5,034 recent views

#### 100% online

Start instantly and learn at your own schedule.

#### Approx. 25 hours to complete

Suggested: 7 hours/week...

#### 100% online

Start instantly and learn at your own schedule.

#### Approx. 25 hours to complete

Suggested: 7 hours/week...

### 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
NTU MOOC 課程問題詢問與回報機制1m

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 Reviews

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

By JCAug 7th 2019