Course Syllabus

Table of contents

1. Advanced method and theory of machine learning:
2. Advanced applications of machine learning:
3. Advanced unsupervised and semi-supervised learning:
4. Graph neural networks.
5. Causal inference and causal discovery.
6. Interpretability and explainability, safety and fairness.
7. Adversarial machine learning, robustness of neural networks, open discussions.

Advanced method and theory of machine learning:

Review of logistic regression, MLP, CNN, decision tree, kernel machine, etc; ensemble learning (boosting, GBDT); learning theory (PAC Bayes, VC dimension, Rademacher complexity).

Advanced applications of machine learning:

Recommendation systems, etc.

Advanced unsupervised and semi-supervised learning:

Nonlinear dimensionality reduction and denoising; generative models (VAE, GAN, diffusion model); spectral clustering; semi-supervised learning.

Graph neural networks.

Causal inference and causal discovery.

Interpretability and explainability, safety and fairness.

Adversarial machine learning, robustness of neural networks, open discussions.