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

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

Instructor: 于天立

Access provided by Connors State College

10,689 already enrolled

5 modules

Gain insight into a topic and learn the fundamentals.

4.6

(61 reviews)

Intermediate level

Some related experience required

1 week to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

5 modules

Gain insight into a topic and learn the fundamentals.

4.6

(61 reviews)

Intermediate level

Some related experience required

1 week to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

Skills you'll gain

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

5 assignments

Taught in Chinese (Traditional)

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

There are 5 modules in this course

本課程第二部分著重在和人工智慧密不可分的機器學習。課程內容包含了機器學習基礎理論（包含 1990 年代發展的VC理論）、分類器（包含決策樹及支援向量機）、神經網路（包含深度學習）及增強式學習（包含深度增強式學習。

此部份技術包含最早追溯至 1950 年代直到最近 2016 年附近的最新發展。此課程從基礎理論開始，簡介了各機器學習主流技法以及從淺層學習架構演變到最近深度架構的轉換。本課程之核心目標為：（一）使同學對人工智慧相關的機器學習技術有基礎概念（二）同學能夠理解機器學習基礎理論、分類器、神經網路、增強式學習（三）同學能將相關技術應用到自己的問題上修課前，基礎背景知識：需要的先備知識：計算機概論建議的先備知識：資料結構與演算法

What's included

6 videos2 readings1 assignment

6 videosTotal 73 minutes

1-1 Brief Introduction to Machine Learning, Learning from Example8 minutes
1-2 Hypotheses ,Relation between Instance Space and Hypotheses14 minutes
1-3 The Find-S Algorithm10 minutes
1-4 Version Space and The List-Then Eliminate Algorithm12 minutes
1-5 The Candidate Elimination Algorithm15 minutes
1-6 Biased and Unbiased Hypothesis Space, Futility of Bias-Free Learning12 minutes

2 readingsTotal 2 minutes

NTU MOOC 課程問題詢問與回報機制1 minute
課程投影片開放下載公告1 minute

1 assignmentTotal 30 minutes

Week 1 Quiz30 minutes

What's included

8 videos1 assignment

8 videosTotal 119 minutes

2-1 Introduction to Computational Learning Theory, Setting of Sample Complexity20 minutes
2-2 Setting 3, PAC Learnable10 minutes
2-3 Exhausting the Version Space: Definition, Theorem ,Proof and some examples19 minutes
2-4 Shatter, Dichotomy, VC dimension14 minutes
2-5 Some examples and discussion about VC dimension14 minutes
2-6 Upper and Lower Bounds on Sample Complexity with VC dimension, The Mistake Bound for Algorithms14 minutes
2-7 Optimal Mistake Bound13 minutes
2-8 The Weighted-Majority Algorithm and its Bound11 minutes

1 assignmentTotal 30 minutes

Week 2 Quiz30 minutes

What's included

6 videos1 assignment

6 videosTotal 113 minutes

3-1 Decision Trees and its Hypothesis Space17 minutes
3-2 Learning Decision Tree, Information19 minutes
3-3 Generalization and Overfitting, Kai Square Pruning,Rule Post-Pruning22 minutes
3-4 Model Evaluation: Metrics for Performance Evaluation, Methods for Model Comparison19 minutes
3-5 Ensemble: Embedding, Bagging and Boosting13 minutes
3-6 Support Vector Machine: Optimization, Soft Margins, and Kernel Trick21 minutes

1 assignmentTotal 24 minutes

Week 3 Quiz24 minutes

What's included

9 videos1 assignment

9 videosTotal 150 minutes

4-1 Introduction to Neural Network22 minutes
4-2 Single-Layer Network and Perceptron Learning Rule15 minutes
4-3 Multi-Layer Perceptron, Back Propagation Learning, Decline of ANN10 minutes
4-4 Cascade Correlation Neural Networks, Deep or Shallow Structure23 minutes
4-5 Deep Learning: Convolutional Neural Networks17 minutes
4-6 LeNet 5, Dropout, ReLU and the Variants, Maxout, Residual Net18 minutes
4-7 Recurrent Networks, Long Short-Term Memory (LSTM), Neural Turing Machine, Memory-Augmented Neural Networks (MANN)15 minutes
4-8 Autoencoder: Denoising Autoencoder, Stacked Autoencoder and Variational Autoencoder12 minutes
4-9 Generative Adversarial Net (GAN), AE+GAN and Its Applications16 minutes

1 assignmentTotal 16 minutes

Week 4 Quiz16 minutes

What's included

7 videos1 assignment

7 videosTotal 136 minutes

5-1 Basic Term of Markov Decision Process, Sequential Decisions, Policy, Utility22 minutes
5-2 Derivation of Bellman Equation20 minutes
5-3 Value iteration and Policy Iteration22 minutes
5-4 Q-learning, Learning Policy,Simple GLIE Scheme24 minutes
5-5 Temporal Difference Algorithm,Generalization12 minutes
5-6 Deep Q-learning and Improvement12 minutes
5-7 Deep Policy Network, Partially Observable MDP,Summary22 minutes