WEEK 1 - 09/05

Topic 1. Introduction;
    2. Regression; Bias and Variance Errors

WEEK 2 - 09/12

TopicLinear Model Classification: Probabilistic Generative Model, Logistic Regression

WEEK 3 - 09/19

Topic1. Ensemble: Random forest, AdaBoost
    2. Neural Networks: Introduction, Gradient Decent and Back Propagation, Tips, Implementation (李宏毅教授教學影片)

WEEK 4 - 09/26

Topic1. Dimensionality Reduction: Principle Component Analysis
    2. Auto encoder (李宏毅教授教學影片)

WEEK 5 - 10/03

Topic1. Neighbor Embedding
    2. Convolutional Neural Network (李宏毅教授教學影片)

WEEK 6 - 10/17

Topic1. Expectation Maximization and Gaussian Mixture Models
    2. Semi-Supervised Learning (李宏毅教授教學影片)

WEEK 7 - 10/17

Topic1. Expectation Maximization and Gaussian Mixture Models
    2. Semi-Supervised Learning (李宏毅教授教學影片)

WEEK 8 - 10/17

Topic1. Expectation Maximization and Gaussian Mixture Models
    2. Semi-Supervised Learning (李宏毅教授教學影片)

WEEK 9 - 10/31

Topic1. Variational Auto-Encoder
    2. Recurrent Neural Network (李宏毅教授教學影片)

WEEK 10 - 11/07

Topic1. Support Vector Machine: Margin and primal form
    2. Duality Theory of Constrained Optimization – Introduction

WEEK 11 - 11/14

TopicStrong Duality Theorem

WEEK 12 - 11/21

TopicStrong Duality Theorem

WEEK 13 - 11/28

TopicSupport Vector Machine: Kernel form and KKT conditions

WEEK 14 - 12/05

TopicReinforcement Learning: Markov Decision Process and Bellman optimality equations

WEEK 15 - 12/12

TopicReinforcement Learning: Value and Policy Iterations; Multi-arm bandit problem

HOMEWORK

PROGRAM