Syllabus
Instructor
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.
Prerequsisites
CSCI E-50 (or CS50x) or at least one year of experience with Python.
Expectations
You are expected to
- watch all lectures,
- implement seven projects, and
- submit seven quizzes.
Grades
Final grades are determined using the following weights:
| Projects | 70% |
| Quizzes | 15% |
| Test | 15% |
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.
Lectures
| date | lecture | topics | |
|---|---|---|---|
| Lecture 0 | 1/25 | Search | graph search, heuristic search, adversarial search, alpha-beta pruning |
| Lecture 1 | 2/8 | Knowledge | knowledge representation, propositional logic, inference, resolution, first-order logic |
| Lecture 2 | 2/22 | Uncertainty | probability, random variables, probabilistic inference, Bayesian Networks, Markov Models |
| Lecture 3 | 3/8 | Optimization | local search, hill climbing, constraint satisfaction, backtracking search |
| Lecture 4 | 3/29 | Learning | classification, regression, super vector machines, reinforcement learning, clustering |
| Lecture 5 | 4/12 | Neural Networks | feed-forward networks, backpropagation, convolutional networks, recurrent networks |
| Lecture 6 | 4/26 | Language | context-free grammar, n-gram models, Naive Bayes, tf-idf, word2vec |
Sections
Lectures are supplemented by sections led by the teaching fellows. A schedule will be posted on the course’s website.
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
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.
Test
The test is opportunity to synthesize concepts across weeks and solve new problems based on lessons learned. The test is open-book: you may use any and all non-human resources during the test, 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 |
|---|---|
| Tue 5/11 | 20210515T235900-0400 |
Lateness Policy
For each minute that a quiz, project, or portion thereof is turned in late, the course will impose a 0.1% deduction on your grade for that assessment. (Therefore, once something is 16 hours and 40 minutes late it will earn no credit at all.) Late work will not be accepted for the test.
Extension Policy
Once during the term you may grant yourself a 3-day (72-hour) extension on a project. That extension cannot be apportioned among multiple projects or be applied to any of the quizzes or the test. 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.
The course otherwise does not allow for extensions of any kind. 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. Extensions that are only requested after a project’s deadline, even via the above form, will not be considered at all. 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
The 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 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 only to the extent prescribed by its specification, with approval from the course heads.
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.
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.
Reasonable
- Communicating with classmates about projects in English (or some other spoken language), and properly citing those discussions.
- Discussing the course’s material with others in order to understand it better.
- Helping a classmate identify a bug in their code at office hours, elsewhere, or even online, as by viewing, compiling, or running their code after you have submitted that portion of the project yourself. Add a citation to your own code of the help you provided and resubmit.
- 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 assigned problems and that you cite the lines’ origins.
- Reviewing past semesters’ tests and quizzes and solutions thereto.
- 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, provided you properly cite the help.
- Submitting the same or similar work to this course that you have submitted previously to this course, CS50 AP, or CS50x.
- Turning to the course’s heads for help or receiving help from the course’s heads during the quizzes or test.
- 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 or your own final project.
- 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 problem prior to its deadline.
- Accessing or attempting to access, without permission, an account not your own.
- Asking a classmate to see their solution to a project before its deadline.
- Discovering but failing to disclose to the course’s heads bugs in the course’s software that affect scores.
- 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.
- Looking at another individual’s work during the quizzes or test.
- Manipulating or attempting to manipulate scores artificially, as by exploiting bugs or formulas in the course’s software.
- Paying or offering to pay an individual for work that you may submit as (part of) your own.
- Providing or making available solutions to projects to individuals who might take this course in the future.
- Searching for or soliciting outright solutions to projects online or elsewhere.
- Splitting a 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.
- Turning to humans (besides the course’s heads) for help or receiving help from humans (besides the course’s heads) during the quizzes or test.
- Viewing another’s solution to a project’s problem and basing your own solution on it.
- Viewing the solution to a lab before trying to solve it yourself.