機器學習

Machine Learning

學期

115-1

學分

3 學分

當期課號

535359

永久課號

EECM30060

開課單位

電信工程研究所、人工智慧技術與應用碩士學位學程、前瞻半導體研究所、人工智慧跨域學程-工程與科學組、人工智慧跨域學程-生醫組、資通安全碩士學位學程、量子科學與工程碩士學位學程、電機工程學系

授課教師

江孟芬

校區

光復

類別

選修

上課時間表

節	週五
2 09:00–09:50	機器學習 ED201（光復） 3 節連堂
3 10:10–11:00
4 11:10–12:00

* 根據陽明交大上課時間表所列

概述

This course provides a comprehensive introduction to the fundamental concepts and methodologies of machine learning, covering: (i) core principles of machine learning, such as bias-variance theory; (ii) unsupervised learning methods, including clustering, association rule mining, anomaly detection, and Principal Component Analysis (PCA); (iii) supervised learning techniques, including decision trees, regression, support vector machines, and neural networks; (iv) ensemble learning methods, including bagging ensembles and boosting ensembles; and (v) modern learning paradigms, including self-supervised learning, the Transformer architecture, large-scale pre-training, and post-training strategies such as fine-tuning and instruction tuning.

先修科目

Probability, Programming, Data Science

備註

無備註

教學方式

教師未提供此項資料

評分方式

• Four Individual Assignments: 60% • Final Exam: 40%

課程大綱

教師未提供此項資料

週次計畫

週次	主題
第 1 週	Introduction to Machine Learning
第 2 週	Unsupervised Learning (I): Clustering
第 3 週	Unsupervised Learning (II): Principal Component Analysis [HW1 Release]
第 4 週	Unsupervised Learning (III): Anomaly Detection
第 5 週	Supervised Learning (I): Instance-based Learning, Logistic Regression
第 6 週	Supervised Learning (II): Bayesian Learning [HW2 Release]
第 7 週	Supervised Learning (III): Hard-margin SVMs
第 8 週	Supervised Learning (IV): Soft-margin SVMs
第 9 週	Supervised Learning (V): Kernelized SVMs [HW3 Release]
第 10 週	Supervised Learning (VI): Deep Neural Network
第 11 週	Supervised Learning (VII): Graph Neural Network
第 12 週	Modern Learning Paradigm (VIII): Ensemble Learning [HW4 Release]
第 13 週	Modern Learning Paradigm (I): Transformer
第 14 週	Modern Learning Paradigm (II): Pre-Training
第 15 週	Modern Learning Paradigm (III): Post-Training
第 16 週	Final Exam

教科書

• Christopher M. Bishop, Hugh Bishop (2023). Deep Learning: Foundations and Concepts. Springer. • Sebastian Raschka, Yuxi Liu, Vahid Mirjalili (2022). Machine Learning with PyTorch and Scikit-Learn. Packt Publishing Ltd. • Mitchell, T. M. (1997). Machine learning. New York: McGraw-Hill. • Han, J., Kamber, M., & Pei, J. (2014). Data Mining (3rd Revised ed.). Morgan Kaufmann Publishers. (Online via library) • Bishop, C. M. (2006). Pattern Recognition and Machine Learning (1st ed. 2006. Corr. 2nd printing 2011). New York, NY: Springer-Verlag New York Inc. • Tan, P.-N., Steinbach, M., & Kumar, V. (2019). Introduction to data mining (2nd ed). Boston: Pearson Education Limited.

Office Hours

地點: ED201
時間: F234
聯絡方式: meng.chiang@nycu.edu.tw