We may earn an affiliate commission when you visit our partners.

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

于天立

4.6

Based on 61 ratings

, see reviews

于天立

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

Enroll now

Or subscribe to Coursera Plus

And get unlimited access to Coursera

Two deals to help you save

Save money when you learn. Here are two deals and offers that may be relevant to this course.

All coupon codes, vouchers, and discounts are applied automatically unless otherwise noted.

Valid until July 14

Coursera Plus Annual

Work toward what's next for your career with access to 10,000+ programs. Discover emerging skills and save.

Valid until August 30

Google AI App Builder

Learn how to use Gemini API and API Studio with a three-course series from Google DeepMind

What's inside

Syllabus

Concept learning

Computational Learning Theory

Classification

Traffic lights

Read about what's good

what should give you pause

and possible dealbreakers

Examines core ML techniques, including classifiers, neural networks, and reinforcement learning, relevant to AI

Covers topics such as computational learning theory and concept learning, providing a theoretical foundation

Progresses from浅層學習架構 to deep learning, showcasing the evolution of ML

Suitable for learners with a foundation in computer science

Recommended for learners with knowledge in data structures and algorithms

Save this course

Create your own learning path. Save this course to your list so you can find it easily later.

Save

Reviews summary

機器學習：理論基礎與重要概念

根據學生們的說法，這門「人工智慧：機器學習與理論基礎」課程提供了扎實的機器學習理論基礎，從經典的VC理論到最新的深度學習與強化學習都有涵蓋。講師的講解清晰易懂，能幫助理解複雜概念。然而，學員也指出課程偏重理論，實作較少，且需要一定的數學基礎，對初學者來說可能較具挑戰性。作業設計有助於鞏固知識，但難度較高。整體而言，課程適合想建立堅實理論基礎的學習者。

作業難度較高，能幫助深化理解

"作業很有深度，雖然花了很多時間，但寫完後真的學到很多東西。"

"作業的難度不低，但非常能幫助理解課程講的理論，是很好的練習。"

"為了完成作業，我需要回頭重看好幾遍講義和參考資料，學得很扎實。"

講師能清楚解釋複雜的理論概念

"教授講課非常清晰，能把複雜的數學概念用比較好懂的方式呈現，很厲害！"

"老師的教學非常有條理，跟著課程進度很容易理解，不會覺得聽不懂。"

"感謝老師把這些不容易懂的理論解釋得這麼好，讓我對機器學習更有信心了。"

深入探討機器學習的原理與理論

"這門課讓我對機器學習的理論有非常深入的理解，不只是學怎麼使用工具而已。"

"我覺得課程很強調從基礎原理出發，花了很多時間在推導和解釋理論。"

"如果你想打好機器學習的理論根基，這門課是個非常好的選擇，內容很扎實。"

"我過去只知道怎麼套用模型，上了這門課才真正理解背後的運作原理。"

課程偏重理論，實作程式碼部分較少

"這門課理論很強，但程式碼實作的例子和練習偏少，希望可以增加一些。"

"我學完理論後，還需要額外找資源來學習怎麼在實際專案中應用。"

"對於想立即應用在工作上的學習者來說，可能會覺得實作的部分不夠多。"

修課前需要具備一定的數學能力

"如果沒有微積分、線性代數和機率的基礎，學起來會比較辛苦，數學很重要。"

"課程中的數學推導真的不少，我需要花很多時間去複習數學才能跟上。"

"建議修課前先把數學複習一下，會學得更順利，不然可能會有點挫折感。"

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in 人工智慧：機器學習與理論基礎 (Artificial Intelligence - Learning & Theory) with these activities:

Connect with a mentor or expert in the field of machine learning

Show steps

Gain insights from experienced professionals and get personalized advice

Browse courses on Mentorship

Show steps

Attend industry events and meetups
Reach out to professors, researchers, or practitioners in the field

Review basics of probability and statistics

Show steps

Reinforce your understanding of the fundamental building blocks of machine learning

Browse courses on Probability

Show steps

Solve problems from textbooks or online resources
Revisit your notes and textbooks from a previous probability and statistics course
Look up online tutorials and do practice exercises

Participate in online discussion forums and collaborate with peers

Show steps

Connect with other learners, exchange knowledge, and get feedback on your ideas

Browse courses on Peer Support

Show steps

Join online discussion forums and introduce yourself
Ask questions, share insights, and engage in discussions
Collaborate on projects or assignments

Four other activities

Expand to see all activities and additional details

Show all seven activities

Follow guided tutorials on supervised and unsupervised learning

Show steps

Build hands-on experience with different machine learning algorithms and techniques

Browse courses on Supervised Learning

Show steps

Identify a few well-regarded online tutorials or courses
Follow the tutorials to implement algorithms and build models
Experiment with different parameters and datasets to observe their impact on model performance

Solve practice problems on machine learning algorithms

Show steps

Develop a deeper understanding of the strengths and weaknesses of different machine learning algorithms

Browse courses on Predictive Modeling

Show steps

Find practice problems on websites like LeetCode, HackerRank, or Kaggle
Attempt to solve the problems on your own
Review solutions and learn from your mistakes

Build a machine learning model for a real-world problem

Show steps

Apply your skills to solve a practical problem and gain valuable hands-on experience

Show steps

Define the problem and collect relevant data
Choose appropriate machine learning algorithms and train models
Evaluate model performance and iterate to improve results

Contribute to open source projects related to machine learning

Show steps

Gain practical experience and contribute to the advancement of the field

Browse courses on Open Source

Show steps

Identify open source projects on platforms like GitHub
Find areas where you can contribute your skills
Submit code contributions and participate in discussions

Career center

Learners who complete 人工智慧：機器學習與理論基礎 (Artificial Intelligence - Learning & Theory) will develop knowledge and skills that may be useful to these careers:

Artificial Intelligence Architect

Hold an integral role in the design and development of artificial intelligence systems. As the backbone of AI, your skills in machine learning, such as reinforcement learning, neural networks, and classification, are essential. This course may help you build a solid theoretical foundation and practical knowledge in these areas.

