, $x + 1$ (92.5 becomes 93, 92.49 does not).

Policies

Homework Submissions & Grading

  • All homework submissions and labs must be uploaded to Gradescope by 8:00 pm Eastern on the due date. Written submissions must be in PDF format, and must be typed (i.e., no scans of handwritten assignments will be accepted). Scanned figures are only permitted where explicitly specified in the assignment instructions. Any such figures must be clear and perfectly legible.
  • The use of LaTeX to typeset mathematical equations is highly encouraged, but not mandatory. Overleaf is an excellent browser-based LaTeX editor with real-time compilation capabilities. Overleaf Professional is free to all Northeastern students.
  • It is encouraged that you collaborate with your classmates to review course content, notes and other reading material. However, any such collaborations must be kept strictly conceptual, and not involve any actual assignment problems. I recommend re-using examples from lecture, or reaching out to the instructor/TAs if in doubt.
  • If you do discuss any concepts with a classmate, you must list all such collaborators on your submission. You must write all solutions by yourself, in your own words, and are strictly forbidden from sharing written solutions or code.
  • The TAs and instructors reserve the right to ask you to explain your solutions, and inability to do so may result in academic penalties (see sections below).

  • Grading : All grades will be released via Gradescope.
  • Regrade Requests : All regrade requests must be submitted within 1 week of receiving your grade. Requests for all submissions must be submitted from within Gradescope. Requests submitted via email will almost certainly be missed.

Policy on the use of Generative AI

  • For programming submissions (except assignment 0), students may use any AI tool available to them, as long as they are appropriately cited (a code comment will suffice). While the same policy applies to labs, I advise against using AI for these.
  • Students may not use generative AI to complete problem sets in any capacity. These are intended to test students' ability to demonstrate mastery of techniques learnt in the course by a) presenting sound and rigorous theoretical analysis, and b) critically analyzing code. Any indication of the use of AI tools in the written submissions will constitute a violation of academic integrity, and be subject to academic penalties (see section below).
  • The TAs and I reserve the right to refuse help with debugging code that was found online or generated by AI tools, if you cannot sufficiently explain it.
  • The use of AI solely to rephrase sentences and improve writing clarity, etc. - while an acceptable use case - makes it difficult for instructors to discern whether the entire answer was AI-generated. Therefore, if AI is used in this manner, students are required to submit an additional appendix at the end of their submission with their corresponding originally written answers. Failure to include such an appendix will be treated as an academic integrity violation.
  • The appendix is aimed only at helping me understand the usage patterns of AI tools. Points will not be taken off for using AI to improve writing when disclosed as per the policies above. Please feel free to clarify policies with me when in doubt.

Academic Integrity

  • Please familiarize yourself with Northeastern University's Academic Integrity Policy
  • Sharing or discussing assignment solutions or code in any form is strictly forbidden. Searching for solutions online is okay, but must be clearly and appropriately cited. Any conceptual discussions held with classmates must be clearly disclosed in the assignment submission by all parties.
  • Any violation of academic integrity (as outlined by all homework policies above) will result in the following penalties:
    • Academic penalties up to, and including, a grade of F for the course.
    • A report of the violation will be filed with OSCCR, where outcomes can range from warnings or academic probation to dismissal from the University.
    • International students should note that they do not have the option to withdraw from the course upon receiving an F grade due to F-1 visa credit requirements. Dismissal may cause the student to be in violation of their visa status.
  • Recognize that most violations are easily avoided by simply acknowledging any difficulties you may be having with the course and seeking help from your professor in a timely fashion. We're here to help you learn.
  • International students often report suffering from cultural shock, homesickness, and being overwhelmed by a new education system. However, cheating is never the right solution. I want to assure you that I will never be inconvenienced by a student reaching out for help, or think poorly of a student for asking me lots of questions.

    I was in your shoes not that long ago, and I am happy to talk to you about any of these issues and offer you my support and guidance. However, it is imperative that this conversation happens in the absence of an academic integrity violation. Once a violation is identified, I will have no choice but to report it in the interest of fairness.

Late Policy

  • Homework deadlines will typically be on Fridays at 8:00 pm Eastern. Students will receive an automatic extension until Sunday 8:00 pm, without penalty. Deadlines for submissions related to the final project are absolute, and no extensions will be provided for these deliverables.
  • Treat the automatic extensions to problem sets/programming assignments as a fallback for genuine emergencies - assignments in this course take a significant amount of time to complete. No office hours are offered during the extension period.
  • Requests to submit assignments after the late deadline due to last-minute difficulties will be ignored. It is your responsibility to ensure that the correct files are properly uploaded, submitted, and reflected in Gradescope well in advance of the deadline.
  • Beyond the automatic late deadline, I will not grant further extensions, except in the case of limited and verifiable emergency situations, or University and DRC-sanctioned accommodations. It is imperative that you communicate with me (or the TA team) early on when circumstances permit.
  • In case you are close to the late deadline, and feel that you will be unable to submit an assignment in time, please reach out to me. Depending on your circumstances, I may not be able to give you an extension, but I will certainly offer you the right resources to help you make the most of your assignment.
  • Do not succumb to the temptation to copy from a classmate in order to salvage your grade close to a deadline - while it may seem like an easy way out at the time, doing so will only result in a much worse, irreversible outcome for both parties.

