Syllabus
Instructor
Head Teaching Fellow
Doug Lloyd
lloyd@cs50.harvard.edu
Description
This course explores the concepts and algorithms at the foundation of modern artificial intelligence, diving into the ideas that give rise to technologies like game-playing engines, handwriting recognition, and machine translation. Through hands-on projects, students gain exposure to the theory behind graph search algorithms, classification, optimization, reinforcement learning, and other topics in artificial intelligence and machine learning as they incorporate them into their own Python programs. By course’s end, students emerge with experience in libraries for machine learning as well as knowledge of artificial intelligence principles that enable them to design intelligent systems of their own.
Prerequisites
CSCI E-50 (or CS50x) or at least one year of experience with Python.
Expectations
You are expected to
- watch seven lectures,
- attend seven sections,
- submit seven quizzes, and
- implement seven projects.
Grades
Final grades are determined using the following weights:
| Projects | 70% |
| Quizzes | 20% |
| Section attendance | 10% |
Scores are normalized across teaching fellows at term’s end, so mid-semester comparisons among students of scores are not reliable indicators of standing.
Projects will be graded on the basis of correctness, design, and style, with each project’s overall score computed as 3 × correctness + 2 × design + 1 × style.
- Correctness refers to the extent to which your code is consistent with the project’s specifications and free of bugs.
- Design refers to the extent to which your code is written well (i.e., efficiently, elegantly, and logically).
- Style refers to the extent to which your code is readable (i.e., clear, consistent, commented, indented, with variables aptly named). This includes, but is not limited to, adherence to Python’s style guide, which you can verify using
pycodestyle.
For Project 0, only the axis of correctness will be evaluated.
Lectures
Note: lecture topics are subject to change.
| date | lecture | topics | |
|---|---|---|---|
| Lecture 0 | Tue 6/211 | Search | graph search, heuristic search, adversarial search, alpha-beta pruning |
| Lecture 1 | Mon 6/27 | Knowledge | knowledge representation, propositional logic, inference, resolution, first-order logic |
| Lecture 2 | Tue 7/51 | Uncertainty | probability, random variables, probabilistic inference, Bayesian Networks, Markov Models |
| Lecture 3 | Mon 7/11 | Optimization | local search, hill climbing, constraint satisfaction, backtracking search |
| Lecture 4 | Mon 7/18 | Learning | classification, regression, support vector machines, reinforcement learning, clustering |
| Lecture 5 | Mon 7/25 | Neural Networks | feed-forward networks, backpropagation, convolutional networks, recurrent networks |
| Lecture 6 | Fri 7/29 | Language | context-free grammar, n-gram models, Naive Bayes, tf-idf, word2vec |
1 Mon 6/20 and Mon 7/4 are university holidays, and lectures will therefore be released on those Tuesdays instead.
Sections
Lectures are supplemented by 60 to 90-minute sections led by the teaching fellows. Sections are an opportunity to discuss the course’s material, ask questions, and explore related material. Students are required to attend, live and with webcam and audio enabled, one section per week unless granted an exception in writing by the course’s head teaching fellow before the start of the term.
Office Hours
Office hours are opportunities for guidance and feedback from the staff on projects as well as for discussion of the course’s material more generally. A schedule will be posted on the course’s website.
Projects
| released | due | |
|---|---|---|
| Project 0 | Tue 6/211 | 2022-06-26T23:59:00-04:00 |
| Project 1 | Mon 6/27 | 2022-07-03T23:59:00-04:00 |
| Project 2 | Tue 7/51 | 2022-07-10T23:59:00-04:00 |
| Project 3 | Mon 7/11 | 2022-07-17T23:59:00-04:00 |
| Project 4 | Mon 7/18 | 2022-07-24T23:59:00-04:00 |
| Project 5 | Mon 7/25 | 2022-07-31T23:59:00-04:00 |
| Project 6 | Fri 7/29 | 2022-08-05T23:59:00-04:00 |
1 Mon 6/20 and Mon 7/4 are university holidays, and projects will therefore be released on those Tuesdays instead.
Quizzes
Quizzes are short assignments associated with each lecture that allow you to apply each week’s concepts. Each quiz is open-book: you may use any and all non-human resources during a quiz, but the only humans to whom you may turn for help or from whom you may receive help are the course’s heads.
