Layer 4

Layer 5

Layer 6

Layer 7

Net Output



Explain ⇓

Live Demo: Sketches to Photos

The live demo utilizes a Neural Network to synthesis photos with face sketches, which is helpful for various applications, e.g., identifying the suspect. The Neural Network in this example is regressing pixel values live in your browser based on ConvNetJS, a JavaScript based ConvNet library. It takes a pixel of a sketch and transforms it through a series of functions into RGB values as the output. The transformed representations in this visualization can be losely thought of as the activations of the neurons along the way. The Sketch-Photo pairs are from the CUHK Face Sketch Database (CUFS). By the end of the class, you will know exactly what all these numbers mean.

The First CUHK Deep Learning Symposium | Grand Final Project Presentation | Official Flyer

What's this about?
The final project presentation is carried out by each individual student reflecting their outcome after the course. The topic covers a wide span from computer vision, speech recognition, NLP to various applications, with a focus on applying the deep learning knowledge to specific research areas. We welcome walk-in audience!

Proposal -> Working on the project -> Initial submission -> Two review comments -> Final submission and Presentation


Teaching Assistants

Head TA

TAs for Final Project only

Best way to reach us regarding the course:

Course Description

This course provides an introduction to deep learning. Students taking this course will learn the theories, models, algorithms, implementation and recent progress of deep learning, and obtain empirical experience on training deep neural networks. The course starts with machine learning basics and some classical deep models, followed by optimization techniques for training deep neural networks, implementation of large-scale deep learning, multi-task deep learning, transferred deep learning, recurrent neural networks, applications of deep learning to computer vision and speech recognition, and understanding why deep learning works. The students are expected to have some basic background knowledge on calculus, linear algebra, probability, statistics and random process as a prerequisite. The course offered in Spring 2017 features:
  • The latest developments in deep learning, e.g., deep reinforcement learning, GAN, RNN with language models, ResNet and so on.
  • Hands on experience with the optimization of deep learning, using popular DL toolkits (for example, Torch, Caffe, Tensorflow).
  • Two invited guest speakers whose work will shed some light on the course and inspire us.
      Mar 31 (in conjuction with tutorial session): Yuanjun Xiong (The Chinese University of Hong Kong):
      Deep Learning in Action: Implementation, Techniques, and Frameworks [slides]

Time and Venue

Term 2 (January - April, 2017)
  • Tuesday, 14:30-15:15
    LT, Basic Medicine Science Building (map)
  • Thursday, 14:30-16:15
    L4, Science Center (map)
  • Friday, 16:30-17:30
    703, ERB (Engineering Bldg. next to SHB)

Office Hours

Xiaogang: Appointment by email, SHB 415

Mon. 14:30 - 16:30 in SHB 304 with Tong Xiao
Wed. 10:00 - 12:00 in SHB 301 with Hongyang Li
Fri. 9:30 - 11:30 in SHB 304 with Wei Yang

Grading Policy

Assignments: 30%
Two quizzes: 30%
Final Project: 40%


Our Twitter account: @dl_cuhk
WeChat official account:

WeChat discussion.
(For course attendants only, registered or sit-in)
Scan the QR code below in WeChat! :)

Assignment Details

See the Assignment Page for more details.

Final Project Details

See the Project Page for more details.


I am a student outside the EE department, can I register in the class?
Yes, you are welcome to register. For graduate students outside our EE department, you can fill in this form and ask approval from both your supervisor and the course instructor during the add/drop period.
Is this course hard for undergrad students?
The course is designed for senior undergrad and graduate students. It is not for the faint of heart. However, we will show lots of interesting cases and hands-on experience about deep learning models. Some part of the lectures requite calculus and linear algebra, but we will walk you through those knowledge. We think for undergrads, you will learn a lot at the end of the course through lectures, tutorials and the final project.
I have a question about the class. What is the best way to reach the course staff?
Course attendants please use the WeChat group discussion (link above), so that other students may benefit from your questions and our answers. If you have a personal matter regarding the course, email us at the class mailing list
Will I get charged using the Amazon EC2 service?
The final project and some tutorials will involve some GPU implementation. For those registered students who do not have the resource, we recommend using Amazon EC2 service, which provides a GPU-equipped server environment. Details will be covered at the tutorial. At the end of this course, we will cover some of your cost with the invoices. The maximum amount we can reimburse to you is 20 USD/person.
Can I audit or sit in?
In general we are very open to sitting-in guests. Out of courtesy, we would appreciate that you first email us or talk to the instructor after the first class you attend. If the class is too full and we're running out of space, we would ask that you please allow registered students to attend.
Can I work in groups for the Final Project?
No. The final project is done individually and details will be announced later.

Past Contributors

We sincerely thank all the contributors who made great efforts in supporting this course:
Prof. Wanli Ouyang, Prof. Hongsheng Li
Dr. Xingyu Zeng, Dr. Zhe Wang