CS 462: Introduction to Deep Learning (Fall 2024)

Course Information


Instructor: Hao Wang
Email: hogue.wang@rutgers.edu
Office: CBIM 008
TA: Xinxi Zhang, Liam Schramm
TA Email: xz657@scarletmail.rutgers.edu, lbs105@cs.rutgers.edu
TA Office: CBIM
Time: Tuesday, 3:50-5:10 pm
Thursday, 3:50-5:10 pm
Location: TIL-226
Recitation (Sec. 01): Monday, 7:45-8:40 pm
Location (Sec. 01): TIL-242
Recitation (Sec. 02): Tuesday, 5:55-6:50 pm
Location (Sec. 02): LSH-B269
Office Hours: Wednesday, 3:00-4:00 pm or by appointment
Please use this Zoom link.
TA Office Hours: Monday, 5:30-6:30 pm
Friday, 2:00-3:00 pm
or by appointment
Please use this Zoom link.

Mask Requirement in Class

Masks should conform to CDC guidelines: https://www.cdc.gov/coronavirus/2019-ncov/prevent-getting-sick/about-face-coverings.html


Announcements

  • TBD.

    • Course Descriptions

    In this course, we will cover the following topics in machine learning:

  • Machine learning basics
  • Deep learning architectures:
  • Multi-Layer Perceptrons (MLP)
  • Activation Functions, Backpropagation, Vanishing/Exploding Gradinent
  • Convolutional Neural Networks (CNN)
  • Modern CNN
  • (Modern) Recurrent Neural Networks (RNN)
  • Attention Operations, Transformer, BERT
  • Advanced topics on deep learning:
  • Optimization for Deep Learning
  • Deep Generative Models including VAE and GAN


    • Prerequisites

  • MATH 250 (Linear Algebra) and CS 112 (Data Structure) and [CS 206 (Intro. to Discrete Struct. II) or MATH 477 (Prob. Theory) or STATS 379 (Basic Prob. Theory)].
  • Students must be familiar with python programming. The mini-project (and most probably the course project) will be based on python. You could use your own computer, Rutgers iLab, or Google Colab to run the code.

    • Expected Work

  • 40%: 2-3 Homework Assignments
  • 60%: Course Project (Proposal, Presentation, and Report)

    • Infrastructure Requirements

  • Please visit the Rutgers Student Tech Guide page for resources available to all students. If you do not have the appropriate technology for financial reasons, please email Dean of Students deanofstudents@echo.rutgers.edu for assistance. If you are facing other financial hardships, please visit the Office of Financial Aid at https://financialaid.rutgers.edu/.

    • Computing Resources

  • Rutgers iLab Servers: https://report.cs.rutgers.edu/nagiosnotes/iLab-machines.html
  • Google Colab: https://colab.research.google.com

    • Textbooks and Materials

    There is no textbook for this course. However, the following books can be useful though as references on relevant topics:

  • Deep Learning (DL), Goodfellow, Ian and Bengio, Yoshua and Courville, Aaron, MIT Press, 2016, ISBN: 9780262035613
  • Dive into Deep Learning (https://d2l.ai/)
  • Pattern Recognition and Machine Learning (PRML), Christopher C. Bishop, Springer, 2006, ISBN: 9780387310732
  • Natural Language Processing with Distributed Representations (NLP), Kyunghyun Cho, https://arxiv.org/abs/1511.07916

    • You may also find this tuturial Deep Learning with PyTorch: A 60 Minute Blitz helpful.

    For the topic of reinforcement learning, some useful materials are:

  • Reinforcement Learning (2nd)
  • Lecture by David Silver

    • Tips and More Details on Final Projects

    Below are some tips and details.

    Team Forming: Students can form a team of at most five (recommended team size is 3-4).

    Tips for Course Project Presentation: Here are some tips that can make the project presentations smoother and more effective:

  • If the project is based on published papers, at the start of presentation you could introduce some background and details on the paper. To do this more effectively, you could look for demo videos on the Internet. Showing the demo as part of the presentation can tremendously help others understand the paper. You could also look for talks/slides on the paper available online (from YouTube or the authors’ websites). You can re-use some of the content if you feel it is helpful.
  • Pause for questions. At some points of your presentation, you could pause and ask if there are any questions.


    • Tentative Schedule

    Note that this is a tentative syllabus to give you an idea of what topics this course will cover. This syllabus is subject to change as the course progresses.

    Week Date Topic Assignment
    Machine Learning Basics
    1 Sep 3 Course Introduction and Machine Learning Basics (1a)
    1 Sep 5 Machine Learning Basics (1b)
    2 Sep 10 Machine Learning Basics (2a)
    2 Sep 12 Machine Learning Basics (2b) HW1 Release
    3 Sep 17 Linear Models (1) Reading: Warmup on PyTorch
    3 Sep 19 Linear Models (2)
    Deep Learning Architectures
    4 Sep 24 Multi-Layer Perceptrons (MLP) (1)
    4 Sep 26 Multi-Layer Perceptrons (MLP) (2)
    5 Oct 1 Convolutional Neural Networks (CNN) (1)
    5 Oct 3 Convolutional Neural Networks (CNN) (2)
    6 Oct 8 Modern CNN (1)
    6 Oct 10 Modern CNN (2) HW2 Release
    7 Oct 15 (Modern) Recurrent Neural Networks (RNN) (1)
    7 Oct 17 (Modern) Recurrent Neural Networks (RNN) (2)
    8 Oct 22 Attention Operations and Transformer (1) Reading: Ch 10 & 11 of D2L
    8 Oct 24 Attention Operations and Transformer (2)
    9 Oct 29 Transformer, BERT, and GPT (1) Optional HW3 Release
    9 Oct 31 Transformer, BERT, and GPT (2)
    Advanced Topics on Deep Learning
    10 Nov 5 Optimization for Deep Learning and Deep Generative Models - VAE (1a)
    10 Nov 7 Deep Generative Models - VAE (1b)
    11 Nov 12 Deep Generative Models - VAE (2a)
    11 Nov 14 Deep Generative Models - VAE (2b) and GAN
    Mini Conference
    12 Nov 19 Final Project Presentation (Mini Conference) I
    12 Nov 21 Final Project Presentation (Mini Conference) II
    13 Nov 26 Final Project Presentation (Mini Conference) III
    13 Nov 28 No Class (Thanksgiving Recess)
    14 Dec 3 Final Project Presentation (Mini Conference) IV
    14 Dec 5 Final Project Presentation (Mini Conference) V
    15 Dec 10 Final Project Presentation (Mini Conference) VI

    Rutgers CS Diversity and Inclusion Statement

    Rutgers Computer Science Department is committed to creating a consciously anti-racist, inclusive community that welcomes diversity in various dimensions (e.g., race, national origin, gender, sexuality, disability status, class, or religious beliefs). We will not tolerate micro-aggressions and discrimination that creates a hostile atmosphere in the class and/or threatens the well-being of our students. We will continuously strive to create a safe learning environment that allows for the open exchange of ideas while also ensuring equitable opportunities and respect for all of us. Our goal is to maintain an environment where students, staff, and faculty can contribute without the fear of ridicule or intolerant or offensive language. If you witness or experience racism, discrimination micro-aggressions, or other offensive behavior, you are encouraged to bring it to the attention to the undergraduate program director, the graduate program director, or the department chair. You can also report it to the Bias Incident Reporting System.