| released | due | |
|---|---|---|
| Quiz 0 | Tue 6/211 | 2022-06-23T23:59:00-04:00 |
| Quiz 1 | Mon 6/27 | 2022-06-30T23:59:00-04:00 |
| Quiz 2 | Tue 7/51 | 2022-07-07T23:59:00-04:00 |
| Quiz 3 | Mon 7/11 | 2022-07-14T23:59:00-04:00 |
| Quiz 4 | Mon 7/18 | 2022-07-21T23:59:00-04:00 |
| Quiz 5 | Mon 7/25 | 2022-07-28T23:59:00-04:00 |
| Quiz 6 | Fri 7/29 | 2022-08-02T23:59:00-04:00 |
1 Mon 6/20 and Mon 7/4 are university holidays, and quizzes will therefore be released on those Tuesdays instead.
Lateness Policy
For each minute that an assessment is turned in late, the course will impose a 0.1% deduction on your grade for that assessment. (Therefore, once an assessment is 16 hours and 40 minutes late it will earn no credit at all.) Late work will not be accepted for Project 6.
Extension Policy
Once during the term you may grant yourself a 2-day (48-hour) extension. That extension cannot be apportioned among multiple projects, any quizzes, or to Project 6 at all. To grant yourself this extension, submit this form by the project’s deadline. No other action or confirmation from the course heads is required. If you try to submit the form multiple times, subsequent submissions will be automatically ignored unless you write to the course staff to cancel an earlier submission (and its corresponding extension, if it was granted).
The course otherwise does not allow for extensions on its assignments. Late submissions are only allowed on Gradescope to accommodate students who have received extensions, or to be accepted for reduced credit pursuant to the above Lateness Policy. The deadlines listed in the syllabus, above, should be considered the generally applicable deadlines.
Exceptions to this policy will be considered only (a) in situations of documented medical or family emergency, or (b) if the request comes to the course directly from your Extension School academic adviser, if you are a degree candidate. In these situations, communication with the course staff is paramount. The course rarely grants extensions retroactively, and so it is imperative you be in touch about your need for an extension promptly. The only individuals authorized to grant extensions are the instructor and the head teaching fellow.
Accessibility
The Accessibility Services Office (ASO) is available to support all students who require accommodations due to disabling conditions; all such accommodations must be approved and coordinated by the ASO. If you require accommodations, please contact the ASO at 617-998-9640, or by email at accessibility@extension.harvard.edu.
Academic Honesty
This course’s philosophy on academic honesty is best stated as “be reasonable.” The course recognizes that interactions with classmates and others can facilitate mastery of the course’s material. However, there remains a line between enlisting the help of another and submitting the work of another. This policy characterizes both sides of that line.
The essence of all work that you submit to this course must be your own. Collaboration on assigned projects is not permitted except to the extent that you may ask classmates and others for help so long as that help does not reduce to another doing your work for you. Generally speaking, when asking for help, you may show your code to others, but you may not view theirs, so long as you and they respect this policy’s other constraints. Collaboration on the course’s final project is permitted to the extent prescribed by its specification.
Below are rules of thumb that (inexhaustively) characterize acts that the course considers reasonable and not reasonable. If in doubt as to whether some act is reasonable, do not commit it until you solicit and receive approval in writing from the course’s heads. Acts considered not reasonable by the course are handled harshly. If the course refers some matter for disciplinary action and the outcome is punitive, the course reserves the right to impose local sanctions on top of that outcome that may include an unsatisfactory or failing grade for work submitted or for the course itself. The course ordinarily recommends exclusion (i.e., required withdrawal) from the course itself.
Regret clause. If you commit some act that is not reasonable but bring it to the attention of the course’s heads within 72 hours, the course may impose local sanctions that may include an unsatisfactory or failing grade for work submitted, but the course will not refer the matter for further disciplinary action except in cases of repeated acts.
Reasonable
- Communicating with classmates about projects in English (or some other spoken language).
- Discussing the course’s material with others in order to understand it better.
- Helping a classmate identify a bug in his or her code at office hours, elsewhere, or even online, as by viewing, compiling, or running his or her code, even on your own computer.
- Incorporating a few lines of code that you find online or elsewhere into your own code, provided that those lines are not themselves solutions to projects and that you cite the lines’ origins.
- Sending or showing code that you’ve written to someone, possibly a classmate, so that he or she might help you identify and fix a bug.
- Sharing a few lines of your own code online so that others might help you identify and fix a bug.
- Turning to the web or elsewhere for instruction beyond the course’s own, for references, and for solutions to technical difficulties, but not for outright solutions to projects.
- Whiteboarding solutions to projects with others using diagrams or pseudocode but not actual code.
