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.

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