EE5438 Applied Deep Learning

Course Description

Applied Deep Learning is a hands-on course that equips aspiring AI scientists and engineers with the skills to design, train, and deploy deep neural networks using PyTorch. Through collaborative Python projects and real-world datasets, you’ll master key architectures—MLPs, CNNs, RNNs, Transformers and LLMs—alongside optimization, regularization, and hyperparameter tuning. Blending theory with practice, the course empowers you to build scalable AI solutions and innovate at the forefront of deep learning research and application.

Topics Covered

• A Brief History of AI with Deep Learning
• Perceptron and Multi-Layer Perceptrons (MLPs)
• Gradient Descent and Backpropagation
• Optimizations and Regularizations
• Convolutional Neural Networks (CNNs)
• Recurrent Neural Networks (RNNs)
• Self-Attention and Transformers
• Large Language Models (LLMs): BERT, GPT and T5
• LLM Decoding Strategies and Prompt Engineering
• Parameter-Efficient Fine-Tuning (PEFT)
• Instruction Tuning and Preference Alignment
• Multimodality: CLIP, Flamingo, LLaVA, GPT-4V

Grading

• Assignments: 15%
• Quiz: 5%
• Midterm: 10%
• Group Project: 20%
• Final Exam: 50%

Prerequisites

• Multi-variable Calculus and Linear Algebra
• Probability and Statistics
• Object-Oriented Programming

Please be advised: EE5438 is a course with STRONG Mathematical and Programming components.

Instructor

Prof. PO Lai-Man
Email: eelmpo@cityu.edu.hk
Phone: 3442-7779
Room: G6506, Green Zone, 6/F, AC1

Graders

• JIANG Zeyu - zeyujiang4-c@my.cityu.edu.hk
• LI Kun - kunli25-c@my.cityu.edu.hk
• LIU Yuyang - yuyangliu5-c@my.cityu.edu.hk
• WU Haoxuan - haoxuanwu2-c@my.cityu.edu.hk

Course Details

• Level and Units: P5 Level with 3 CUs
• Lecture: Thursday 9:00am to 11:50am
• Venue: YEUNG LT-14

Important Rules

Lecture Attendance

Required. You are responsible for whatever is taught in the lecture and tutorial.

Submission Guidelines

• Format: Hardcopies are not required
• Delivery: Soft copies (PDF, PPT, Colab source code, related files) must be uploaded to CANVAS by 11:00pm deadline
• Late Submission: Must be received by course email before 11:00PM on due date
• Policy: NO late homework accepted without previous arrangement with instructor
• Penalty: If approved, late homework receives 20% per business day penalty
• Format Requirements: Write name and student number on top right corner, show all work clearly

Academic Integrity

Cheating: Copying fellow classmates' assignments or programs is a very serious offense! If found cheating, you will automatically get an F grade in this course and your act will be reported to the Department for necessary disciplinary actions. Please don't let others copy your assignments or programs as we don't have a way to tell who is copying who and you may be liable to the penalties.

Quick Links

• View the course schedule
• Check out project assignments
• Browse helpful resources and links

Department Information

Department of Electrical Engineering
City University of Hong Kong
Tat Chee Avenue, Kowloon Tong, Hong Kong
Visit Department Website