課程名稱 |
機器學習 Machine Learning |
開課學期 |
111-1 |
授課對象 |
工學院 應用力學研究所 |
授課教師 |
舒貽忠 |
課號 |
AM7192 |
課程識別碼 |
543 M1180 |
班次 |
|
學分 |
3.0 |
全/半年 |
半年 |
必/選修 |
選修 |
上課時間 |
星期一5,6(12:20~14:10)星期四5,6(12:20~14:10) |
上課地點 |
應111應111 |
備註 |
初選不開放。 總人數上限:20人 |
課程簡介影片 |
|
核心能力關聯 |
核心能力與課程規劃關聯圖 |
課程大綱
|
為確保您我的權利,請尊重智慧財產權及不得非法影印
|
課程概述 |
The course offers an introduction to machine learning with an emphasis on the fundamental principles behind how and why learning algorithms work. The topics are selected, including (1) Supervised Learning: generative and discriminative probabilistic classifiers (Bayes/logistic regression)、least squares regression、neural networks (deep learning);(2) Probabilistic Graphical Model: Hidden Markov model (HMM);(3) Basic Learning Theory:PAC learning and model selection. This course is designed to give a thorough grounding currently needed by students who do research in machine learning. |
課程目標 |
After taking the course, students will be able to employ calculus, linear algebra, optimization, probability and statistics to develop learning models for various practical problems. In addition, they will be prepared for advanced research in machine learning and related fields. |
課程要求 |
Calculus and Linear Algebra |
預期每週課後學習時數 |
|
Office Hours |
|
指定閱讀 |
Various readings are required and will be assigned after each lecture. |
參考書目 |
1. C. M. Bishop. Pattern Recognition and Machine Learning, Springer, 2006
2. Shai Shalev-Shwartz and Shai Ben-David. Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press, 2014.
3. O. Calin. Deep Learning Architectures: A Mathematical Approach, Springer, 2020
4. K. P. Murphy. Probabilistic Machine Learning: An Introduction, MIT Press, 2022
5. Y. S. Abu-Mostafa, M. Magdon-Ismail and H. T. Lin. Learning From Data, AMLbook, 2012
6. E. Alpaydin. Introduction to Machine Learning, MIT Press, 2020. |
評量方式 (僅供參考) |
|
週次 |
日期 |
單元主題 |
第1週 |
5/9, 8/9 |
Learning, Evaluation of Model, Generalization Error, Empirical Risk Minimization and Inductive Bias |
第2週 |
12/9, 15/9, 19/9 |
Bayes optimal classifier, No-Free-Lunch Theorem and its proof |
第3週 |
19/9, 22/9 |
Perceptron learning algorithm (linear classifier) |
第4週 |
26/9 |
Naive Bayes classifier (example for detecting spam emails) |
第5週 |
3/10, 6/10 |
Bernoulli distribution, Bernoulli Naive Bayes classifier, Learning parameters estimated by MLE (maximum likelihood estimation) |
第6週 |
13/10 |
Gaussian distribution, Gaussian Naive Bayes classifier, Learning parameters estimated by MLE (maximum likelihood estimation) |
第7週 |
17/10, 20/10 |
Decision boundary for Gaussian Naive Bayes classifier, Confusion matrix, Logistic regression derived from Gaussian Naive Bayes classifier, Multivariate Gaussian Bayes classifier and its decision boundary (Quadratic Discriminant Analysis) |
第8週 |
27/10 |
Discriminative Probabilistic Classifier: Logistic Regression |
第9週 |
31/10, 3/11 |
Logistic Regression, Gradient-Based Optimization: Gradient Descent, Stochastic Gradient Descent (LR vs PLA) |
第10週 |
7/11, 10/11 |
Nonlinear Transformation, Abstract Neuron, Example of Multi-Layer Perceptron (MLP) : XOR problem with Analysis |
第11週 |
14/11 |
Examples: Clusters Splitting and Label Data using One-Hot Vector, Softmax function for Classification, General formulation of Multi-Layer Perceptron |
第12週 |
21/11, 24/11 |
Another type of XOR problem presented by Boolean Operation and MPL, Derivation of Backpropagation |
第13週 |
28/11, 1/12 |
Backpropagation vs Direct Chain Rule, Convolutional Neural Network |
第14週 |
5/12, 8/12 |
Convolutional Neural Network (sparse interactions, shared weights, equivariance to translation), Practical Implementation (4D kernel matrix), CNN Explainer |
第15週 |
12/12, 15/12 |
Backpropagation in CNN and Pooling |
|