週次 | 教學內容與作業進度 | 教學方式 | 備註 | 各週遠距上課網址( 按我進TronClass課程目錄 ) |
第1週
|
course introduction; topic 1: when can machines learn? the learning problem
|
遠距教學
|
9月2日,homework 0 announced
|
|
第2週
|
learning to answer yes/no; types of learning
|
遠距教學
|
9月9日,homework 1 announced
|
|
第3週
|
feasibility of learning; topic 2: why can machines learn? training versus testing
|
遠距教學
|
9月16日
|
|
第4週
|
the VC dimension; noise and error
|
遠距教學
|
9月23日,homework 2 announced
|
|
第5週
|
topic 3: how can machines learn? linear regression; logistic regression
|
遠距教學
|
9月30日
|
|
第6週
|
linear models for classification; nonlinear transformation
|
遠距教學
|
10月7日,homework 0 due; homework 1 due; homework 2 due; homework 3 announced
|
|
第7週
|
topic 4: how can machines learn better? hazard of overfitting; regularization
|
遠距教學
|
10月14日
|
|
第8週
|
validation; three learning principles
|
遠距教學
|
10月21日,homework 3 due; homework 4 announced; final project announced
|
|
第9週
|
topic 5: how can machines learn by embedding numerous features? linear support vector machine; dual support vector machine
|
遠距教學
|
10月28日
|
|
第10週
|
kernel support vector machine; soft-margin support vector machine
|
遠距教學
|
11月4日,homework 4 due; homework 5 announced
|
|
第11週
|
topic 6: how can machines learn by combining predictive features? blending and bagging; adaptive boosting
|
遠距教學
|
11月11日
|
|
第12週
|
decision tree; random forest; gradient boosted decision tree
|
遠距教學
|
11月18日,homework 5 due; homework 6 announced
|
|
第13週
|
topic 7: how can machines learn by distilling hidden features? neural network; (preliminary) deep learning
|
遠距教學
|
11月25日
|
|
第14週
|
modern deep learning
|
遠距教學
|
12月2日,homework 6 due; homework 7 announced
|
|
第15週
|
no class as instructor needs to attend ACML 2024 and NeurIPS 2024; recording: machine learning for modern artificial intelligence
|
遠距教學
|
12月9日
|
|
第16週
|
finale
|
遠距教學
|
12月16日,homework 7 due
|
|
第17週
|
no class and winter vacation started (really?)
|
遠距教學
|
12月23日,final project due
|
|
第18週
|
-
|
遠距教學
|
|
|