CS230 Deep Learning

Course Information

• The course content and deadlines for all assignments are listed in our syllabus.
• All class communication happens on Ed. For private inquiries, please make a private post on Ed.
• For longer discussions with TAs and to get help in person, we strongly encourage you to come to office hours.
• Please DO NOT reach out to the instructors’ emails or individual teaching staff’s emails. Instead, make a private Ed post to reach out to the course staff for the fastest response. You may contact the teaching staff at cs230-qa@cs.stanford.edu for any private or sensitive matters.
• If you are interested in auditing the course, fill out this form.

Course Staff

Andrew Ng
Instructor

Kian Katanforoosh
Instructor

John Cho
Course Manager

Swati Dube Batra
Course Advisor

Course Assistants

Yash Kankariya

Bassem Akoush

Logistics

All course announcements take place through the CS230 Ed forum. Please make sure to join!

Class components

CS230 has the following components:

• In-person lecture - once a week. You can access lectures by going to the “Panopto Course Videos” tab of Canvas.
• Video lectures, programming assignments, and quizzes on Coursera
• A midterm covering material from the first half of the quarter
• The final project
• Weekly TA-led sections

The flipped classroom format

CS230 follows a flipped-classroom format, every week you will have:

• In-person lectures on Tuesdays: these lectures will be a mix of advanced lectures on a specific subject that hasn’t been treated in depth in the videos or guest lectures from industry experts. You can access these lectures on Canvas, and they will also be posted afterwards as well.
• Two modules from the deeplearning.ai Deep Learning Specialization on Coursera. You will watch videos at home, solve quizzes and programming assignments hosted on online notebooks.
• TA-led sections on Fridays: Teaching Assistants will teach you hands-on tips and tricks to succeed in your projects, but also theorethical foundations of deep learning.

One module of the deeplearning.ai Deep Learning Specialization on Coursera includes:

• Lecture videos which are organized in “weeks”. You will have to watch around 10 videos (more or less 10min each) every week.
• Quizzes (≈10-30min to complete) at the end of every week to assess your understanding of the material.
• Programming assignments (≈2h per week to complete). The programming assignments will usually lead you to build concrete algorithms, you will get to see your own result after you’ve completed all the code. It’s gonna be fun! For both assignment and quizzes, follow the deadlines on the Syllabus page, not on Coursera.

Coursera Modules

A large portion of this course is delivered through pre-recorded modules on Coursera. We will cover all 5 courses in the Deep Learning Specialization by DeepLearning.AI.

Invitations and access

• You will receive a separate invitation to your @stanford.edu email for each course.
• Invitations will be sent on a rolling basis during the week following the first lecture.
• Accept each invitation on the same day you receive it. After that day, invitations will be re-sent only by request through the Google Form available on Ed.

Weekly deadlines

• Programming assignments and quizzes are built into the Coursera modules. They are due every Tuesday, 30 minutes before lecture begins.

Technical support

• For technical issues with Coursera, please start with the DeepLearning.AI community forum, where most common problems have already been discussed and solved.
• Search the forum first for an existing solution.
• If you don’t find one, report the issue to the DeepLearning.AI team, who are usually quick to respond. To get started, open the course reading titled “Join the DeepLearning.AI Forum to ask questions, get support, or share amazing ideas!” and follow its instructions.
• Our CAs are here to support your learning and deepen your understanding of the concepts, but we are not Coursera technical experts. Checking the forum first is the fastest way to get your issue resolved.

Midterm

The exam is 3 hours, pen and paper format, and attendance is mandatory. See the syllabus for the date.

Poster Session

Date, time, and location will be available on the syllabus.

• All on-campus students must attend and present in person. Attendance is mandatory.
• CGOE-only teams (no on-campus members) will submit a video presentation instead.
• Teams with at least one on-campus student must submit a poster and present in person — no make-up sessions or video substitutions are allowed.

Prerequisites

Students are expected to have the following background, and if they want, are invited to take the Workera self-assessments. An invitation to take these assessments will be given once you enroll in the class.

• Familiarity with the probability theory (CS 109 or STATS 116).
• Familiarity with basic statistics and data science.
• Familiarity with linear algebra (MATH 51).
• Knowledge of basic computer science principles and skills, at a level sufficient to write a reasonably non-trivial computer program.

Grading

Here’s more information about the class grade:

Breakdown

Below is the breakdown of the class grade:

• 45%: Final project (proposal 2%, milestone 7%, final report 30%, poster session 6%)
• 35%: Midterm
• 12%: Programming assignments
• 8%: Quizzes

Note: Programming assignments and quizzes are graded on a completion basis.

Submitting Assignments

From the Coursera sessions (accessible from the invite you receive by email), you will be able to watch videos, solve quizzes and complete programming assignments. Each quiz and programming assignment can be submitted directly from the session and will be graded by our autograders.

You will submit your project deliverables on Gradescope. You should be added to Gradescope automatically by the end of the first week. If you are not added by the first week of the course, please make a private post on Ed.

