[ECG5304] - Deep Learning for Digitalization Technologies / [EE5934/6934] - Deep Learning (Part 1)

Electrical and Computer Engineering, NUS

Description:

This course is about deep learning. Students taking this course will learn the theories, models, algorithms, and recent progress of deep learning. The course starts with machine learning basics and classical neural network models, followed by deep convolutional neural networks, recurrent neural networks, reinforcement learning, etc., and their applications. Students are expected to have good knowledge of calculus, linear algebra, probability and statistics as prerequisites.

This website contains only information of Part 1 (the first half of the course).


Textbooks (The textbooks are used loosely): Instructor: Assoc. Prof. (adj.) Joey Tianyi Zhou (Part 1) Lecturer Yuecong Xu (Part 2)

Teaching Schedule:

The following schedule will not be strictly followed.

Date
Topic
Notes
Week 1 1. Introduction to Deep Learning

Machine Learning Basics. Data Pre-processing.
Week 2 2. Neural networks, training pipeline and learning strategies

History of Deep Learning. Perceptrons. MLPs. Optimisation, Regularization.
Week 3 3. Autoencoder, CNN and RNN and their Variants

Denoising Autoencoder. Adversarial Examples. CNNs. RNNs. LSTMs.
Week 4 4. Transformer

Sequence to Sequence with RNNs. Attention. Modules in GPTs.
Week 5 5. Prompting

Prompting in NLP/CV/vision-language models. Soft/hard Prompts.
Week 6 6. Model and Dataset Compression

Model Compression for DNNs. Dataset Pruning/Distillation


Syllabus: