EE 655000 Machine Learning 機器學習
Summer 2024, Mon. 14:30 to 17:20 and Thur. 14:30 to 17:20, Location Delta 台達 208
Instructor: Min Sun
TAs: 陳嘉旻 cjm108061535@gapp.nthu.edu.tw
王彥晴 loo24mone42@gmail.com
Course Description
機器學習領域有各種不同演算法，讓電腦可以從資料中學習，完成目標任務。隨著各領域數位化資料的累積，機器學習已經應用在五花八門 的各種領域。例如早期應用在資料探開，搜索，推薦上。到後來可以應用在各種非結構資料上，如語音、影像、文字等。如今機器學習更是 應用在各種科學領域，例如天文學、生物學、化學等。 機器學習結合了統計、數學與資訊科學等學門。廣義來說，機器學習研究如何讓電腦具有學習的能力，從以往的經驗及 數據中學習到知 識，以增進電腦本身的效能，因此機器學習也可解釋為利用資料來建立一些模擬真實世界的模型 （Models），利用這些模式來描述資料中 的特徵（Patterns）以及關係（Relations）。這些模式有兩種用處，第 一，瞭解資料的特徵與關係可以提供決策所需要的資訊。第 二，資料的特徵可以幫助進行預測。
本課程包括手寫作業以及程式作業，以及自學ML應用介紹(ML self-tutorial)、期中/期末報告 (最多2人一組)。 請在後面了解自學ML應用介紹(ML self-tutorial)、期中/期末報告等要求。syllabus.
Prerequisites
本課程需要使用Python編寫程式，此外會使用到線性代數、微積分、機率等概念。Textbook
Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006, ISBN: 0387310738Resource
Machine Learning by Prof. Andrew NgGrading
總成績保括- 55% 手寫作業以及程式作業。
- 35% 期中簡報、期末簡報、期末報告. 最多2人一組。
- 10% 自學ML應用介紹(ML self-tutorial)。
Important Links
Contact Info and Office Hours
教授聯繫資訊如下。- Min Sun: sunmin@ee.nthu.edu.tw
- Min Sun, Delta 962, Time: By Request
- TAs, EECS Building 711, Time: Wed. 13:00~15:00
Tentative Syllabus
| Week | Class Dates | Topic | Slides | Recording | Extra Info (e.g., Homework/Exam) |
|---|---|---|---|---|---|
| 1-1 | Mon, July 1 | Opening | Group Form Out | ||
| Math Review | |||||
| Python tutorial | |||||
| 1-2 | Thu, July 4 | Intro. to ML | Homework 1 out. Group Finalisation (7/6) | ||
| Probability Distributions | |||||
| 2-1 | Mon, July 8 (Class Recorded. Except "Intro to Competitions") | Probability Distributions | Class Recorded on eLearn | ||
| Linear Regression Models | |||||
| Intro to Competitions | link | ||||
| 2-2 | Thu, July 11 (Class Recorded. No Class.) | Linear Classification Models | Class Recorded on eLearn. Homework 2 out. | ||
| Self-Tutorial | |||||
| 3-1 | Mon, July 15 | NN | |||
| PyTorch Intro | Colab | ||||
| 3-2 | Thu, July 18 | NN | Homework 1 due | ||
| Self-Tutorial | |||||
| 4-1 | Mon, July 22 | Competiton Preparation: Open to team-based meeting | |||
| 4-2 | Thu, July 25 | Mid-Term Presentations | Each team presents 10 minutes. | ||
| 5-1 | Mon, July 29 | Kernel Methods | Homework 2 due | ||
| Self-Tutorial | |||||
| 5-2 | Thu, Aug. 1 | Sparse Kernel Machines | |||
| Self-Tutorial | |||||
| 6-1 | Mon, Aug. 5 | Graphical Model | |||
| 6-2 | Thu, Aug. 8 | Mixture Models and EM | |||
| Sampling Methods | |||||
| Self-Tutorial | |||||
| 7-1 | Mon, Aug. 12 | Ensemble Learning | |||
| Buffer | |||||
| 7-2 | Thu, Aug. 15 | Competiton Preparation: Open to team-based meeting | |||
| 8-1 | Mon, Aug. 19 | Competiton Preparation: Open to team-based meeting | Competition due on Aug. 19 at midnight. Final Report Due on Aug. 20 at noon. | ||
| 8-2 | Mon, Aug. 22 | Final presentation | Each team presents 10 minutes. | ||