About this course: Machine learning is the study that allows computers to adaptively improve their performance with experience accumulated from the data observed. Our two sister courses teach the most fundamental algorithmic, theoretical and practical tools that any user of machine learning needs to know. This second course of the two would focus more on algorithmic tools, and the other course would focus more on mathematical tools. [機器學習旨在讓電腦能由資料中累積的經驗來自我進步。我們的兩項姊妹課程將介紹各領域中的機器學習使用者都應該知道的基礎演算法、理論及實務工具。本課程將較為著重方法類的工具，而另一課程將較為著重數學類的工具。]
Created by: National Taiwan University
Taught by: Hsuan-Tien Lin, 林軒田, 教授 (Professor)
資訊工程學系 (Computer Science and Information Engineering)
| Level | Intermediate |
| Language | Chinese (Traditional) |
| Hardware Req | 需要一般個人電腦或同等級的計算資源以撰寫程式執行作業 |
| How To Pass | Pass all graded assignments to complete the course. |
| User Ratings |
Syllabus
WEEK 1
第九講: Linear Regression
weight vector for linear hypotheses and squared error instantly calculated by analytic solution
4 videos, 3 readings
- Video: Linear Regression Algorithm
- Video: Generalization Issue
- Video: Linear Regression for Binary Classification
- Reading: 課程大綱
- Reading: 課程形式及評分標準
- Reading: 延伸閱讀
WEEK 2
第十講: Logistic Regression
gradient descent on cross-entropy error
to get good logistic hypothesis
4 videos
- Video: Logistic Regression Error
- Video: Gradient of Logistic Regression Error
- Video: Gradient Descent
WEEK 3
第十一講: Linear Models for Classification
binary classification via (logistic) regression; multiclass classification via OVA/OVO decomposition
4 videos
- Video: Stochastic Gradient Descent
- Video: Multiclass via Logistic Regression
- Video: Multiclass via Binary Classification
WEEK 4
第十二講: Nonlinear Transformation
nonlinear model via nonlinear feature transform+linear model with price of model complexity
4 videos
- Video: Nonlinear Transform
- Video: Price of Nonlinear Transform
- Video: Structured Hypothesis Sets
Graded: 作業三
WEEK 5
第十三講: Hazard of Overfitting
overfitting happens with excessive power, stochastic/deterministic noise and limited data
4 videos
- Video: The Role of Noise and Data Size
- Video: Deterministic Noise
- Video: Dealing with Overfitting
WEEK 6
第十四講: Regularization
minimize augmented error, where the added regularizer effectively limits model complexity
4 videos
- Video: Weight Decay Regularization
- Video: Regularization and VC Theory
- Video: General Regularizers
WEEK 7
第十五講: Validation
(crossly) reserve validation data to simulate testing procedure for model selection
4 videos
- Video: Validation
- Video: Leave-One-Out Cross Validation
- Video: V-Fold Cross Validation
WEEK 8
第十六講: Three Learning Principles
be aware of model complexity, data goodness and your professionalism
4 videos
- Video: Sampling Bias
- Video: Data Snooping
- Video: Power of Three
Graded: 作業四
FAQs
How It Works
Coursework
Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.
Help from Your Peers
Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.
Certificates
Earn official recognition for your work, and share your success with friends, colleagues, and employers.
Creators
National Taiwan University
We firmly believe that open access to learning is a powerful socioeconomic equalizer. NTU is especially delighted to join other world-class universities on Coursera and to offer quality university courses to the Chinese-speaking population. We hope to transform the rich rewards of learning from a limited commodity to an experience available to all.More courses information, the official Facebook Page: https://www.facebook.com/ntumooc2017/
Ratings and Reviews
good course
林老師的課不僅聽起來比較清晰易懂，並且深度足夠（比Andrew Ng的課而言深度要大不少），值得多次聽講。作業質量也比較高，能夠有很好的鍛煉效果。期待後續的技法課程能夠在coursera上面公佈。
Good!
Coursera provides universal access to the world’s best education,
partnering with top universities and organizations to offer courses online.
© 2018 Coursera Inc. All rights reserved.
good job 希望技法的课也能开呀。