See salaries and explore the career path for Artificial Intelligence Architect

Data Mining Analyst

As a Data Mining Analyst, you extract raw data, convert it into valuable information to identify patterns, then, in turn, leverage those patterns to make sound business decisions. This course provides a comprehensive introduction to machine learning techniques that are vital for data mining, such as neural networks, classification, and reinforcement learning.

See salaries and explore the career path for Data Mining Analyst

Deep Learning Engineer

Deep Learning Engineers are experts in deep learning, a subfield of machine learning that has revolutionized AI. This course can help build a solid foundation in neural networks and deep learning, which are crucial technologies for deep learning engineers.

See salaries and explore the career path for Deep Learning Engineer

Artificial Intelligence Developer

As an AI Developer, you are responsible for the design and implementation of intelligent systems. This course provides a comprehensive introduction to machine learning techniques that are used in AI development, including neural networks, reinforcement learning, and classification.

See salaries and explore the career path for Artificial Intelligence Developer

Machine Learning Researcher

As a Machine Learning Researcher, you will push the boundaries of machine learning and advance artificial intelligence. This course may prove useful by providing a deep dive into the theoretical foundations of machine learning, including computational learning theory and reinforcement learning.

See salaries and explore the career path for Machine Learning Researcher

Computational Linguist

Computational Linguists apply computer science techniques to analyze and understand human language. This course may be useful in providing a foundation in machine learning, including neural networks, which are used in computational linguistics to process and analyze natural language.

See salaries and explore the career path for Computational Linguist

Machine Learning Engineer

Machine Learning Engineers bring artificial intelligence to life! Design and build machine learning models that bring automation to a wide range of tasks. This course may provide a useful foundation in machine learning basics such as reinforcement learning, neural networks, classification, and computational learning theory.

See salaries and explore the career path for Machine Learning Engineer

Computer Vision Engineer

Computer Vision Engineers combine computer science and machine learning to build powerful systems that see and interpret the world around us. This course may be useful in providing a strong foundation in deep learning and neural networks, which are crucial technologies in the field of computer vision.

See salaries and explore the career path for Computer Vision Engineer

Natural Language Processing Engineer

Natural Language Processing Engineers specialize in enabling computers to understand and generate human language. This course may be useful in establishing a foundation in neural networks and deep learning, which are essential technologies for natural language processing.

See salaries and explore the career path for Natural Language Processing Engineer

Robotics Engineer

Robotics Engineers design, construct, and maintain robots. This course provides a useful introduction to machine learning, including reinforcement learning, which is used in robotics to control and navigate robots effectively.

See salaries and explore the career path for Robotics Engineer

Quantitative Analyst

Quantitative Analysts use mathematical and statistical techniques to analyze financial data. This course may be useful in providing a foundation in reinforcement learning, which is used in quantitative finance to optimize investment strategies.

See salaries and explore the career path for Quantitative Analyst

Data Scientist

As a Data Scientist, you use advanced techniques and knowledge in the field of large data and use it to extract meaningful information. This course may help you establish a foundation in machine learning theory and techniques, including deep learning, classification, and reinforcement learning. These are fundamental aspects of large data analysis.

See salaries and explore the career path for Data Scientist

Software Engineer

A Software Engineer will solve business and technical problems through the design and development of computer software. This course helps build a foundation in the theory and application of machine learning, providing valuable knowledge in reinforcement learning and neural networks.

See salaries and explore the career path for Software Engineer

Computer Scientist

Computer Scientists conduct research and design innovative solutions across a wide range of computing disciplines. This course may provide a useful foundation in machine learning, including neural networks, which are used in computer science to solve complex computational problems.

See salaries and explore the career path for Computer Scientist

Cognitive Scientist

Cognitive Scientists seek to understand the human mind by studying the brain and behavior. This course can help build a foundation in the theoretical underpinnings of artificial intelligence, providing valuable insights into how the human mind works.

See salaries and explore the career path for Cognitive Scientist

Reading list

We've selected 12 books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in 人工智慧：機器學習與理論基礎 (Artificial Intelligence - Learning & Theory).

Pattern Recognition and Machine Learning

Save

這本書是模式識別和機器學習領域的經典教科書，內容涵蓋模式識別和機器學習的基礎理論、演算法和應用，適合作為本課程的補充教材。

(English) Pattern Recognition and Machine Learning...

Hardcover

$$$

(English) Pattern Recognition and Machine Learning...

Paperback

$$$

(English) Pattern Recognition and Machine Learning (text...

Unknown Binding

$$$$