Electrical and Computer Engineering, NUS
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 2 (the second half of the course).
The following schedule will not be strictly followed.
Date | | |
---|---|---|
February 28 |
1. CONVOLUTIONAL NEURAL NETWORK (CNN)
|
Lecture 1
Lecture 1 with annotation |
March 7 |
2. RECURRENT NEURAL NETWORKS AND TRANSFORMER
|
Lecture 2
Lecture 2 with annotation |
March 14 |
3. TRANSFORMER + DEEP GENERATIVE NETWORKS (AUTOENCODER)
|
Lecture 3
CEG5304: CA 3 and CA 4 EE6934: CA 3 + Essay |
March 21 |
4. DEEP GENERATIVE NETWORKS: VAE + DIFFUSION MODELS
| Lecture 3 with annotation |
March 28 |
5. GAN + NERF + REINFORCEMENT LEARNING
| See "Lecture 3 with annotatation" |
April 4 |
6. REINFORCEMENT LEARNING: MDP + Q-LEARNING + POLICY GRADIENTS
| Lecture 6 with annotation |
April 11 |
7. BAYESIAN DEEP LEARNING
| Lecture 7 |