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

Machine Learning

Andrew Ng

Enroll now

Or subscribe to Coursera Plus

And get unlimited access to Coursera

Here's a deal for you

Save money when you learn with a deal that may be relevant to this course.

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

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

Traffic lights

Read about what's good

what should give you pause

and possible dealbreakers

Taught by Andrew Ng, who is recognized for his work in Deep Learning

Develops machine learning, datamining, and statistical pattern recognition skills, which are core skills for data scientists

Teachers students to apply learning algorithms to building smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas

Examines best practices in machine learning and AI, which are highly relevant to industry

Offers a broad introduction to machine learning, datamining, and statistical pattern recognition

Teaches students to implement and get machine learning techniques to work for themselves

Save this course

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

Save

Reviews summary

Foundational ml: strong theory, outdated tools

According to students, this "Machine Learning" course offers a foundational and comprehensive introduction to the field. Many learners praise the instructor, Andrew Ng, for his exceptional clarity in explaining complex topics and mathematical concepts. The course is widely regarded for building a strong theoretical understanding of algorithms from first principles, preparing learners to understand the 'why'. However, a significant number of reviews highlight that the use of Octave for programming assignments feels outdated and can be a barrier to practical application in current industry settings, where Python is dominant. While excellent for its core principles, some recent feedback suggests it lacks depth in modern deep learning techniques.

Ideal for newcomers, potentially slow for experienced learners.

"Great for beginners, but intermediate learners might find it slow."

"It's a great stepping stone for anyone starting in ML."

"Good course for beginners to understand the mathematical underpinnings of ML."

"This course provided me with a basic overview, but as someone with some prior experience, it felt a bit simple."

Hands-on assignments reinforce theoretical concepts effectively.

"The Octave/MATLAB programming assignments really solidify the concepts and give you hands-on experience."

"The assignments are challenging but rewarding."

"The Octave assignments might seem like a barrier to some, but they truly help in understanding the underlying mechanisms of the algorithms."

Andrew Ng excels at explaining complex topics clearly.

"Andrew Ng is a fantastic instructor, explaining complex topics like backpropagation and SVMs with such clarity."

"The lectures are well-structured, and the instructor is very knowledgeable."

"Ng's explanations are legendary. The lectures are incredibly clear and the way Andrew Ng breaks down complex math is brilliant."

"Still the best introductory ML course out there. The instructor is amazing."

Builds a deep understanding of ML algorithms from scratch.

"Seriously, if you want to understand the *why* behind machine learning algorithms, this is the course."

"This course is absolutely foundational for anyone getting into ML. ... the theoretical understanding gained is invaluable."

"It focuses on intuition and mathematical understanding rather than just using black-box libraries. This approach gives you a solid base."

"I appreciate the focus on first principles. I learned how to understand the mathematical underpinnings of ML."

Course lacks depth in current deep learning techniques.

"The course could also benefit from more advanced topics or deeper dives into neural networks beyond the basics."

"Some topics felt a bit superficial, especially modern deep learning."

"I expected a modern ML course, but this was all about Octave and basic algorithms. It doesn't prepare you for real-world projects with Python and deep learning."

Use of Octave is a major drawback, lacking modern relevance.

"My main gripe is the use of Octave instead of Python; it makes applying concepts to modern ML tasks a bit cumbersome."

"I found the Octave labs were a real pain. It felt like I was learning a new tool just for the course."

"Honestly, this course feels outdated. While the foundations are there, modern ML is almost entirely done in Python...Learning Octave felt like a waste of time."

"The only downside is the outdated programming environment (Octave) which makes it less practical for immediate application in industry."

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 Machine Learning with these activities:

Meet with other students to discuss machine learning concepts.

Show steps

Provides opportunities to engage with peers, share insights, and reinforce learning.

Browse courses on Machine Learning

Show steps

Find other students who are interested in machine learning.
Schedule a time to meet.
Discuss machine learning concepts and share ideas.

Tutorials on data structuring

Show steps

Will help reinforce learning about neural networks.

Show steps

Find a tutorial on neural networks.
Follow the tutorial and complete the practice exercises.
Apply what you learned in the tutorial to a personal project.

Read Michael Nielsen's Neural Networks and Deep Learning

Show steps

Will give you a comprehensive understanding of neural networks.

Show steps

Read the book.
Complete the exercises in the book.
Write a short summary of the book.

Two other activities

Expand to see all activities and additional details

Show all five activities

Solve coding challenges related to machine learning.

Show steps

Will help strengthen problem-solving skills in machine learning.

Browse courses on Machine Learning

Show steps

Find coding challenges related to machine learning.
Solve the coding challenges.
Review the solutions to the coding challenges.

Develop a machine learning model to solve a real-world problem.

Show steps

Provides end-to-end experience on applying ML to real-life scenarios, fostering deep understanding and expertise.

Browse courses on Machine Learning

Show steps

Identify a real-world problem that can be solved using machine learning.
Collect and prepare a dataset.
Design and implement a machine learning model.
Evaluate the performance of the model.
Deploy the model.

Career center

Learners who complete Machine Learning will develop knowledge and skills that may be useful to these careers:

Data Scientist

Data Scientists leverage statistical analysis, optimization methods, and computer science to extract value from data and solve complex business problems. Machine learning is essential to this role as it enables Data Scientists to develop algorithms that can learn from data and make predictions. This course provides a strong foundation in supervised and unsupervised learning techniques, which are essential for a successful career in Data Science. Furthermore, the course's emphasis on practical application will prepare you to effectively implement and deploy machine learning models in the real world.

