A note from the Machine Learning course given by Hung-Yi Lee.

Written by Yi-Hsuan Hung in 2020.

<aside> 🚀 點擊以下主題開始

</aside>

Table of content

1. Regression

• Three Steps for Machine Learning
• Bias and Variance
• Gradient Descent Theory

2. Classification

• Probabilistic Generative Model
• Logistic Regression

3. CNN

• Deep Learning
• Back Propagation
• Implement Deep Learning
• Tips for Deep Learning
• CNN
• Why Deep?

4. RNN

• Semi-supervised Learning
• Unsupervised Learning - Linear Dimension Reduction
• Unsupervised Learning - Word Embedding
• RNN

5. Explainable AI

6. Adversarial Attack

7. Network Compression

8. Seq to Seq

• Generation & Attention
• Tips for Generation
• Recursive Network
• Transformer

9. Unsupervised Learning

• Dimension Reduction (Linked to RNN)
• Neighbor Embedding
• Auto-Encoder
• BERT

10. Anomaly Detection

11. GAN

• Introduction of GAN
• Conditional Generation
• Unsupervised Conditional Generation
• Basic Theory
• WGAN, EBGAN
• Feature Extraction (Info GAN, VAE-GAN, BiGAN)
• Photo Editing
• Sequence Generation
• Evaluation
• Flow-based Generative Model

12. Transfer Learning

13. Meta Learning

• Meta Learning
• MAML & Reptile
• Gradient Descent as LSTM

14. Lifelong Learning

15. Reinforcement Learning

• Deep Reinforcement Learning

Appendix

• PyTorch

Written by YI-HSUAN HUNG, 2020

Bookmarks

Hung-yi Lee

Machine Learning (Hung-yi Lee, NTU) - YouTube

Pages

Regression

Classification

CNN

RNN

Explainable AI