中正大學課程大綱
課程名稱(中文)： 機器學習 開課單位： 工學院碩博班(College of Engineering (Graduate))
課程名稱(英文) Machine Learning 課程代碼 4015102_01
授課教師： 林軒田 學分數 3
必/選修 選修 開課年級 研究所(原則准許大三以上同學修習)
先修科目或先備能力：
課程概述：
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.
學習目標：
1. The course is designed to prepare junior graduate students with a solid backgro
教科書：
Learning from Data, by Yaser Abu-Mostafa,, Malik Magdon-Ismail and Hsuan-Tien Lin
上課時間:星期三 09:10-12:10
是否接受非同步授課:是
實體期末評量時間:The final exam will be held on December 9, 2026.

課程大綱 分配時數 核心能力 備註
單元主題 內容綱要 講授 示範 隨堂作業 其他
course introduction
topic 1: when can machines

learn?
the learning problem
homework 0 announced
learning to answer yes/no
types of learning
homework 1 announced
feasibility of learning
topic 2: why can machines

learn?
training versus testing
the VC dimension
noise and error
homework 2 announced
topic 3: how can machines learn?
linear regression;
logistic regression
linear models for classification
nonlinear transformation
homework 0 due; homework 1
due; homework 2 due;
homework 3 announced
topic 4: how can machines learn better?
hazard of overfitting;
regularization
validation
three learning principles
homework 3 due; homework 4
announced; final project
announced
topic 5: how can machines learn by embedding numerous features?
linear support vector machine;
dual support vector machine
kernel support vector machine
soft-margin support vector
machine
homework 4 due; homework 5

announced
topic 6: how can machines learn by combining predictive features?
blending and bagging;
adaptive boosting
decision tree
random forest;
gradient boosted decision tree
homework 5 due; homework 6

announced
no class as instructor needs to attend ACML 2026 and NeurIPS 2026;
recording: machine learning for
modern artificial intelligence
Final exam
topic 7: how can machines learn by distilling hidden features?
neural network;
(preliminary) deep learning
homework 6 due
modern deep learning/finale


請尊重智慧財產權，不得非法影印教師指定之教科書籍

教學要點概述：
1. 教材編選(可複選)：自編簡報(ppt)教科書作者提供
2. 教學方法(可複選)：講述板書講述
3. 評量工具(可複選)：上課點名 0%, 隨堂測驗0%, 隨堂作業50.00%, 程式實作0%, 實習報告0%,
                       專案報告30.00%, 期中考20.00%, 期末考0%, 期末報告0%, 其他0%,
4. 教學資源：課程網站 教材電子檔供下載 實習網站
5. 教學相關配合事項： 課程要求 Computer Programming, Calculus, Probability, Linear Algebra

課程目標與教育核心能力相關性        
請勾選：