Late Days

You have 6 penalty-free late days for extenuating circumstances and anything else. They are applied automatically based on your submission time on Coursera and Gradescope.

• After your 6 late days are used, you may still submit an assignment up to 3 days late. Each additional late day deducts 2% from your final grade.
• No assignment can be accepted more than 3 days late, whether or not you have late days remaining.
• No late submissions are accepted for the final report, poster, or exams.
• Each late day applies to one assignment, per student. For example, submitting one quiz and one programming assignment a few minutes late uses 2 late days.
• In the event of any issues, please submit whatever work you have to avoid receiving a zero. We’re happy to assist with any questions you may have, but to help keep response times efficient for everyone, please review the course materials first and search on Ed before posting. Keep in mind that receiving assistance a few hours before the deadline is not always feasible.

Group work:

• OAE-granted extensions do not apply to group assignments (only to individual work).
• Late days can only be applied to a group assignment if all group members have late days available — coordinate with your team in advance, or the late penalty will apply.

OAE Accommodations

Submit a private post on Ed with your accommodation letter.

• You must request an OAE extension on Ed before the assignment is due, stating the number of extra days requested (as permitted by your letter).
• Extensions are not automatically applied — you must formally request them in advance.
• OAE extensions cannot be used for the final project report or poster/video.

Students who may need an academic accommodation based on the impact of a disability must initiate the request with the Office of Accessible Education (OAE). Professional staff will evaluate the request with required documentation, recommend reasonable accommodations, and prepare an Accommodation Letter for faculty. Students should contact the OAE as soon as possible since timely notice is needed to coordinate accommodations.

Honor code

We strongly encourage students to form study groups. Students may discuss and work on programming assignments and quizzes in groups. However, each student must write down the solutions independently, and without referring to written notes from the joint session. In other words, each student must understand the solution well enough in order to reconstruct it by him/herself. In addition, each student should submit his/her own code and mention anyone he/she collaborated with. It is also an honor code violation to copy, refer to, or look at written or code solutions from a previous year, including but not limited to: official solutions from a previous year, solutions posted online, and solutions you or someone else may have written up in a previous year. Furthermore, it is an honor code violation to post your assignment solutions online, such as on a public git repo.

The Stanford Honor Code

The Stanford Honor Code as it pertains to CS courses

Generative AI Policy: Each student is expected to submit their own work for assignments. You may use generative AI tools (i.e., Co-Pilot, ChatGPT) as you would use a human collaborator. You may not directly ask generative AI tools for answers or copy solutions, and you must acknowledge generative AI tools as collaborators. Using Generative AI tools to substantially complete an assignment or exam (e.g. by directly copying) is prohibited and will result in honor code violations. We will be doing our due diligence in reviewing assignments to enforce this policy. For more details:

Regrade Requests

For any work that is graded on Gradescope, you will be able to submit a regrade request for a specified time. Please keep in mind the following guidelines:

• A valid regrade request is one where a grader may have missed something in your answer. For example:
  • “I was marked wrong, but my answer matches that in the solutions”
  • “The grader said my algorithm doesn’t work on XXX example, but I implemented it and it does work on that example”
  • “The grader missed part of my work on a second page, which I’ve correctly tagged myself on Gradescope”
• “I disagree with the rubric” or “I feel like I deserve more partial credit” are not valid regrade requests.
• If you submit a regrade request, we reserve the right to complete a full review of your assignment, and your grade may decrease.

AI Policy

Policy on the Use of AI Tools in Assignments

Students are required to independently submit their solutions for CS230 assignments. Collaboration with generative AI tools such as Co-Pilot and ChatGPT is allowed, treating them as collaborators in the problem-solving process. However, the direct solicitation of answers or copying solutions — whether from peers or external sources — is strictly prohibited and considered a violation of the Honor Code.

Policy on the Use of AI Tools in Project Reports

You are permitted to use AI tools, such as Claude Code and Codex, for coding, debugging, research assistance, and polishing or editing your report.

Permitted Uses

You may use AI tools to assist with:

• Coding and debugging: Writing, debugging, or improving code.
• Literature and research assistance: Finding relevant papers, methods, or resources.
• Writing assistance: Improving grammar, clarity, organization, or style.
• Technical assistance: Explaining methods, suggesting baseline approaches etc.

Original Work

AI tools may assist with your writing, but they must not be used to generate the report in its entirety. The core analysis, interpretation of results, and original conclusions must be your own work.

Mandatory AI Disclosure

You must include a brief AI Disclosure section at the end of your report. This section:

• Is exempt from the report page limit.
• Must identify the AI tools used.
• Must describe the specific tasks for which each tool was used.

Author Responsibility

You are fully responsible for all content submitted in your report. Points may be deducted for irresponsible AI use, including:

• Hallucinated or fabricated citations
• Invalid or unsupported claims
• Unverified or incorrect code
• AI-generated content that has not been appropriately checked