週次 |
授課內容 |
第1週 |
Course Logits
What is Machine Learning?
Type of ML
Implementation: Data Plotting |
第2週 |
Formal Model
Perceptron |
第3週 |
Implementation: Perceptron
AdaLine and Gradient Descent
Implementation : Adaline
Implementation : Adaline SGD
Probably Approximately Correct (PAC) Learning
Agonostic PAC Learning |
第4週 |
Uniform Convergence
General Linear Model
Logistic Regression |
第5週 |
Implementation: A General Flow of Learning Process
No Free Lunch Theorem
Bias-Variance TradeOff |
第6週 |
Midterm I |
第7週 |
Convex Learning Problems
Surrogate Function |
第8週 |
Stability of Strongly Convex Learning Problems
Support Vector Machine
Kernel Trick |
第9週 |
The Representer Theorem
KNN
Decision Tree
Implementation: Kernel SVM, KNN, Decision Tree, and Random Forest |
第10週 |
Data Preprocessing
L1 Regularization
Implementation: Feature Selection
Principle Component Analysis |
第11週 |
LDA
Kernel PCA
Implementation: Kernel PCA
Machine Learning Pipeline and Cross Validation |
第12週 |
Midterm II |
第13週 |
Learning Curve
Imbalanced Data
Majority Voting
Implementation: Majority Voting and Parameter Tuning
Bagging
AdaBoost |
第14週 |
Clustering and K-means
Determine the number of clusters
|
第15週 |
Agglomerative Clustering
DBSCAN |
第16週 |
Final Report, Hand out the take-home final Exam |
第17週 |
自主跨域學習 |
第18週 |
自主跨域學習 |