Hung-yi Lee's Lectures

back to index

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

0 ML Lecture 0-1: Introduction of Machine Learning

1 ML Lecture 0-2: Why we need to learn machine learning?

2 ML Lecture 1: Regression - Case Study

3 ML Lecture 1: Regression - Demo

4 ML Lecture 2: Where does the error come from?

5 ML Lecture 3-1: Gradient Descent

6 ML Lecture 3-2: Gradient Descent (Demo by AOE)

7 ML Lecture 3-3: Gradient Descent (Demo by Minecraft)

8 ML Lecture 4: Classification

9 ML Lecture 5: Logistic Regression

10 ML Lecture 6: Brief Introduction of Deep Learning

11 ML Lecture 7: Backpropagation

12 ML Lecture 8-1: “Hello world” of deep learning

13 ML Lecture 8-2: Keras 2.0

14 ML Lecture 8-3: Keras Demo

15 ML Lecture 9-1: Tips for Training DNN

16 ML Lecture 9-2: Keras Demo 2

17 ML Lecture 9-3: Fizz Buzz in Tensorflow (sequel)

18 ML Lecture 10: Convolutional Neural Network

19 ML Lecture 11: Why Deep?

20 ML Lecture 12: Semi-supervised

21 ML Lecture 13: Unsupervised Learning - Linear Methods

22 ML Lecture 14: Unsupervised Learning - Word Embedding

23 ML Lecture 15: Unsupervised Learning - Neighbor Embedding

24 ML Lecture 16: Unsupervised Learning - Auto-encoder

25 ML Lecture 17: Unsupervised Learning - Deep Generative Model (Part I)

26 ML Lecture 18: Unsupervised Learning - Deep Generative Model (Part II)

27 ML Lecture 19: Transfer Learning

28 ML Lecture 20: Support Vector Machine (SVM)

29 ML Lecture 21-1: Recurrent Neural Network (Part I)

30 ML Lecture 21-2: Recurrent Neural Network (Part II)

31 ML Lecture 22: Ensemble

32 ML Lecture 23-1: Deep Reinforcement Learning

33 ML Lecture 23-2: Policy Gradient (Supplementary Explanation)

34 ML Lecture 23-3: Reinforcement Learning (including Q-learning)

35 ML Lecture 21-1: Recurrent Neural Network (Part I) English version