See salaries and explore the career path for Data Scientist

Machine Learning Engineer

Machine Learning Engineers are responsible for designing, developing, and deploying machine learning models. This course provides a comprehensive overview of machine learning techniques, including supervised learning, unsupervised learning, and best practices in machine learning. The course's hands-on approach will help you build a solid foundation in machine learning engineering and prepare you for a successful career in this field.

See salaries and explore the career path for Machine Learning Engineer

Artificial Intelligence Engineer

Artificial Intelligence Engineers design, develop, and maintain AI systems. This course provides a solid foundation in machine learning, which is a key component of AI. The course will help you develop the skills needed to build and deploy AI systems that can solve complex problems and automate tasks.

See salaries and explore the career path for Artificial Intelligence Engineer

Data Analyst

Data Analysts collect, analyze, and interpret data to help businesses make informed decisions. This course provides a strong foundation in machine learning, which is increasingly used by Data Analysts to extract insights from data. The course will help you develop the skills needed to analyze data, identify trends, and make predictions that can drive business growth.

See salaries and explore the career path for Data Analyst

Software Engineer

Software Engineers design, develop, and maintain software applications. Machine learning is becoming increasingly important in software development, and this course can help Software Engineers build a foundation in this field. The course will help you develop the skills needed to incorporate machine learning into software applications and create innovative solutions.

See salaries and explore the career path for Software Engineer

Product Manager

Product Managers are responsible for defining, developing, and launching new products. Machine learning is increasingly used to create new products and improve existing products, and this course can help Product Managers build a foundation in this field. The course will help you develop the skills needed to understand the potential of machine learning and how to incorporate it into product development.

See salaries and explore the career path for Product Manager

Business Analyst

Business Analysts help businesses understand their needs and develop solutions to improve their operations. Machine learning is increasingly used to improve business processes and make better decisions, and this course can help Business Analysts build a foundation in this field. The course will help you develop the skills needed to understand the potential of machine learning and how to incorporate it into business analysis.

See salaries and explore the career path for Business Analyst

Operations Research Analyst

Operations Research Analysts use mathematical and analytical methods to solve business problems. Machine learning is increasingly used to solve complex operations research problems, and this course can help Operations Research Analysts build a foundation in this field. The course will help you develop the skills needed to understand the potential of machine learning and how to incorporate it into operations research.

See salaries and explore the career path for Operations Research Analyst

Quantitative Analyst

Quantitative Analysts use mathematical and statistical methods to analyze financial data. Machine learning is increasingly used to develop trading strategies and make investment decisions, and this course can help Quantitative Analysts build a foundation in this field. The course will help you develop the skills needed to understand the potential of machine learning and how to incorporate it into quantitative analysis.

See salaries and explore the career path for Quantitative Analyst

Statistician

Statisticians collect, analyze, and interpret data. Machine learning is increasingly used to develop statistical models and make predictions, and this course can help Statisticians build a foundation in this field. The course will help you develop the skills needed to understand the potential of machine learning and how to incorporate it into statistical analysis.

See salaries and explore the career path for Statistician

Computer Scientist

Computer Scientists design, develop, and analyze computer systems. Machine learning is a subfield of computer science, and this course can help Computer Scientists build a foundation in this field. The course will help you develop the skills needed to understand the principles of machine learning and how to develop machine learning algorithms.

See salaries and explore the career path for Computer Scientist

Mathematician

Mathematicians study the properties of numbers, shapes, and other abstract concepts. Machine learning is a mathematical discipline, and this course can help Mathematicians build a foundation in this field. The course will help you develop the skills needed to understand the mathematical principles of machine learning and how to develop machine learning algorithms.

See salaries and explore the career path for Mathematician

Physicist

Physicists study the laws of nature. Machine learning is increasingly used to solve complex physics problems, and this course can help Physicists build a foundation in this field. The course will help you develop the skills needed to understand the potential of machine learning and how to incorporate it into physics research.

See salaries and explore the career path for Physicist

Biologist

Biologists study living organisms. Machine learning is increasingly used to analyze biological data and develop new drugs and treatments, and this course can help Biologists build a foundation in this field. The course will help you develop the skills needed to understand the potential of machine learning and how to incorporate it into biological research.

See salaries and explore the career path for Biologist

Economist

Economists study the production, distribution, and consumption of goods and services. Machine learning is increasingly used to analyze economic data and develop economic models, and this course can help Economists build a foundation in this field. The course will help you develop the skills needed to understand the potential of machine learning and how to incorporate it into economic research.

See salaries and explore the career path for Economist

Featured in The Course Notes

This course is mentioned in our blog, The Course Notes. Read two articles that feature Machine Learning:

5 New Specializations that Teach You Future-Proof Skills

7 minute read

Learn AI: Machine Learning and Deep Learning Online Courses

18 minute read

Reading list

We've selected 28 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 Machine Learning.

Probabilistic Machine Learning

Save

Provides a comprehensive overview of machine learning from a probabilistic perspective. It covers a wide range of topics, including supervised and unsupervised learning, and provides a rigorous mathematical foundation for the field.

Probabilistic Machine Learning: Advanced Topics...

Hardcover

$$$$

The Elements of Statistical Learning

Save

Classic textbook in the field of statistical learning and provides a comprehensive overview of the topic. It covers fundamental concepts, algorithms, and applications in a clear and concise manner.

The Elements of Statistical Learning: Data Mining,...

Hardcover

$$$

The Elements of Statistical Learning: Data Mining,...

Hardcover

$$$

The Elements of Statistical Learning: Data Mining,...

Kindle Edition

$$$