COMP7606B - Deep learning

Semester 2, 2020-21

Instructors
Dr. Bethany M.Y. Chan
Professor Francis Y.L. Chin
Teaching assistants
Dr. Linkai Luo
Dr. Wu Bruce Zhang
Syllabus Machine learning is a fast-growing field in computer science and deep learning is the cutting edge technology that enables machines to learn from large-scale and complex datasets. Ethical implications of deep learning and its applications will be covered and the course will focus on how deep neural networks are applied to solve a wide range of problems in areas such as natural language processing, and image processing. Other applications such as financial predictions, game playing and robotics may also be covered. Topics covered include linear and logistic regression, artificial neural networks and how to train them, recurrent neural networks, convolutional neural networks, generative models, deep reinforcement learning, and unsupervised feature learning.
Introduction by Instructor

Over the past several years, Google, Facebook and many major internet companies have invested significantly in machine learning technology, in particular, so-called “deep learning” technology using very-large- scale multi-layer neural networks, in order to enhance their services with, for example, better image searching and machine translation capabilities. With deep learning’s demonstrated great success in applications across many domains that affect our daily lives, it is important for IT professionals to acquire an understanding of how deep learning works. The module does not assume any prior knowledge in artificial intelligence or machine learning.

Special Note: This course is co-coded with DASC7606 which is for MDASC students.
Learning Outcomes
Course Learning Outcomes Relevant Programme Learning Outcome
CLO1. Able to understand deep learning concepts. PLO.4, 5, 6, 7, 14
CLO2. Able to understand the application of deep learning concepts to various problems. PLO.4, 5, 6, 7, 9, 11, 14
View Programme Learning Outcomes
Pre-requisites Knowledge of algorithms, calculus, linear algebra, and programming would be an advantage.
Compatibility Students who have obtained credits for COMP7801 in the academic year 2017-18 are not allowed to take COMP7606.
Topics covered
Course Content No. of Hours Course Learning Outcomes
1. Basic Concepts
   a. Motivation for Studying Deep Learning
   b. Linear Models: Linear Classification, Linear Regression, Logistic Regression
   c. Artificial Neural Networks: Perceptron, Feed Forward, Backpropagation, Training
   d. Introduction to TensorFlow
2. RNNs and Natural Language Processing		 15 CLO1, COL2
3. CNNs and Image Processing
4. Other topics such as:
    - Unsupervised Feature Learning,
    - Deep Generative Models,
    - Deep Reinforcement Learning		 15 CLO1, COL2
 
Assessment
Description Type Weighting * Examination Period ^ Course Learning Outcomes
2 assignments Continuous Assessment 40% - CLO1, CLO2
Written examination
 Written Examination 60% May 10 to May 29, 2021 CLO1, CLO2
* The weighting of coursework and examination marks is subject to approval
^ The exact examination date uses to be released when all enrolments are confirmed after add/drop period by the Examinations Office.  Students must oblige to the examination schedule. Students should NOT enrol in the course if they are not certain that they will be in Hong Kong during the examination period.  Absent from examination may result in failure in the course. There is no supplementary examination for all MSc curriculums in the Faculty of Engineering.
Course materials Recommended references:
  • Available from the course webpage
Session dates
Date Time Venue Remark
Session 1 19 Jan 2021 (Tue) 7:00pm - 10:00pm GH-WGW Hybrid
Session 2 26 Jan 2021 (Tue) 7:00pm - 10:00pm GH-WGW Hybrid
Session 3 2 Feb 2021 (Tue) 7:00pm - 10:00pm GH-WGW Hybrid
Session 4 9 Feb 2021 (Tue) 7:00pm - 10:00pm GH-WGW Hybrid
Session 5 23 Feb 2021 (Tue) 7:00pm - 10:00pm GH-WGW Hybrid
Session 6 2 Mar 2021 (Tue) 7:00pm - 10:00pm GH-WGW Hybrid
Session 7 23 Mar 2021 (Tue) 7:00pm - 10:00pm GH-WGW Hybrid
Session 8 30 Mar 2021 (Tue) 7:00pm - 10:00pm GH-WGW Hybrid
Session 9 13 Apr 2021 (Tue) 7:00pm - 10:00pm GH-WGW Hybrid
Session 10 20 Apr 2021 (Tue) 7:00pm - 10:00pm GH-WGW Hybrid
GH - Graduate House
Add/drop 18 January, 2021 - 1 February, 2021
Quota 60   [For MSc(CompSc) students]
30   [For MDASC students]
Back