EE5438Applied Deep Learning

What you will study

Course overview and aims

The purpose of this course is to familiarize students with state-of-the-art deep learning techniques adopted by the industry, such as MPL, CNN, LSTM, Transformer, BERT, GPT-3, ChatGPT, LLaMA LLaVA and more. Students will learn theoretical and practical concepts of deep neural networks, including optimization, inference, architecture, and applications. After completing this course, students should be able to develop and train deep neural networks, reproduce research results, and conduct original research. Additionally, students will use the Python programming language to implement deep learning applications through the PyTorch package.

Course content

Complete official information for this field is not available.

Before you take this course

Check prerequisites, precursors and corequisites separately, together with equivalence and exclusion conditions. “and” means conditions must be met together; “or” marks alternatives. Read combined conditions in the groupings shown in the original text below.

Prerequisites

Nil

Precursors

[MA2011 Multi-variable Calculus and Linear Algebra]; and [MA3160 Probability and Stochastic Processes]; and [EE3206 Java Programming and Applications]

Corequisites

This edition of the official syllabus does not state this item.

Additional course requirements

This edition of the official syllabus does not state this item.

Equivalent courses and conditions

Nil

Exclusive courses and conditions

EE4016 Applications of AI with Deep Learning

Assessment and passing the course

Assessment

Continuous assessment: 50%; Examination: 50%; Examination duration: 2 hours

Passing requirements

Remark: To pass the course, students are required to achieve at least 30% in course work and 30% in the examination. # may include homework, tutorial exercise, project/mini-project, presentation

The catalogue assessment percentages are indicative; the course syllabus provides the detailed assessment scheme.