 |
CMSC 5743 Efficient Computing of Deep Neural Networks – Fall 2021
| Lecture: | F 18:30-21:15 | WMY 506 |
| Zoom: https://cuhk.zoom.us/j/98497053271 | ||
| Instructor: | Prof. Bei Yu | byu@cse.cuhk.edu.hk |
| Course Tutors: | Yang Bai | ybai@cse.cuhk.edu.hk |
| Qi Sun | qsun@cse.cuhk.edu.hk |
Announcements
Dec. 03, 2021: HW1 & HW2 solutions are posted.
Nov. 19, 2021: Homework 3 is posted and the due date is at Dec. 16.
Nov. 05, 2021: Homework 2 due date is extended to Nov. 18.
Oct. 29, 2021: Homework 2 is posted and the due date is at Nov. 11.
Oct. 08, 2021: Homework 1 due date is extended to Oct. 21.
Oct. 08, 2021: no lecture today due to black rainstorm.
Aug. 04, 2021: Course schedule is updated – no final project but three homeworks are introduced.
May. 05, 2021: Course webpage is built up and the teaching schedule is online.
Course Requirements
Homework (30%), Lab (70%), and extra bonus.
Please submit your lab reports and homework through blackboard (link).
Schedule
| Date | Topic | Lab/Tutorial | Homework | Note |
| Sep. 10 | L01 Introduction (slides) | Lab01 PyTorch (report, code) | Due on Sep. 19 | |
| Sep. 17 | L02 Conv Speedup (slides) | Lab02 GEMM (report, code, slides) | Due on Sep. 26 | |
| Sep. 24 | L03 Pruning (slides) | OCR Model (slides) | HW 1 (pdf) | Due on Oct. 21 |
| Oct. 01 | N/A | National Day | ||
| Oct. 08 | N/A | Black Rainstorm | ||
| Oct. 15 | L04 Decomposition (slides) | Data Augmentation (slides) | HW 2 (pdf) | Due on Nov. 18 |
| Oct. 22 | L05 CUDA (slides) | Lab03 CUDA (report, code, slides) | Due on Nov. 07 | |
| Oct. 29 | N/A | no lecture | ||
| Nov. 05 | L06 Quantization (slides) | continue on CUDA | Due on Nov. 14 | |
| Nov. 12 | L07 BNN (slides) | OCR Deployment (slides) | HW 3 (pdf) | Due on Dec. 16 |
| Nov. 19 | L08 MNN (slides) | Lab04 MNN (report, slides, code) | Due on Nov. 28 | |
| Nov. 26 | L09 TVM (slides) | Lab05 TVM-1 (slides, code) | Due on Dec. 12 | |
| Dec. 03 | L10 KD (slides) | Lab06 TVM-2 (slides, code) | Due on Dec. 19 | |
| - | L11 NAS (slides) |
References
All papers mentioned in lecture slides.
Sze, Vivienne, et al., “Efficient processing of deep neural networks”, Synthesis Lectures on Computer Architecture, 2020.
Erwei Wang et al., “Deep Neural Network Approximation for Custom Hardware: Where We've Been, Where We're Going”, CSUR, 2019.
Qianru Zhang et al., “Recent Advances in Convolutional Neural Network Acceleration”, NeuroComputing, 2019.
Bing Li et al., “Running Sparse and Low-Precision Neural Network: When Algorithm Meets Hardware”, ASPDAC, 2018.
Homework Solutions
Knowledge Graph
 |