UCSD ECE176: Introduction to Deep Learning & Applications (Winter 2021)

Time and Location

• Lectures: Tuesday and Thursday, 2:00 pm - 3:20 pm, on Zoom.

• Office Hours:

  • Monday, 9:30 - 10:30 am, on Zoom.

  • Friday, 5:00 - 6:00 pm, on Zoom.

Instructors

• Xiaolong Wang: xiw012@ucsd.edu

• Rishabh Jangir: rjangir@ucsd.edu

• Ruihan Yang: ruy002@eng.ucsd.edu

Overview

This course covers the fundamentals in deep learning, basics in deep neural network including different network architectures (e.g., ConvNet, RNN), and the optimization algorithms for training these networks. We will have hands-on implementation course and assignments in python and PyTorch. This course will introduce the deep learning applications mostly in computer vision, and will also cover applications in robotics and sequence modeling.

Prerequisites

Students are expected to have basic background on Linear Algebra and programing skills with python. Students should have taken the following courses or courses related to them:

• MATH 18: Linear Algebra (4)

• ECE 143: Programming for Data Analysis

• MATH 31AH: Honors Linear Algebra

Requirements

The course will be taught remotely via Zoom conference meetings scheduled on Canvas. The class will be taught on live and students are expected to attend the class to interact with the instructors. The zoom class will be recorded and the recorded lecture will be uploaded to Canvas.

Students are expected to sign up on Piazza and GradeScope. Discussion and important announcements will be made on Piazza. The homework should be turned in and will be graded on GradeScope.

Grading

Grading will be based on 4 programming homework assignments, 1 final project proposal report and 1 final project. The programming assignments include programming in python and a submitting report along with the code. You can team up for the final project, each team has 1 or 2 students. For the 2-people team, each student should explicitly state what did they do in the report. Each student needs to do some coding for the final project, cannot just “do experiments”, “write reports”, “contributed ideas”. The proposal has to be a minimum of one page long. The final project proposals are due by February 4, 2021.

References

• Introduction to Deep Learning by Svetlana Lazebnik

• Convolutional Neural Networks for Visual Recognition

• Deep Learning

• Computer Vision

Collaboration and Academic Integrity

Please note that an important element of academic integrity is fully and correctly attributing any materials taken from the work of others. You are encouraged to work with other students and to discuss the assignments in general terms (e.g., “Do you understand the A* algorithm” or “What is the update equation for Value iteration?”). However, the work you turn in should be your own – you should not split parts of the assignments with other students and you should certainly not copy other students’ code or papers. All projects in this course are individual assignments. More generally, please familiarize yourself with UCSD's Code of Academic Integrity, which applies to this course. Instances of academic dishonesty will be referred to the Office of Student Conduct for adjudication.

IDEA Engineering Student Center

Please consider participating in the programs and events organized by the IDEA Engineering Student Center. The IDEA center, located just to the right of the lobby of Jacobs Hall, is a hub for student engagement, academic enrichment, personal and professional development, leadership, community involvement, and a respectful learning environment for all. The IDEA center's mission is to foster an inclusive and welcoming community, promote academic success, develop engineering leaders, and, most importantly, support your mental health and wellness needs. These opportunities can be found on the IDEA Center Facebook page and the Center web site.