機器學習導論
Introduction to Machine Learning
| 節 | 週三 | 週五 |
|---|---|---|
2 09:00–09:50 | 機器學習導論 ED220 | |
7 15:30–16:20 | 機器學習導論 ED220 2 節連堂 | |
8 16:30–17:20 |
* 根據陽明交大上課時間表所列
Learn the basic principles and some popular methods of machine learning 1. Introduction 2. Math Background & Commonly Used Probability Distributions 3. Supervised Learning (Linear Models, Neural Networks, Kernel Methods) 4. Unsupervised Learning (Mixture Models, EM Algorithm) 5. Sequential Data 6. Deep Learning (CNN, RNN, GAN, Transformer) 7. Reinforcement Learning
Required: Probability, Linear Algebra Recommended: Random Processes
Course Lectures: You may either come to the calssroom or listen to the lectures via Google Meet. Wednesday (3:30pm-5:20pm) ED220 (Live Broadcast: https://meet.google.com/xab-yhgc-oew) Friday (9:00am - 9:50am) ED220 (Live Broadcast: https://meet.google.com/igi-qotv-hzb) To be announced at NYCU E3 platform
Homework 45% Final Project 25% (Demo: 2023/6/14 ~ 2023/6/16) Final Exam 30% (3:30pm - 5:30pm. 2023/5/31)
| 週次 | 主題 |
|---|---|
| 第 1 週 | • Course Syllabus • Introduction • Math Background |
| 第 2 週 | • Math Background • Probability Distributions |
| 第 3 週 | • Probability Distributions • Conjugate Priors |
| 第 4 週 | • GMM • Non-parametric Models • Linear Models for Regression • Regularized Least Squares |
| 第 5 週 | • Bias-Variance Decomposition • Bayesian Linear Regression |
| 第 6 週 | |
| 第 7 週 | |
| 第 8 週 | (清明連假) |
| 第 9 週 | |
| 第 10 週 | |
| 第 11 週 | |
| 第 12 週 | |
| 第 13 週 | |
| 第 14 週 | |
| 第 15 週 | |
| 第 16 週 | |
| 第 17 週 | |
| 第 18 週 |
(Optional) Pattern Recognition and Machine Learning, by Christopher M. Bishop, Springer, 2007.
- 地點
- Room 649, Engineering Building IV
- 時間
- 2:00pm - 3:00pm Wednesday
- 聯絡方式
- shengjyh@nycu.edu.tw