Machine Learning (Li Hongyi, National Taiwan University)

The machine learning course taught by the well-received teacher Li Hongyi of National Taiwan University is also one of the very rare courses of this kind to be taught in Chinese. Friends who are not good at foreign languages ​​are in luck. The course focuses on deep learning and emphasizes practicality. In addition to the explanation of basic knowledge and algorithms, it also includes the interpretation of various related cutting-edge technologies. The projects involved in the course are very new and keep pace with the times.

Teacher Li's lectures focus on explaining the basic principles in a simple and easy-to-understand manner. He is humorous and easy to understand. He often uses animation images to explain the principles by analogy. It is really a breath of fresh air in machine learning tutorials~

The reprinted video is for communication and learning only. The original address of the reprint is: https://www.youtube.com/watch?v=CXgbekl66jc&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49

• Chapter 1：(0-1) Introduction of Machine Learning (38 minutes and 56 seconds)

• Chapter 2：(0-2)Why we need to learn machine learning? (1 minutes and 19 seconds)

• Chapter 3：(1-1)Regression-Case Study (1 hours and 18 minutes and 34 seconds)

• Chapter 4：(1-2)Regression-Demo (6 minutes and 52 seconds)

• Chapter 5：(2)Where does the error come from? (43 minutes and 14 seconds)

• Chapter 6：(3-1)Gradient Descent (1 hours and 1 minutes and 51 seconds)

• Chapter 7：(3-2)Gradient Descent (Demo by AOE) (2 minutes and 34 seconds)

• Chapter 8：(3-3)Gradient Descent (Demo by Minecraft) (1 minutes and 40 seconds)

• Chapter 9：(4)Classification (1 hours and 9 minutes and 40 seconds)

• Chapter 10：(5) Logistic Regression (1 hours and 7 minutes and 13 seconds)

• Chapter 11：(6) Brief Introduction of Deep Learning (46 minutes and 30 seconds)

• Chapter 12：(7)Backpropagation (31 minutes and 25 seconds)

• Chapter 13：(8-1) “Hello world” of deep learning (29 minutes and 51 seconds)

• Chapter 14：(8-2)Keras 2.0 (9 minutes and 37 seconds)

• Chapter 15：(8-3) Keras Demo (11 minutes and 12 seconds)

• Chapter 16：(9-1) Tips for Training DNN (1 hours and 26 minutes and 2 seconds)

• Chapter 17：(9-2) Keras Demo 2 (15 minutes and 20 seconds)

• Chapter 18：(9-3) Fizz Buzz in Tensorflow (sequel) (6 minutes and 9 seconds)

• Chapter 19：(10) Convolutional Neural Network (1 hours and 19 minutes and 28 seconds)

• Chapter 20：(11)Why Deep? (57 minutes and 44 seconds)

• Chapter 21：(12) Semi-supervised (59 minutes and 59 seconds)

• Chapter 22：(13) Unsupervised Learning - Linear Methods (1 hours and 40 minutes and 20 seconds)

• Chapter 23：(14)Unsupervised Learning - Word Embedding (40 minutes and 38 seconds)

• Chapter 24：(15)Unsupervised Learning-Neighbor Embedding (30 minutes and 58 seconds)

• Chapter 25：(16)Unsupervised Learning-Auto-encoder (42 minutes and 3 seconds)

• Chapter 26：(17) Unsupervised Learning - Deep Generative Model (Part I) (29 minutes and 34 seconds)

• Chapter 27：(18) Unsupervised Learning - Deep Generative Model (Part II) (1 hours and 3 minutes and 30 seconds)

• Chapter 28：(19)Transfer Learning (1 hours and 14 minutes and 28 seconds)

• Chapter 29：(20)Support Vector Machine (SVM) (1 hours and 5 minutes and 26 seconds)

• Chapter 30：(21-1)Recurrent Neural Network (Part I) (48 minutes and 59 seconds)

• Chapter 31：(21-2) Recurrent Neural Network (Part II) (1 hours and 30 minutes and 49 seconds)

• Chapter 32：(22)Ensemble (1 hours and 39 minutes and 58 seconds)

• Chapter 33：(23-1)Deep Reinforcement Learning (1 hours and 6 minutes and 21 seconds)

• Chapter 34：(23-2) Policy Gradient (Supplementary Explanation) (13 minutes and 19 seconds)

• Chapter 35：(23-3) Reinforcement Learning (including Q-learning) (1 hours and 5 minutes and 33 seconds)