Syllabus
The syllabus is a living document and work-in-progress. We maintain the right to update it as appropriate.
Table of contents
Overview
- Course number
- CIS 5210 - Artificial Intelligence
- Prerequisites & recommended background knowledge
- CIS 1210 (Programming Languages and Techniques II)
- A data structures and algorithms course, plus substantial programming experience
- Instructor
- J (Jay / Joyce) Zhou
Course materials
Website
You are here!
This website will host or link to all essential materials for this course.
Canvas
Canvas contains Zoom links and recordings as appropriate for lecture, recitation, and online office hours.
Ed Discussion Board
Ed Discussion Board provides a forum for students to get support from course staff and each other. We will also use it to post course announcements (although we will try to announce these consistently across lecture and website updates as appropriate) and potentially share bonus resources.
OHQ
OHQ will be used to manage questions in virtual office hours. Please write some explanation of your question/problem and your current best understanding of an answer.
Gradescope
Gradescope is the tool we use for submitting, grading, and reviewing homework assignments and exams.
You should be able to initially access the Gradescope for the course via the Canvas sidebar. After the initial access, you should be able to log into Gradescope directly and see CIS 5210 on it.
Textbooks
There are two main books that will be referenced in this course.
Artificial Intelligence: A Modern Approach (4th edition) by Russell and Norvig.
- Primary textbook for the course.
- Note that the 4th edition adds substantial new material over the 3rd edition, so you should use the 4th edition.
- You can buy the textbook on Amazon or get it from the UPenn bookstore (digital rental costs around $40).
Speech and Language Processing (3rd ed. draft) by Jurafsky and Martin.
- Supplemental; this will be helpful in the last third of the course.
- This textbook is currently free online while the textbook authors are revising it to write their 3rd edition.
Course Components
See also the course schedule for a weekly event visualization, and the course module calendar for a breakdown of what topics we are covering over time.
Lectures
Lectures will be Monday/Wednesday/Friday from 13:45-15:30 ET (1:45pm-3:30pm). They are in David Rittenhouse Laboratory (DRLB) 4C2 and streamed & recorded over Zoom. See Canvas for Zoom access and recording links.
Attendance is not required, but encouraged if possible as it is easier to ask questions. We are happy to answer lecture-related questions on Ed from people who are following along via recordings.
We may have some special topics sessions at unusual hours; these will be held over Zoom with recordings available on Canvas.
Recitations
Weekly TA-held recitations will be held on Fridays, 8-9PM ET by default. They are streamed & partially recorded over Zoom. See Canvas for Zoom access and recording links.
Attendance is not required, but encouraged if possible as it is easier to ask questions. We are happy to answer recitation-related questions on Ed from people who are following along via recordings.
In the past, recitations were designed around helping you with the homework assignments and many students have found it useful. Things may change some this semester, but we still encourage students to participate. As with anything, you develop your skills with experience and this provides experiences for you to practice your AI familiarity (and programming skills).
Homework Assignments
There are a total of 10 programming assignments. Homework will be distributed on the course website (Assignments page) and submitted+autograded on Gradescope.
We strongly recommend implementing and testing your code locally before submitting homework assignments to Gradescope.
See Policies for further information.
Exams
There will be a midterm and a final exam, graded by course staff with grades posted to Gradescope.
For both exams: we will provide a PDF with the exam questions, and you will hand-write your responses and upload them to the relevant Gradescope assignment. We recommend you print out the PDF or otherwise get a blank sheet of paper to write your answers on, then take a picture of or scan your responses and upload the resulting image/PDF files to Gradescope.
During each exam, you may post private questions on Ed to ask any clarifying questions. Course staff will try to answer these questions quickly. We will also maintain a clarification and FAQ pinned post for the midterm that will be updated as appropriate.
Please contact us if you expect to be unable to hand-write exam responses, unable to take the exam during the open window, or encounter any other issues.
The midterm exam will be a take-home exam done via Gradescope. It will remain open from 2026/06/28 00:01 ET to 2026/06/29 23:59 ET. The exam will be open for approximately 48 hours. The exam is intended to take around 2 hours, although you are free to work on it for as little or as long as you like within the availability window as long as you submit your answers before the window closes.
The midterm scope includes everything from the beginning of the course until and including Logical Agents. If you are unsure if a topic is within scope, please ask!
The final exam will be a take-home exam done via Gradescope. It will remain open from 2026/08/07 00:01 ET to 2026/08/08 23:59 ET. The exam will be open for approximately 48 hours. The final exam is intended to take around 2 hours, although we will tell you if expected length changes. The same general policies apply.
The final exam topics will cover everything from the beginning of the course until and including Natural Language Processing. We intend to place greater emphasis on topics in the second half of the course (starting from and including Markov Decision Processes).
See Policies for further information.
Extra Credit Activities
We may offer a small amount of extra credit for activities such as bonus homework assignments, readings, etc. These will be announced over time, and we will enable hybrid and async participation in such activities as appropriate.
By default, all extra credit is due by the end of day ET on the last day of classes in the term, or by the end of day ET on the last day the final exam is open, whichever is later.
Policies
Creating a Welcoming Environment
You have a right to a learning environment that feels safe, where you are treated with respect and feel that you can contribute ideas constructively. Put another way, you have the right to an inclusive learning environment.
We want every student to feel that they have a safe and healthy learning environment, and if at any point you feel like this is not the case in any way, please let course staff know and we will see what we can do to help.
