About this Course
6,366 recent views

100% online

Start instantly and learn at your own schedule.

Flexible deadlines

Reset deadlines in accordance to your schedule.

Intermediate Level

Approx. 25 hours to complete

Suggested: 7 hours/week...

Chinese (Traditional)

Subtitles: Chinese (Traditional)
Learners taking this Course are
  • Technical Solutions Engineers
  • Machine Learning Engineers
  • Product Managers
  • Data Scientists
  • Designers

100% online

Start instantly and learn at your own schedule.

Flexible deadlines

Reset deadlines in accordance to your schedule.

Intermediate Level

Approx. 25 hours to complete

Suggested: 7 hours/week...

Chinese (Traditional)

Subtitles: Chinese (Traditional)

Syllabus - What you will learn from this course

Week
1
1 hour to complete

Concept learning

6 videos (Total 73 min), 2 readings, 1 quiz
6 videos
1-2 Hypotheses ,Relation between Instance Space and Hypotheses14m
1-3 The Find-S Algorithm10m
1-4 Version Space and The List-Then Eliminate Algorithm12m
1-5 The Candidate Elimination Algorithm15m
1-6 Biased and Unbiased Hypothesis Space, Futility of Bias-Free Learning12m
2 readings
NTU MOOC 課程問題詢問與回報機制1m
課程投影片開放下載公告2m
1 practice exercise
Week 1 Quiz10m
Week
2
2 hours to complete

Computational Learning Theory

8 videos (Total 120 min), 1 quiz
8 videos
2-2 Setting 3, PAC Learnable10m
2-3 Exhausting the Version Space: Definition, Theorem ,Proof and some examples19m
2-4 Shatter, Dichotomy, VC dimension14m
2-5 Some examples and discussion about VC dimension14m
2-6 Upper and Lower Bounds on Sample Complexity with VC dimension, The Mistake Bound for Algorithms14m
2-7 Optimal Mistake Bound13m
2-8 The Weighted-Majority Algorithm and its Bound11m
1 practice exercise
Week 2 Quiz16m
Week
3
2 hours to complete

Classification

6 videos (Total 114 min), 1 quiz
6 videos
3-2 Learning Decision Tree, Information19m
3-3 Generalization and Overfitting, Kai Square Pruning,Rule Post-Pruning22m
3-4 Model Evaluation: Metrics for Performance Evaluation, Methods for Model Comparison19m
3-5 Ensemble: Embedding, Bagging and Boosting13m
3-6 Support Vector Machine: Optimization, Soft Margins, and Kernel Trick21m
1 practice exercise
Week 3 Quiz24m
Week
4
3 hours to complete

Neural Network and Deep learning

9 videos (Total 151 min), 1 quiz
9 videos
4-2 Single-Layer Network and Perceptron Learning Rule15m
4-3 Multi-Layer Perceptron, Back Propagation Learning, Decline of ANN10m
4-4 Cascade Correlation Neural Networks, Deep or Shallow Structure23m
4-5 Deep Learning: Convolutional Neural Networks17m
4-6 LeNet 5, Dropout, ReLU and the Variants, Maxout, Residual Net18m
4-7 Recurrent Networks, Long Short-Term Memory (LSTM), Neural Turing Machine, Memory-Augmented Neural Networks (MANN)15m
4-8 Autoencoder: Denoising Autoencoder, Stacked Autoencoder and Variational Autoencoder12m
4-9 Generative Adversarial Net (GAN), AE+GAN and Its Applications16m
1 practice exercise
Week 4 Quiz16m
4.8
1 ReviewsChevron Right

Top reviews from 人工智慧:機器學習與理論基礎 (Artificial Intelligence - Learning & Theory)

By JCAug 7th 2019

整體上, 是值得推薦的入門課程, 把machine learning的基本課程與熱門的topics提出來講. 習題的內容算簡單, 大部份在檢驗觀念.

Instructor

Avatar

于天立

副教授 (Associate Professor)
電機工程學系 (Department of Electrical Engineering)

About 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/...

Frequently Asked Questions

  • Once you enroll for a Certificate, you’ll have access to all videos, quizzes, and programming assignments (if applicable). Peer review assignments can only be submitted and reviewed once your session has begun. If you choose to explore the course without purchasing, you may not be able to access certain assignments.

  • When you purchase a Certificate you get access to all course materials, including graded assignments. Upon completing the course, your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. If you only want to read and view the course content, you can audit the course for free.

More questions? Visit the Learner Help Center.