DEEP Learning



Class overview

This course covers the fundamentals of deep neural networks. We introduce multi-layer perceptrons, back-propagation, and automatic differentiation. We will also discuss Convolutional Neural Networks, Recurrent Neural Networks, Graph Neural Networks, and Generative Adversarial Networks. In this course, you will learn the foundations of Deep Learning, understand how to build deep neural networks, and learn how to participate in machine learning competitions.

Lecturer: Qi (Rose) Yu (roseyu@ucsd.edu)

  • TA: Rui (Ray) Wang (ruw020@ucsd.edu), Mayank Sharan (msharan@ucsd.edu), Zheng Ding (zhding@ucsd.edu)

  • Lecture Time: 3:30 pm - 4:50 pm PT, Tuesday, Thursday

  • Discussion Time: 5 - 5:50 pm PT, Wednesday, Center Hall 214

  • Office Hour:

    1. Rose Yu | 4:00 pm - 4:50 pm | Monday |EBU3B 3208

    2. Zheng Ding | 10:00 am - 10:50 am | Tuesday |EBU3B B250A

    3. Mayank Sharan | 5:00 pm - 5:50 am | Thursday |EBU3B B260A

    4. Rui Wang |10:00 am - 10:50 am | Friday |EBU3B B250A

  • Location: Waren West

  • Canvas: https://canvas.ucsd.edu/courses/35488

  • Piazza: piazza.com/ucsd/spring2022/151b

Syllabus

Week 1 (Mar 28) Introduction and machine learning recap HW 1 release

Week 2 (Apr 4th) Multi-layer perceptron

Week 3 (Apr 11th) Convolutional neural network HW 2 release

Week 4 (Apr 18th) Recurrent neural network

Week 5 (Apr 25th) Deep learning implementation

Week 6 (May 2nd) Mid-term week

Week 7 (May 9th) Deep learning theory

Week 8 (May 16th) Graph neural network Milestone report due

Week 9 (May 23rd) Generative adversarial network

Week 10 (May 30 th) Presentation week Final report due

Lectures

Class Assessment

  • 30 % homework (15% x 2)

  • 25 % Mid-term exam

  • 40 % Kaggle competition

    • 5 % milestone report

    • 15 % final report

    • 10 % final presentation

    • 10 % competition ranking

  • 5 % class participation

Resources

FAQ

Q: What are the pre-requisites?

  • (MATH 31BH or MATH 20C) and (ECON 120A or ECE 109 or CSE 103 or MATH 181A or MATH 183, MATH 170A);

  • Proficiency in Python.

Q: Can first year undergraduates take this course?

  • Restricted to students with sophomore, junior, or senior standing within the CS25, CS26, CS27, CS28, EC26, and DS25 majors.

  • All other students will be allowed as space permits.

About me

My Chinese name is Qi Yu. That is also the instructor's name in the registrar's office. I publish under the name Rose Yu. You can learn more about my research at my personal website.