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

Ends today! This point in the year is perfect for 40% off 10,000+ programs. Save now.

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

Instructor: 于天立

10,931 already enrolled

Included with Learn more

Ask Coursera

5 modules

Gain insight into a topic and learn the fundamentals.

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.

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

Tools you'll learn

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 Algorithm11 minutes
1-4 Version Space and The List-Then Eliminate Algorithm13 minutes
1-5 The Candidate Elimination Algorithm15 minutes
1-6 Biased and Unbiased Hypothesis Space, Futility of Bias-Free Learning13 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 120 minutes

2-1 Introduction to Computational Learning Theory, Setting of Sample Complexity21 minutes
2-2 Setting 3, PAC Learnable11 minutes
2-3 Exhausting the Version Space: Definition, Theorem ,Proof and some examples19 minutes
2-4 Shatter, Dichotomy, VC dimension15 minutes
2-5 Some examples and discussion about VC dimension15 minutes
2-6 Upper and Lower Bounds on Sample Complexity with VC dimension, The Mistake Bound for Algorithms15 minutes
2-7 Optimal Mistake Bound14 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 114 minutes

3-1 Decision Trees and its Hypothesis Space17 minutes
3-2 Learning Decision Tree, Information20 minutes
3-3 Generalization and Overfitting, Kai Square Pruning,Rule Post-Pruning22 minutes
3-4 Model Evaluation: Metrics for Performance Evaluation, Methods for Model Comparison20 minutes
3-5 Ensemble: Embedding, Bagging and Boosting14 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 151 minutes

4-1 Introduction to Neural Network22 minutes
4-2 Single-Layer Network and Perceptron Learning Rule16 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 Scheme25 minutes
5-5 Temporal Difference Algorithm,Generalization12 minutes
5-6 Deep Q-learning and Improvement13 minutes
5-7 Deep Policy Network, Partially Observable MDP,Summary22 minutes

1 assignmentTotal 14 minutes

Week 5 Quiz14 minutes

Instructor

于天立

National Taiwan University

2 Courses31,986 learners

Offered by

National Taiwan University

Explore more from Machine Learning

Status: Free Trial
Politecnico di Milano
Learning with AI
Course

Why people choose Coursera for their career

Felipe M.

Learner since 2018

"To be able to take courses at my own pace and rhythm has been an amazing experience. I can learn whenever it fits my schedule and mood."

Jennifer J.

Learner since 2020

"I directly applied the concepts and skills I learned from my courses to an exciting new project at work."

Larry W.

Learner since 2021

"When I need courses on topics that my university doesn't offer, Coursera is one of the best places to go."

Chaitanya A.

"Learning isn't just about being better at your job: it's so much more than that. Coursera allows me to learn without limits."

Frequently asked questions

To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.

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.

Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.