DEEP Learning

Class overview

This course covers the fundamentals of deep neural networks at the undergraduate level. We introduce linear regression, multi-layer perceptrons, back-propagation, and automatic differentiation. We will also discuss Convolutional Neural Networks, Recurrent Neural Networks, and Transformers. The course will be a combination of lectures, presentations, and machine learning competitions.

Lecturer: Qi (Rose) Yu (roseyu@ucsd.edu)
TA:
- Sophia Sun (shs066@ucsd.edu)
- Lakshya LNU (llnu@ucsd.edu)
- Andrew Ghafari (aghafari@ucsd.edu)
- Arnav Parekhji (aparekhji@ucsd.edu)
Tutor:
- James Zhao (jjz005@ucsd.edu)
- Yash Shah (ynshah@ucsd.edu)
- Yunchao Yao (y8yao@ucsd.edu)
- Brooks Niu (rniu@ucsd.edu)
Lecture: 2:00 pm - 3:20 pm PT, Tuesday, Thursday PETER 110
Discussion: 2:00 pm - 2:50 pm PT, Friday, MOS 0114
Office Hour:
- Rose Yu | 5:00 pm - 6:00 pm | Monday | EBU3B 3208
- Sophia Sun | 11:00am - 12:00 pm | Friday | EBU3B B250A
- Lakshya LNU | 11:15am - 12:15 pm | Tuesday | EBU3B B250A
- Andrew Ghafari | 12:00pm - 1:00 pm | Thursday| EBU3B B250A
- Arnav Parekhji | 9:30am - 10:30am | Wednesday | Zoom: https://ucsd.zoom.us/j/7154489061
- James Zhao | 11:00am - 12:00 pm | Wednesday | EBU3B B250A
- Yash Shah | 5:00 pm - 6:00 pm | Thursday | EBU3B B240A
- Yunchao Yao | 11:00 am - 12:00 pm | Thursday | EBU3B B240A
- Brooks Niu | 1:00 pm - 2:00 pm | Wednesday | Zoom: https://ucsd.zoom.us/j/93542387707
- Daniel George |12:00pm - 1pm |Friday | Zoom: https://ucsd.zoom.us/j/7973551377
Canvas: https://canvas.ucsd.edu/courses/45095
Piazza: https://piazza.com/ucsd/spring2023/151b

Syllabus

Week 1 (April 3rd) Introduction and Background HW 1 release

Week 2 (Apr 10th) Multi-layer perceptron

Week 3 (Apr 17th) Automatic Differentiation HW 2 release

Week 4 (Apr 24th) Convolutional neural network

Week 5 (May 1st) Recurrent neural network HW3 release

Week 6 (May 8th) Mid-term week

Week 7 (May 15th) Deep learning implementation HW4 release

Week 8 (May 22nd) Attention and Transformer Milestone report due

Week 9 (May 29th) Graph neural network

Week 10 (June 5 th) Presentation week Final report due

Lectures

Lecture Slides

Latex Template

Class Assessment

40 % homework (10% x 4)
35 % Kaggle competition
- 5 % milestone report
- 10 % final report
- 10 % final presentation
- 10 % competition ranking
25 % Mid-term exam

Resources

Kaggle Competition

Competition Page

Reading Materials

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.