Courses Offered

COMP3340 Applied Deep Learning

COMP3340 Applied Deep Learning

2022-23
Instructor(s):Luo Ping
(Class A) No. of credit(s):6
Recommended Learning Hours:
Lecture: 26.0
Tutorial: 13.0
Pre-requisite(s):COMP2119 or ELEC2543 or FITE2000; and MATH1853 or MATH2014
Co-requisite(s):  
Mutually exclusive with:ELEC4544
Remarks:

Course Learning Outcomes

1. [1]
understand the motivations and principles for building deep learning systems based on empirical data, and how deep learning relates to the broader field of artificial intelligence.
2. [2]
formulate problems associated with domain specific data (e.g., image recognition, image generation, reinforcement learning, and language translation) in terms of deep learning models.
3. [3]
implement solutions to computer vision, natural language processing, and robotic problems using deep learning toolboxes such as PyTorch or Tensorflow, apply numerical optimization algorithms.
Mapping from Course Learning Outcomes to Programme Learning Outcomes
 PLO aPLO bPLO cPLO dPLO ePLO fPLO gPLO hPLO iPLO j
CLO 1TTT
CLO 2TTT
CLO 3TTT

T - Teach, P - Practice
For BEng(CompSc) Programme Learning Outcomes, please refer to here.

Syllabus

Calendar Entry:
An introduction to algorithms and applications of deep learning. The course helps students get hands-on experience of building deep learning models to solve practical tasks including image recognition, image generation, reinforcement learning, and language translation. Topics include: machine learning theory; optimization in deep learning; convolutional neural networks; recurrent neural networks; generative adversarial networks; reinforcement learning; self-driving vehicle.

Detailed Description:

Introduction Mapped to CLOs
Course Introduction: Overview of computer vision, natural language processing, reinforcement learning in video game, and historical context. Introduction to Python/NumPy. 1
Loss Functions and Optimization: Linear classification, higher-level representations, image features, optimization, stochastic gradient descent (SGD). 1, 2
Introduction to Neural Networks: Backpropagation, Multi-layer Perceptrons. 1, 2
Case #1: Able to build neural networks with backpropagation and SGD.2, 3
Convolutional Neural Networks Mapped to CLOs
Convolutional Neural Networks: History, Convolution and pooling, ConvNets beyong vision, Introduction to PyTorch 1, 2
CNN Architectures: AlexNet, VGG, GoogLeNet, ResNet, etc 1, 2
Case #2: Able to finetune and evaluate deep neural networks (e.g. AlexNet) for image recognition and others.2, 3
Generative Adversarial Networks Mapped to CLOs
GAN Architectures: Vanilla GAN, WGAN, DCGAN, CGAN, BEGAN, SRGAN, etc. 1, 2
Case #3: Able to finetune and evaluate SRGAN on CelebA for face image generation, super resolution, and others2, 3
Reinforcement Learning Mapped to CLOs
RL basics: policy gradients, hard attention1, 2
Q-Learning1, 2
Actor-Critic1, 2
Case #4: Able to train CNN_DQN to play Atari.2, 3

Assessment:
Continuous Assessment: 50%
Written Examination: 50%

Teaching Plan

Please refer to the corresponding Moodle course.

Moodle Course(s)

Please login with your CS account (for staff only)