Machine Learning Zhejiang University

Zhejiang University Machine Learning Course

• Chapter 1：Textbook introduction (6 minutes and 31 seconds)

• Chapter 2：Grade arrangement (17 minutes and 44 seconds)

• Chapter 3：Overview of the content of this course (17 minutes and 36 seconds)

• Chapter 4：Concept introduction (10 minutes and 20 seconds)

• Chapter 5：no free lunch theorem (20 minutes and 41 seconds)

• Chapter 6：Support vector machine (linear model) problem (20 minutes and 4 seconds)

• Chapter 7：Support vector machine (linear model) mathematical description (38 minutes and 28 seconds)

• Chapter 8：Image display of support vector machine (linear model) (1 minutes and 33 seconds)

• Chapter 9：Support vector machine nonlinear model optimization objective function and constraints (11 minutes and 29 seconds)

• Chapter 10：Support vector machine (nonlinear model) low-dimensional to high-dimensional mapping (28 minutes and 28 seconds)

• Chapter 11：Support vector machine (nonlinear model) primitive and dual problems (30 minutes and 51 seconds)

• Chapter 12：Support vector machine converts the original problem of support vector machine into a dual problem (57 minutes and 33 seconds)

• Chapter 13：Support vector machine – introduction to kernel function (7 minutes and 36 seconds)

• Chapter 14：Application of Support Vector Machine to the King of Soldiers Problem (10 minutes and 44 seconds)

• Chapter 15：Application of Support Vector Machine – King of Soldiers Problem (31 minutes and 51 seconds)

• Chapter 16：Application of support vector machines – King of Soldiers problem (test results) (4 minutes and 23 seconds)

• Chapter 17：ROC curve (18 minutes and 19 seconds)

• Chapter 18：Support vector machines – handle multi-class problems (11 minutes and 58 seconds)

• Chapter 19：Artificial neural network – mathematical model of neurons (17 minutes and 27 seconds)

• Chapter 20：Artificial Neural Network – Perceptron Algorithm (38 minutes and 58 seconds)

• Chapter 21：Artificial neural networks – the first cold winter of artificial intelligence (15 minutes and 7 seconds)

• Chapter 22：Artificial neural network – multi-layer neural network (11 minutes and 44 seconds)

• Chapter 23：Artificial neural network—three-layer neural network can simulate any decision-making surface (15 minutes and 54 seconds)

• Chapter 24：Artificial Neural Network—Backpropagation Algorithm (1 hours and 29 minutes and 55 seconds)

• Chapter 25：Artificial Neural Network – Parameter Settings (1 hours and 22 minutes and 15 seconds)

• Chapter 26：Deep learning database preparation (17 minutes and 59 seconds)

• Chapter 27：Deep learning autoencoder (23 minutes and 42 seconds)

• Chapter 28：Deep learning convolutional neural network LeNet (1 hours and 18 minutes and 45 seconds)

• Chapter 29：Deep Learning – Convolutional Neural Network (AlexNet) (39 minutes and 22 seconds)

• Chapter 30：Deep Learning – Programming Tools (Caffe and Tensorflow) (29 minutes and 32 seconds)

• Chapter 31：Deep learning – a popular network structure in recent years (19 minutes and 5 seconds)

• Chapter 32：Deep Learning – Applications of Convolutional Neural Networks (18 minutes and 40 seconds)

• Chapter 33：AlphaGo Go rules (16 minutes and 56 seconds)

• Chapter 34：Proof that AlphaGo Go has a winning strategy (8 minutes and 58 seconds)

• Chapter 35：Reinforcement learningQ learning (1 hours and 18 minutes and 8 seconds)

• Chapter 36：Reinforcement learning policy gradient (19 minutes and 23 seconds)

• Chapter 37：Reinforcement Learning AlphaGo (23 minutes and 25 seconds)

• Chapter 38：Feature Extraction – Principal Component Analysis (PCA) (1 hours and 13 minutes and 4 seconds)

• Chapter 39：Feature Selection – Adaptive Boosting (AdaBoost) (1 hours and 11 minutes and 15 seconds)

• Chapter 40：Object detection (RCNN and FCN) (57 minutes and 25 seconds)

• Chapter 41：Overview of Probabilistic Classification (19 minutes and 54 seconds)

• Chapter 42：Probability Density Estimation – Naive Bayes Classifier (16 minutes and 40 seconds)

• Chapter 43：Probability Density Estimation – Gaussian Density Function (31 minutes and 6 seconds)

• Chapter 44：Probability Density Estimation – Gaussian Mixture Model (3 minutes and 47 seconds)

• Chapter 45：EM algorithm (Gaussian mixture model and K-means algorithm) (48 minutes and 44 seconds)

• Chapter 46：Application of K-means algorithm in image compression (5 minutes and 16 seconds)

• Chapter 47：Application of Gaussian Mixture Model in Speaker Recognition (23 minutes and 49 seconds)

• Chapter 48：The general form of EM algorithm and its convergence proof (39 minutes and 24 seconds)

• Chapter 49：Speech recognition overview (7 minutes and 27 seconds)

• Chapter 50：Hidden Markov process (1 hours and 29 minutes and 0 seconds)

• Chapter 51：Introduction to Large Vocabulary Continuous Speech Recognition (35 minutes and 15 seconds)

• Chapter 52：Recurrent Neural Network (RNN) and LSTM (39 minutes and 41 seconds)

• Chapter 53：Philosophical brain in artificial intelligence (9 minutes and 5 seconds)

• Chapter 54：Philosophical consciousness issues in artificial intelligence (13 minutes and 4 seconds)

• Chapter 55：The Philosophical Turing Test in Artificial Intelligence (4 minutes and 17 seconds)

• Chapter 56：Is there any pattern in the philosophical world of artificial intelligence? (5 minutes and 38 seconds)

• Chapter 57：Philosophical Chinese Room Hypothetical Experiment in Artificial Intelligence (7 minutes and 3 seconds)

• Chapter 58：Philosophical creativity and cave theory in artificial intelligence (14 minutes and 0 seconds)

• Chapter 59：Philosophical Generative Adversarial Networks in Artificial Intelligence (15 minutes and 41 seconds)

• Chapter 60：Philosophical and moral dilemmas in artificial intelligence (9 minutes and 37 seconds)

• Chapter 61：Philosophical future prospects in artificial intelligence (4 minutes and 58 seconds)