COMP7801A - Topic in computer science

Semester 2, 2017-18

Dr. Bethany M.Y. Chan
Teaching assistant
Mr. Zhiming Cui
Syllabus Selected topics that are of current interest will be discussed.
Topic for 2017-18 This course will cover topics in deep learning. Topics covered include linear and logistic regression, neural networks, recurrent neural networks, convolutional neural networks, deep reinforcement learning and unsupervised feature learning. There will be an emphasis on applications of deep learning to various problems such as natural language processing, image processing, and game playing. Popular deep learning software, such as TensorFlow, will also be introduced.
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.
Learning Outcomes
Course Learning Outcomes Relevant Programme Learning Outcomes
CLO1. Able to understand deep learning technology in the context of machine learning and artificial intelligence. PLO.4, 5, 6, 7, 14
CLO2. Able to understand the application of deep learning technology to various problems. PLO.4, 5, 6, 7, 9, 11, 14
View Programme Learning Outcomes
Pre-requisites Nil, but knowledge of data structures and algorithms, probability, linear algebra, and programming would be an advantage.
Compatibility -
Topics covered
Course Content No. of Hours Course Learning Outcomes
1. Introduction
    a. Motivation for Studying Deep Learning
    b. Fundamental Machine Learning Techniques: Linear Classification, Linear Regression, Logistic Regression
    c. Artificial Neural Networks: Perceptron, Feed Forward, Backpropagation
    d. TensorFlow
10 CLO1, CLO2
2. Deep Learning Techniques
    a. Natural Language Processing and Recurrent Neural Networks
    b. Images and Convolutional Neural Networks
    c. Others such as: Unsupervised Feature Learning, Deep Generative Models, Deep Reinforcement Learning
20 CLO1,CLO2
Description Type Weighting * Examination Period ^ Course Learning Outcomes
Assignments Continuous Assessment 50% - CLO1,CLO2
2-hour written examination Written Examination 50% May 7 to 26, 2018 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 Lecture Notes will be distributed
Additional Material (articles, books, data sources) will be given during the course.
Session dates
Date Time Venue Remark
Session 1 18 Jan 2018 (Thu) 7:00pm - 10:00pm CB-A  
Session 2 25 Jan 2018 (Thu) 7:00pm - 10:00pm CB-A  
Session 3 1 Feb 2018 (Thu) 7:00pm - 10:00pm CB-A  
Session 4 8 Feb 2018 (Thu) 7:00pm - 10:00pm CB-A  
Session 5 1 Mar 2018 (Thu) 7:00pm - 10:00pm CB-A  
Session 6 15 Mar 2018 (Thu) 7:00pm - 10:00pm CB-A  
Session 7 22 Mar 2018 (Thu) 7:00pm - 10:00pm CB-A  
Session 8 29 Mar 2018 (Thu) 7:00pm - 10:00pm CB-A  
Session 9 12 Apr 2018 (Thu) 7:00pm - 10:00pm CB-A  
Session 10 19 Apr 2018 (Thu) 7:00pm - 10:00pm CB-A  
CB - Chow Yei Ching Building
Add/drop 15 January, 2018 - 28 January, 2018
Quota 100