Classroom Environment

  • Digital devices are permitted for note-taking purposes and to engage with course material such as lecture slides, or in-class activities as instructed. However, any use of laptops/tablets must not be disruptive to your classmates. No phones please.
  • To create and preserve a healthy classroom atmosphere that facilitates teaching and learning, all participants share a responsibility in creating a civil, nonjudgmental, and non-disruptive forum for the discussion of ideas. Students are expected to conduct themselves at all times in a manner that does not disrupt teaching or learning.
  • Your comments to others should be constructive and free from any harassing or disrespectful statements. You are welcome to disagree with other students and the instructor, but such disagreements need to be respectful, and based on facts, evidence and documentation (rather than prejudices and personalities).
  • The instructor reserves the right to interrupt conversations that deviate from these expectations. Repeated unprofessional or disrespectful conduct will be treated as a violation of the Code of Student Conduct.

TA Team & Office Hours

Campuswire is a Piazza alternative that we will be using as the class forum, and for online support. All course announcements will be posted on Campuswire. Please ensure you sign up at this link (Use group join code - 3161).

TAs offer a mix of in-person and online office hours. For all in-person hours (including the instructor's), simply walk in. Online office hours will be conducted using the Khoury Office Hours App and Teams. When it is your turn in the queue, the TA will reach out to you over Teams, so please keep both windows readily accessible. Please note that starting Spring 2026, you must be connected to the Northeastern University VPN to log in to the Office Hours app.

Andrei Biswas
 biswas.and
Wed & Thu, 2-4 pm
Online
Esakkivel Esakkiraja
 esakkiraja.e
Mon 2-4 pm, Fri 5-7 pm
Online
Justin Feldman
 feldman.jus
Mon 4-6 pm, Kariotis 304
Fri 5-7 pm, Online
Rishi Srikaanth
 srikaanth.r
Wed & Thu, 4-6 pm
Ryder 283
Brent Garey
 garey.b
Mon & Thu, 12-2 pm
Kariotis 304
Arzoo Jiwani
 jiwani.a
Tue 1:30-3:30 pm, Wed 12-2 pm
Online
Sabine Laurence
 laurence.s
Tue 3:30-5:30 pm, Kariotis 304
Thu, 3:30-5:30 pm, Online
Micah Marshall
 marshall.mica
Mon & Thu, 2-4 pm
Online
Haig Shirozian
 shirozian.h
Tue & Fri, 11:30 am - 1:30 pm
Kariotis 304
Grace Mackin
 mackin.g
Tue 9-11 am, Online
Thu 11 am - 1 pm, Kariotis 104
Ben Marler
 marler.b
Mon & Wed, 9-11 am
Behrakis 007


Office Hours Calendar


Campus Resources

Healthcare, Counseling, and Wellness

Your health and well-being are paramount, above any and all course deliverables. There is a wide range of support services on campus to ensure your success, and I encourage you to reach out to these resources as appropriate. If I can help connect you, please don't hesitate to reach out to me!

University Health and Counseling Services
Find@Northeastern - 24/7 Mental Health Support
WeCare
Support Groups and Workshops


Title IX

  • 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 financial assistance.
  • Northeastern’s Title IX Policy prohibits Prohibited Offenses, which are defined as sexual harassment, sexual assault, relationship or domestic violence, and stalking. The Title IX Policy applies to the entire community, including students, faculty and staff of all genders.
  • If you or someone you know has been a survivor of a Prohibited Offense, confidential support and guidance can be found through University Health and Counseling Services staff and the Center for Spiritual Dialogue and Service clergy members. By law, those employees are not required to report allegations of sex or gender-based discrimination to the University.
  • Alleged violations can be reported non-confidentially to the Title IX Coordinator within The Office for University Equity and Compliance by filling out the online Discrimination Complaint Form, emailing the OUEC (less secure) at: titleix@northeastern.edu and/or through NUPD (Emergency 617.373.3333; Non-Emergency 617.373.2121). Reporting Prohibited Offenses to NUPD does NOT commit the victim/affected party to future legal action.
  • 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. Note that faculty are mandatory reporters, but not arbiters of situations that may arise. In case of an emergency, please call 911. Please visit the Title IX webpage for a complete list of reporting options and resources both on-campus and off-campus.


Disability Accessibility Services

Students with disabilities who wish to receive academic services and/or accommodations should visit Disability Accessibility Services at 20 Dodge Hall, or call 617-373-2675. If you have not already done so, please have the accommodations letter sent to me early in the semester so that I can best serve your needs.