Course Description

Machine Learning is now available in Coursera's on demand format! To watch videos and complete assignments at your own pace, join the on demand course now at: 

Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. Many researchers also think it is the best way to make progress towards human-level AI. In this class, you will learn about the most effective machine learning techniques, and gain practice implementing them and getting them to work for yourself. More importantly, you'll learn about not only the theoretical underpinnings of learning, but also gain the practical know-how needed to quickly and powerfully apply these techniques to new problems. Finally, you'll learn about some of Silicon Valley's best practices in innovation as it pertains to machine learning and AI.

This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI). The course will also draw from numerous case studies and applications, so that you'll also learn how 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.

No prerequisites for this course.

Write Your Own Review

Reviews on Springboard

  1. It's obvious why this course is so highly rated...

    Core machine learning concepts are covered in a thorough manner, elaborating on both the mathematics involved and the intuition behind the algorithms, yet without getting too caught up in the details. The course is very well structured and balanced throughout the 10 weeks which makes it easy to keep pace with. The lecture examples and programming assignments are very well chosen - both practical and highly stimulating. I particularly appreciated the 'skeleton code' approach to the programming assignments, as this consistently provided a nice starting point and framework for getting stuck into the 'meat' of the algorithms. My sincere thanks to Prof Andrew Ng for your willingness to share from your knowledge and expertise in this area. You deserve all the recognition you are getting and more for your involvement in Coursera and in particular for furthering the development of machine learning and AI in this 'digital age'.

  2. The best course I have ever taken

    It is the best course I have ever taken on MOOCs. You might not believe, but I enjoy it more than watching a movie. Because Dr Ng is excellent in his job. speaks very fluently, explains very simply so that you can completely make sense of the material and you have a good feeling inside. Programming assignments are really hard but if you can code everything from scratch in MATLAB or octave which is the goal of this course, you can fully understand what is going on, not being dependent on software programs to do it for you. I recomment it to everyone interested in machine learning. Even if you are not doing assignments, watch videos, learn and enjoy.

  3. The best CS course I have taken

    Amazingly clear lecture style, great quiz questions and awesome programming assignments make this class a standout. I feel like I have a very good grasp of a potentially difficult topic, all because Prof. Ng is an incredible teacher. By the end of the class, I was checking on Mondays to see when the new lectures were available and completing the whole section in a day or 2.

  4. This is the cutting edge technology, explained as to be used by common people.

    One of the greatest!

    Professor Andrew Ng is great, he makes you understand and doesn't try to make you feel dumb, he explains it all that you need to use Machine Learning without overwhelming you with mathematical complexities.

    This course has many of the greatest Machine Learning algorithms that you can use to work in many many applications.

  5. Practical advanced class

    This is not nearly as theoretical as the Cal Tech course, and the problems aren't as fun as the Berkley AI course, but it gives you a larger survey of techniques to apply to machine learning problems. One annoyance... the professor gets suddenly loud and suddenly soft because he moves away from the mic. Since this is the fourth iteration of the course, and he is the co-founder of Coursera, I would think he would have fixed this by now, but he appears to be using the same videos from the original class. I recommend having your hands near the volume control if you are sensitive to sudden noises.
    Some of this material is quite complex. The programming exercises are simplified due to this, but some can still be quite challenging. The professor often explains the material well, but sometimes he's a bit too casual about it.

  6. just great

    in one word perfect: enticing but at the same time not too difficult. the professor is just great and simplifies the concepts greatly.

  7. A great course with lots of practical applications!

    I had heard so much about this course from so many of my friends that I had to take it. This was one of the first courses I took on coursera and I completely loved it! I can easily give the credit for my getting hooked on to the online learning movement to this course. Andrew is a fantastic teacher and the course material is very well structured . There are lots of practical examples to excite the learner about the applications of machine learning. The course covers fairly advanced math, but it is so well explained that it never feels hard. I would highly recommend this course to anyone looking to pickup the fundamentals of machine learning.

  8. Great Course to begin with!!!

    Hi all, This was one of the first courses I took on Coursera. Great course, and great introduction to AI and Machine Learning. It is a little light on the Math, but overall a great course to begin with....

  9. Andrew Ng has a new fan !

    Andrew Ng, the founder of coursera is offering this course right from the very beginning. After having gone through introductory week 1 videos earlier, I thought of enrolling for this course which is currently running on coursera. Being from mechanical engineering background, I was not too keen on this subject of ML. But this time I enrolled for it on recommendation of my wife who is pursuing a Phd in computer science with NLP/ML being her core areas of research work.  It's really a great course from several aspects: Machine Learning fundamentals, review of mathematical concepts for so many elegant algorithms and a great way to get introduced to advanced programming environments like MATLAB/Octave. The difficulty levels are towards high end relative to other courses offered online, but Andrew offers a lot of tools and practical problems to keep you interested and persistent. A practical advice to successfully complete this course will be to keep pace on weekly basis with the content provided.

  10. The course which got me hooked on MOOCs

    I enrolled as I was starting a new job in a company which specialized in Machine Learning. This course gave me a great conceptual understanding and the basic practical skills I needed to hit the ground running. Andrew has put a tremendous amount of effort into the course. It is intimidating to non mathematicians, but I still think the first half of the course is accessible to a fair number of people, and you can drop out at the appropriate point. 

  11. Very helpful introductory course with several applications

    I enrolled because I just wanted to learn more about machine learning, which runs all the products we use today (e.g., google search, amazon recommendations). The course starts from the beginning so you don't need to be an expert in machine learning, but a basic background in CS and programming does help. Very quickly, I got hooked to the course and ended up completing exercises and problem sets, that I wasn't planning on doing initially. This has really helped me understand how products that we use every day work. I highly recommend it!

  12. Excellent learning and practical knowledge for students, very thoughtful and committed instructor.

    This course is taught by Andrew Ng, who is among the world's leading experts on machine learning. This is the third best thing about this course. A lot of thought has gone into designing the course for the benefit of students. The course covers most of the core machine learning algorithms, and the assignments involve implementing the same, and have parts that are quite challenging. Usually, implementing algorithms from scratch can be a big impediment, with the difficulty involved causing students to give up. On the other hand, using a machine learning library would not provide students a deeper understanding of why and how the algorithms actually work and the tradeoffs involved. In this course, the key is that the assigments come with skeleton code for the algorithms, which the students can build on. It is still challenging, but students get an encouraging start, immediate validation for their learning, and a first-hand feel for the power of machine learning. In practical applications of machine learning, how do teams decide between gathering more data, engineering better features, or exploring a different or more sophisticated algorithm? These are questions that may be tied to huge amounts of time and resources, and Prof. Ng provides valuable lessons with real world examples of typical and costly mistakes, and a mindset/approach that improves chances of success.