106年第2學期-5701 機器學習 課程資訊

評分方式

評分項目	配分比例	說明
期中考	30	筆試
期末專案	30	分組專案
作業	30	回家作業
出席	10	出席

教育目標

機器學習是透過演算法，使用歷史資料做訓練以建立模型，並依此模型對於新的資料進行預測。本課程涵蓋機器學習的基礎理論、演算法、以及應用，探討什麼是機器學習？機器可能學習嗎？如何學習？如何做到較好的學習？讓同學了解機器學習的理論與實務。

課程概述

Machine learning is the science of data analysis that automates a massive number of models building. Its process uses data to iteratively detect patterns and adjust models accordingly, and enables computers to learn without explicitly programmed. This course introduces some important concepts and algorithms of machine learning from both theoretical and practical perspective. The topics include, but not limited to: (1) Supervised learning (Linear Models for Regression and Classification, Kernel Smoothing Methods, Decision Trees, Support Vector Machines, and Neural Networks). (2) Unsupervised learning (Association Rules and Cluster Analysis). (3) Ensemble learning (Bagging, Boosting, Random Forests). (4) Others (MCMC, Optimization Integration).

基本資料

選修課，學分數：0-3
上課時間：五/6,7,8[C101]
修課班級：資工系4,碩1,2
修課年級：年級以上
選課備註：大四可選

參考書目

[1] Yaser S. Abu-Mostafa, Malik Magdon-Ismail and Hsuan-Tien Lin, Learning From Data, AMLbook.com, 2012.
[2] Ethem Alpaydın, Introduction to Machine Learning, 2nd Ed. The MIT Press Cambridge, 2010.
[3] An Introduction to Machine Learning Theory and Its Applications: A Visual Tutorial with Examples, by Nick McCrea.
[4] Deep Reinforcement Learning, David Silver, Google DeepMind, 2017 (http://www.iclr.cc/lib/exe/fetch.php?media=iclr2015:silver-iclr2015.pdf)
[5] Reinforcement Learning: An Introduction, by Richard S. Sutton,‎ Andrew G. Barto, A Bradford Book, 2017