Deep Learning

Time and Location

• Tuesday, Thursday 1:00-2:20 PM Eastern Time
• Instructor: Chen Sun (chen_sun4@brown.edu)
• Office hour: 3:30 to 5:00 PM on Tuesdays, or by appointment
• Classroom: Friedman Hall 108

In-class participation is required unless otherwise approved by the instructor.
Lectures will be recorded for asynchronous viewing.

About

Welcome to CSCI 2470! Deep Learning is a subset of machine learning methods based on artificial neural networks. It emphasizes learning representation with multiple layers (hence “deep”) of neural networks, and can be flexibly applied to diverse domains of applications, ranging from object detection, machine translation, video generation, to protein structure prediction. Our course aims to offer students the mathematical foundation and engineering skills necessary to understand, utilize, and design state-of-the-art deep learning frameworks. The field of Deep Learning research and applications is progressing at a lightning speed. In response, our course is organized with three themes: the underlying design principles shared by most modern deep learning networks, the high-level learning paradigms popularized by the success of deep learning, and several canonical neural network architectures that advance our understanding on what can be achieved by neural networks. We expect students to have taken an introductory course on machine learning, and feel comfortable with Python and object oriented programming.

Resources

• Course syllabus
• Ed
• Canvas
• Anonymous feedback form

Learning Goals

Students who complete this course will:

• Learn the fundamental math and implementation that underlie all modern deep learning systems (e.g. back-propagation and automatic differentiation).
• Know which model architectures to use for processing different types of data (e.g. images, text, actions, etc.).
• Grow hands-on experience implementing models for image understanding and language modeling applications.
• Understand the underlying technologies for user-facing deep learning applications, such as ChatGPT and Stable Diffusions.
• Be practiced in critically analyzing the potential societal impacts of deep learning applications.
• Team up and implement a practical deep learning system for a real-world application.

Grading

• 60% Assignments and Mini-Projects (Required Components)
• 30% Final Project
• 10% Extra “Bonus” Components

Academic Integrity & Collaboration Policy

Academic dishonesty will not be tolerated. This includes cheating, lying about course matters, plagiarism, or helping others commit a violation. Plagiarism includes reproducing the words of others without both the use of quotation marks and citation. Students are reminded of the obligations and expectations associated with the Brown Academic and Student Conduct Codes.
Discussion of course material with your classmates is both permitted and encouraged. However, showing, copying, or other sharing of actual code or verbatim answers to written questions is forbidden. This policy will be enforced.

Use of Generative AI

We encourage transparent, responsible usage of GenAI tools.

We largely follow the guideline issued by the university. The general guideline is to treat GenAI tools as your peer, that you may discuss conceptual questions with them (e.g., similar to the questions you would ask to TAs). We include example usage of GenAI tools in mini project 1, and you are encouraged to use them in the final project.

Transparency:

• Each graded assignment and mini project will have a “GenAI declaration form”
• You are required to upload your conversation with GenAI tools to the form, they will be manually reviewed by the course team
• The course team reserves the right to conduct conceptual reviews with students to make sure they can independently reproduce their submitted code
• Final project report should have a section describing your usage of GenAI tools

Responsible Usage:

• Below are some (non-exhaustive) examples. If you are not sure, send the instructor an email or ask on Ed.
• DOs:
  • Ask conceptual or generic debugging questions
  • Share your interesting conversations (or funny failures) with other students on Ed
  • Use GenAI tools as a building block, or to assist coding for the final project (Our expectation on the complexity of your final project will be higher for groups that use coding LLMs)
• DON’Ts:
  • Upload the handout or stencil code and ask coding LLMs to fill in the gaps
  • Use GenAI tools without submitting the corresponding declaration form
  • “Blindly” trust the tools without confirming with the course team

Diversity & Inclusion

Our intent is that this course provides a welcoming environment for all students who satisfy the prerequisites. All members of the CS community, including faculty and staff, are expected to treat one another in a professional manner. If you feel you have not been treated in a professional manner by any of the course staff, please contact either the instructor, Ugur Cetintemel (Dept. Chair), Tom Doeppner (Vice Chair) or Laura Dobler (diversity & inclusion staff member). We will take all complaints about unprofessional behavior seriously.
Brown welcomes students from all around the country and the world, and their unique perspectives enrich our learning community. To empower students whose first language is not English, an array of support is available on campus, including language and culture workshops and individual appointments. For more information, contact the English Language Learning Specialists at ellwriting@brown.edu.

Accomodations

Brown University is committed to full inclusion of all students. Please inform the instructor if you have a disability or other condition that might require accommodations or modification of any of these course procedures. You may email the instructor, come to office hours, or speak with him after class, and your confidentiality is respected. We will do whatever we can to support accommodations recommended by SEAS. For more information contact Student and Employee Accessibility Services (SEAS) at 401-863-9588 or SEAS@brown.edu. Students in need of short-term academic advice or support can contact one of the deans in the Dean of the College office.

Mental Health

Being a student can be very stressful. If you feel you are under too much pressure or there are psychological issues that are keeping you from performing well at Brown, we encourage you to contact Brown’s Counseling and Psychological Services (CAPS). They provide confidential counseling and can provide notes supporting extensions on assignments for health reasons.