DASC7606C - Deep learning

Semester 1, 2024-25

Professor
Mauro Sozio
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.

Prerequisites: Basic programming skills, e.g., Python is required.
Introduction by Professor

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 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 DASC7606.
  • Students who have taken "COMP7606 Deep learning" should not be allowed to take DASC7606.
Topics covered
Course Content No. of Hours Course Learning Outcomes
1. Basic Concepts
   a. Introduction to Deep Learning
   b. Linear Models: Linear Regression and Gradient Descent, Logistic Regression and Classification
   c. Artificial Neural Networks: Perceptron, Feed Forward, Backpropagation, Training		 6 CLO1, COL2
2. Vision: CNN, AlexNet to ResNet, applications and concepts 9 CLO1, COL2
3. Generative AI: DeepDream, Variational Autoencoders, GAN 3 CLO1, COL2
4. Natural Language Processing: RNN, LSTM, transformers, LLMs, GPT 6 CLO1, COL2
5. Other topics such as: deep reinforcement learning, other deep learning applications, ethics 6 CLO1, COL2
 
Assessment
Description Type Weighting * Examination Period ^ Course Learning Outcomes
2 assignments Continuous Assessment 50% - CLO1, CLO2
Written examination
 Written Examination 50% 7 - 23 December 2024 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 are obliged to follow 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 18 Oct 2024 (Fri) 2:30pm - 5:30pm CYP-P3  
Session 2 19 Oct 2024 (Sat) 2:30pm - 5:30pm CYP-P3  
Session 3 25 Oct 2024 (Fri) 2:30pm - 5:30pm Wang Gungwu Lecture Hall, Graduate House  
Session 4 1 Nov 2024 (Fri) 2:30pm - 5:30pm LE-4  
Session 5 2 Nov 2024 (Sat) 2:30pm - 5:30pm CPD-3.28  
Session 6 8 Nov 2024 (Fri) 2:30pm - 5:30pm LE-4  
Session 7 15 Nov 2024 (Fri) 2:30pm - 5:30pm LE-4  
Session 8 16 Nov 2024 (Sat) 2:30pm - 5:30pm LE-4  
Session 9 22 Nov 2024 (Fri) 2:30pm - 5:30pm LE-4  
Session 10 29 Nov 2024 (Fri) 2:30pm - 5:30pm LE-4  
CPD - Central Podium Levels (Centennial Campus) CYP - Chong Yuet Ming Building LE - Library Extension Building
Add/drop 2 September, 2024 - 19 October, 2024
Maximum class size 148
Back