- Working with (and even paying) a tutor to help you with the course, provided the tutor does not do your work for you.
Not Reasonable
- Accessing a solution to some project prior to (re-)submitting your own.
- Asking a classmate to see his or her solution to a project before (re-)submitting your own.
- Decompiling, deobfuscating, or disassembling the staff’s solutions to projects.
- Failing to cite (as with comments) the origins of code or techniques that you discover outside of the course’s own lessons and integrate into your own work, even while respecting this policy’s other constraints.
- Giving or showing to a classmate a solution to a project when it is he or she, and not you, who is struggling to solve it.
- Paying or offering to pay an individual for work that you may submit as (part of) your own.
- Searching for or soliciting outright solutions to projects online or elsewhere.
- Splitting an assigned project’s workload with another individual and combining your work.
- Submitting (after possibly modifying) the work of another individual beyond the few lines allowed herein.
- Submitting the same or similar work to this course that you have submitted or will submit to another.
- Submitting work to this course that you intend to use outside of the course (e.g., for a job) without prior approval from the course’s heads.
- Using AI-based software that suggests or completes lines of code.
- Viewing another’s solution to a project and basing your own solution on it.
Acknowledgement and Authorization
Harvard plans to record audio, photos, and video of Computer Science 50 (CS50) lectures, sections, office hours, seminars, and other events and activities related to CS50 (the “Recordings”), with the aims of making the content of the course more widely available and contributing to public understanding of innovative learning (the “Projects”). As part of the Projects, the Recordings, or edited versions of them, may be made available to other Harvard students, to students at other educational institutions, and to the broader public via edX, the Internet, television, theatrical distribution, digital media, or other means. One of the ways it is expected that the Recordings, or edited versions of them, will be made publicly available is under a Creative Commons Attribution-NonCommercial-ShareAlike (CC BY-NC-SA) license. Another example is that Harvard may make and disseminate montages of “memories” from the class with images from the Recordings. The Recordings also may be used to make other derivative works in the future. Students may elect not to appear in photos and video used in the Projects and may still participate fully in CS50.
To attend CS50, you will need to sign online an Acknowledgement and Authorization in the following form:
I understand and agree that, if I do not wish any photos or video of me to be used as part of the Projects:
- If I am participating in CS50 in a classroom or other course location, I should sit in the designated “no-film” zone of the classroom or location, and should not walk in the field of view of the cameras.
- If I am participating in CS50 online, I should turn off my own camera and should not display a photo of myself. In addition, if I do not wish my real name to be displayed when I speak and my voice is recorded, I should select a pseudonymous user name in Zoom (or other online service). If I select a pseudonymous user name, I will inform the instructor, so the instructor knows who I am.
I understand that I am free not to be included in the Projects’ photos and video in this way, and that this will not affect my grade or my ability to participate in course activities.
Unless I exclude myself from the Projects’ photos and video as described above and take any other steps outlined by the instructor to avoid being filmed, I authorize Harvard and its designees to make and use Recordings of my participation in CS50 and activities related to CS50. I understand and agree that the Recordings may include my image, name, and voice. I also understand and agree that, even if I opt out of the Projects’ photos and video and choose a pseudonymous user name, my voice will be recorded if I am participating online, and may be picked up by microphones outside the “no-film” zone if I am in a CS50 classroom or other location, and my spoken name also may be included in the Recordings. If the class is online, I may participate instead via chat messages, which will not be included in the Recordings.
I understand and agree that Harvard and its designees will have the irrevocable, worldwide right to make, edit, modify, copy, publish, transmit, distribute, sell, publicly display, publicly perform, and otherwise use and make available the Recordings and any other works that may be derived from those Recordings, in any manner or medium now known or later invented, in connection with the Projects, and to authorize others to do so as well. I hereby transfer to Harvard any rights, including copyrights, I may have in the Recordings that Harvard makes. I will remain free to use and disseminate any ideas, remarks, or other material that I may contribute to course discussions.
I acknowledge and agree that I will not be entitled to any payment, now or in the future, in connection with the Recordings or any works derived from them. This Acknowledgment and Authorization is a binding agreement, and is signed as a document under seal governed by the laws of the Commonwealth of Massachusetts.
Unless you exclude yourself as described in the Acknowledgment and Authorization, you are agreeing, by attending CS50, that your participation in CS50 and related activities may be recorded and used by Harvard in connection with the Projects without further obligation or liability to you, even if you do not sign any authorization.
If you have any questions about the above, contact recordings@cs50.harvard.edu.