Logistics
- Textbook and Design Tool
- Prerequisites
- Assignments, Tests and Final Project
- Grading
- Student Code of Conduct
Textbook and Design Tool
- Recommended readings:
- Overview paper on DNN acceleration
- Deep Learning (Adaptive Computation and Machine Learning series)
- Deep Learning: A Practitioner’s Approach, 1st Edition, By Josh Patterson and Adam Gibson
- Deep Learning for Computer Architects, by Paul Whatmough, Gu-Yeon Wei, David Brooks
Prerequisites
- Undergraduate degree in Electrical Engineering, Computer Engineering or Computer Science.
- Familiarity with Python programming language and Deep Learning libraries such as Tensorflow, Caffe, Keras, Pytorch, etc.
Assignments, Tests and Final Project
- Each student will present one paper from the list provided on Canvas. Students will present in groups of two. The presentation sessions will be listed in the schedule.
- The papers to select for presentation will be listed soon.
- We will have a few lab homework assignments as indicated on the syllabus. The deadline for the assignment submission is 11:59PM on the due date.
- There is one final class project that covers a spectrum of basic deep learning to advanced optimization schemes for efficient DL.
Grading
The final grade breakdown is as follows:
- Class Presentation: 10%
- Assignments: 40% (due date on the schedule)
- Final Project: 50% (15% presentation due on 6/8/23 and 35% report due on 6/16/23)
Student Code of Conduct
- Adherence to UCSD student code of conduct is expected in all phases of this course
- Violations will be reported to the Student Conduct Office