校際選修

115-1 選課時程

進行中

  • 初選第一階段 6/15/2026
  • 初選第二階段 6/22/2026
  • 校際選修 8/24/2026
  • 初選第三階段 8/31/2026
  • 開學後加退選 9/7/2026
  • 逾期加退選 9/21/2026
選課資源

機器學習

Machine Learning

學期
113-1
學分
3 學分
當期課號
578001
永久課號
AAAI30001
開課單位
AI聯盟學分學程(學士班)
授課教師
林軒田
類別
選修
上課時間表
週一
5
13:20–14:10
機器學習
3 節連堂
6
14:20–15:10
7
15:30–16:20

* 根據陽明交大上課時間表所列

概述

Machine learning allows computational systems to adaptively improve their performance with experience accumulated from the data observed. This course introduces the basics of learning theories, the design and analysis of learning algorithms, and some applications of machine learning. The course is designed to prepare junior graduate students with a solid background of machine learning and allow them to use machine learning techniques appropriately in their future research or industry projects.

評分方式

70% homework 30% project (tentative)

週次計畫
週次主題
第 1 週9/2 course introduction; topic 1: when can machines learn? the learning problem (homework 0 announced)
第 2 週9/9 learning to answer yes/no; types of learning (homework 1 announced)
第 3 週9/16 feasibility of learning; topic 2: why can machines learn? training versus testing
第 4 週9/23 the VC dimension; noise and error (homework 2 announced)
第 5 週9/30 topic 3: how can machines learn? linear regression; logistic regression
第 6 週10/7 linear models for classification; nonlinear transformation (homework 0 due; homework 1 due; homework 2 due; homework 3 announced)
第 7 週10/14 topic 4: how can machines learn better? hazard of overfitting; regularization
第 8 週10/21 validation; three learning principles (homework 3 due; homework 4 announced; final project announced)
第 9 週10/28 topic 5: how can machines learn by embedding numerous features? linear support vector machine; dual support vector machine
第 10 週11/4 kernel support vector machine; soft-margin support vector machine (homework 4 due; homework 5 announced)
第 11 週11/11 topic 6: how can machines learn by combining predictive features? blending and bagging; adaptive boosting
第 12 週11/18 decision tree; random forest; gradient boosted decision tree (homework 5 due; homework 6 announced)
第 13 週11/25 topic 7: how can machines learn by distilling hidden features? neural network; (preliminary) deep learning
第 14 週12/2 modern deep learning (homework 6 due; homework 7 announced)
第 15 週12/9 no class as instructor needs to attend ACML 2024 and NeurIPS 2024; recording: machine learning for modern artificial intelligence
第 16 週12/16 finale (homework 7 due) 12/23 no class and winter vacation started (final project due)
教科書

Learning from Data, by Yaser Abu-Mostafa, Malik Magdon-Ismail and Hsuan-Tien Lin, Language: English teaching