機器學習導論
Introduction to Machine Learning
| 節 | 週二 | 週三 |
|---|---|---|
2 09:00–09:50 | 機器學習導論 ED219（光復） | |
3 10:10–11:00 | 機器學習導論 ED219（光復） 2 節連堂 | |
4 11:10–12:00 |
* 根據陽明交大上課時間表所列
Machine learning has been essential to the success of many recent technologies, including autonomous vehicles, search engines, genomics, automated medical diagnosis, image recognition, and social network analysis, among many others. This course will introduce the fundamental concepts and algorithms that enable computers to learn from experience, with an emphasis on their practical application to real problems. This course will introduce supervised learning (decision trees, logistic regression, support vector machines, Bayesian methods, neural networks and deep learning), unsupervised learning (clustering, dimensionality reduction), and reinforcement learning. Additionally, the course will discuss evaluation methodology and recent applications of machine learning, including large scale learning for big data. Relationship to “Machine learning” Introduction to Machine Learning (this course!) is a new introductory-level course in machine learning (ML) with an emphasis on applying ML techniques. This course is intended for students who are interested in the practical application of existing machine learning methods to real problems, rather than in the statistical foundations and theory of ML covered in the graduate course. Machine Learning is a more mathematically rigorous course in statistical machine learning that provides the background necessary to design and use new ML algorithms. Relationship to "deep learning for autonomous driving” “Deep learning for autonomous driving” focuses on applications of deep learning on autonomous driving. It will cover broad and deep knowledge about deep learning background and implementation issues.
Linear algebra, probability and statistics, programming
無備註
課堂講授與上機實作 教材於e3.nctu.edu.tw
評分: 無期中期末考 上機作業: machine learning 30%,deep learning 30%,big data and data preprocessing, 30% 課堂參與出席率: 10%
機器學習與應用 (Machine learning and its application on image recognition)
decision trees, logistic regression, support vector machines, Adaboost, application examples (郭峻因)
- 講授：
- 18
深度學習與應用Deep learning and its application
Convolutional neural network, Reinforcement learning, generative adversarial network, application examples(張添烜)
- 講授：
- 18
備註：教授 Keras/Tensorflow/Pytorch\n6 homeworks
資料前處理與生醫應用Data preprocessing and biomedical applications with deep learning
Data preprocessing on 1-D and 2D biomedical data and recognition with deep learning(李鎮宜)
- 講授：
- 18
| 週次 | 主題 |
|---|---|
| 第 1 週 | 上課日未開學 2/20 2/21 |
| 第 2 週 | Lecture: 神經網路簡介 2/27 2/28 |
| 第 3 週 | Lecture: 神經網路簡介 Lab: 機器學習系統環境建立與基礎神經網絡設計實驗 3/6 3/7 |
| 第 4 週 | Lecture: 機器學習/深度學習技術簡介 Lab: 資料標記工具與樣本建立實驗 3/13 3/14 |
| 第 5 週 | Lecture: 機器學習物件辨識技術與ADAS應用案例 Lab: Adaboost 機器學習人臉辨識實驗 3/20 3/21 |
| 第 6 週 | Lecture: 自動駕駛系統之設計趨勢 Lab: Adaboost ADAS系統實驗 (人、車辨識) 3/27 3/28 |
| 第 7 週 | Lecture: 自動駕駛系統之設計趨勢 Lab: Adaboost ADAS系統實驗 (人、車辨識) 4/3 4/4 |
| 第 8 週 | 手把手深度學習實務 (basic) 4/10 4/11 |
| 第 9 週 | 手把手深度學習實務 (application) 4/17 4/18 |
| 第 10 週 | 手把手深度學習實務 (training) 4/24 4/25 |
| 第 11 週 | recurrent neural network(讓電腦自己寫詩) 5/1 5/2 |
| 第 12 週 | reinforcement learning(讓電腦自己玩遊戲) 5/8 5/9 |
| 第 13 週 | Generative adversarial network(讓電腦自己產生圖片) |
| 第 13 週 | data preprocessing |
以上課講義為主
- 地點
- 李鎮宜ED538 郭峻因ED605 張添烜ED406
- 時間
- 請e-mail 洽各授課老師
- 聯絡方式
- 李鎮宜cylee@si2lab.org 郭峻因 jiguo@nctu.edu.tw 張添烜 tschang@g2.nctu.edu.tw