You can contact staff by making a private post on Ed, reaching out to course staff via email, talking to course staff at office hours, or scheduling a 1-on-1 with the instructor. See staff contact information on the Staff page.
Getting Help
It is very important to us that you succeed in CIS 5210. As a result, we are providing many resources to help you succeed. These include:
- Office hours held by course staff
- The Ed discussion board
- Contacting staff directly via email (see staff page)
- Scheduling a 1-on-1 meeting with the instructor (see staff page)
Please do not be afraid to ask for help if you don’t understand something. We are here to help you succeed. Additionally, some of the course staff will get lonely and bored if no one shows up to their office hours. (Showing up to office hours without any particular questions, maybe for stuff like accountability buddy purposes, is quite welcome.)
It is also very important to us that you maintain your mental wellness throughout the course. A few points are not worth losing sleep over. Folks on the course staff are open to chat, and you can always attend office hours for a non-academic conversation if necessary.
Additionally, if you are experiencing some unforeseen and extenuating circumstances, please feel free to reach out to course staff for help. Notably, the world is not in a particularly peaceful and stable condition right now! Hopefully things are relatively calm for most students, but we know things can come up in the middle of the course (whether it is directly related to school or not), and we are here to help.
Disability Services
The Student Disability Services (SDS) is a unit within the Weingarten Learning Resources Center (WLRC) dedicated to ensure equal access to all University programs, activities and services. They offer a wide range of services for students with disabilities that are individually designed and remove the need to reveal sensitive medical information to the course staff. Please submit a request if you have a medical need for extensions of exam times or assignment deadlines.
Grading & Assessment
- 70% Homework Assignments
- 10 assignments all equally weighted
- 30% Exams
- 15% for midterm 1
- 15% for midterm 2 (AKA: final exam)
- Up to 3-5% in optional extra credit
The course is not curved. Your overall score is computed as 0.3 * exam score + 0.7 * homework score. All homeworks are equally weighted.
Letter grades are computed based on your overall score. Here is an overall score threshold table from a previous offering of the course:
| Score | Grade |
|---|---|
| ≥ 97 | A+ |
| 93-97 | A |
| 90-93 | A- |
| 87-90 | B+ |
| 83-87 | B |
| 80-83 | B- |
| 75-80 | C+ |
| 70-75 | C |
| 65-70 | C- |
| 50-65 | D |
| < 50 | F |
This semester will likely follow a similar grading scale but things may change as needed (e.g. if an exam is made too hard by accident).
Late Homework Policy
Each student has 5 free “late day” tokens. Each HW assignment can be submitted at most two days late, using up to two “late day” tokens. One “day” is defined as anytime between 1 second and 24 hours after the homework deadline. You do not need to ask permission to use your late days. These will be counted when you submit later and the course staff will keep track of late days used. If a submission is late and a token is not applied to it (e.g. if a student has run out of late day tokens), then a 15% deduction will be applied for each 24 hours late. Expect no additional late day tokens to be granted.
If there are exceptional circumstances that are preventing you from getting the assignment(s) turned in on time, please reach out to the instructor as soon as you realize. From there the situation can be discussed further.
Rescheduling Exams
If you know in advance that you will be unable to take an exam, please discuss it with the instructor as soon as possible, at least 24 hours before the exam so that the reason can be verified and plans can be put in place. Make-up exams would likely take place after the initial exam.
For emergency absences, please reach out to the instructor when possible so that plans can be put in place.
Policies regarding absences for the Final Exam are covered by the University Provost; for Spring semester courses, a makeup Final Exam would be scheduled at the start of the following Fall semester. Requests for a makeup Final Exam due to reasons that could reasonably be anticipated (e.g. traveling for vacation) are unlikely to be approved.
Collaboration and Academic Misconduct
Do not collaborate with others on individual graded assignments unless it is explicitly allowed for that assignment. You can discuss homework problems with others (you must explicitly list who you discussed problems with on each homework submission), but all code must be your own independent work. You are not allowed to upload your code to publicly accessible places (like public GitHub repositories), and you are not allowed to access anyone else’s code. If you discover someone else’s code online, please report it to the course staff via a private note on Ed.
Similarly, exams must be completed on your own without help from others. For exams that are open notes or allow a “cheat sheet”, you must create the notes yourself and you are not allowed to use anyone else’s notes. You should not discuss the exam with anyone else in the course until after the scores have been released.
Generative AI Policy
We recognize the increasing prevalence of generative AI tools in a variety of applications. We acknowledge that AI can be a useful learning tool. It can help clarify ideas or help you explore related concepts. However, it is also quite capable of generating plenty of authoritative-sounding nonsense. Without some understanding of fundamental concepts and knowing how to cross-reference model output against an external non-generative-model source of information, it can be hard to tell the difference. Our goal is to help you develop a strong understanding of fundamental concepts and processes without relying on generative AI.
To this end:
- Avoid using AI to generate code or text for homework assignments, peer reviews, or content summaries.
- Do not seek AI help for quizzes, exams, or formal assessments.
- Do not present AI-generated content as your own work or without citation.
- We recognize that generative AI tools may be built-in to your working environment. If you do end up using generative AI for your work (homework, exams, or other graded materials), we require that you explicitly document how, where, and why it was used, and reflect briefly on how it affected your work and learning.
If you have questions or concerns, feel free to reach out.