An excellent introduction into essential machine learning techniques. The
course is very rich in content, and covers a lot of ground, but doesn't ever
devolve into empty hand-waving. The course favours practical approach to
machine learning, and will often skip the theory and/or underlying principles
(leaving formula derivation as a purely optional exercise for those interested
in this aspect of ML). Prof. Ng is obviously enthusiastic about the subject,
and the course as a whole feels very polished. On the downside, the
programming assignments are not very challenging and do not require any
creativity, as they boil down to following very detailed instructions. The
assignments remain quite instructive despite that, as there's a lot of support
code meant to visualize the results and provide various statistics to help
students understand how does everything work. This doesn't seem to be an
oversight or anything like that, but rather conscious course design as a 'ML
cookbook'. Since going through this class last spring I actually employed a
few of the techniques taught in my day-to-day work, and this class was
instrumental in sparkling my newfound interest for statistics. Required
skills: elementary algebra, coding skills Recommended skills: first-order
logic, linear algebra, probability & statistics, multivariate calculus, Octave
Workload: low Difficulty: low Value: high Fun: high
Great introduction, though not enough practical work. Most of the programming is done in Octave, which is limiting. I found my self taking the coursework and redoing it in Python to better understand it.
Of longstanding renown in the MOOC world, Stanford's machine learning course really is the definitive introduction to this topic. The course broadly covers all of the major areas of machine learning -- linear and logistic regression, neural networks, support vector machines, clustering, dimensionality reduction and principal component analysis, anomaly detection, and recommender systems. As with every other Stanford course I've taken, Prof. Ng precedes each segment with a motivating discussion and examples. Graded portions of the course include a quiz after every topic and a programming assignment, in MATLAB/Octave, after most of them.
The programming assignments are excellent. Although 95% of the code comes to you pre-written, what you write really goes to the heart of that week's topics. Given the breadth of the course, these assignments nicely provide depth and meaningful rigor. The quizzes are very fair and sometimes nicely open your eyes to subtleties of the topic you may not have appreciated.
Machine Learning has migrated along with all Coursera courses to their new platform, which offers the benefit of "on demand" scheduling flexibility (you can start whenever you want) but has some unfortunate downsides. Chief among these is the fact that the quizzes provide no feedback (as they used to) and can be taken as many times as you want. With enough persistence, anyone can score 100% in the course. These are minor deficiencies, however, and don't detract from this course's well-deserved reputation.
Those who take and enjoy Machine Learning should consider following it up with The Analytics Edge, an MIT course offered through edX. The Analytics Edge is more about applying data analytics, including but not limited to machine learning techniques, to a wide variety of real-world problems. It's a great complement to this course, leading you through the many ways data can be parsed and processed to illuminate, predict and explain.
This class is a great introduction for anyone interested in machine learning as it lays out the fundamentals in an easy to understand format. Andrew Ng is the chief scientist at Baidu and is well known in the fields of machine learning and artificial intelligence so you can rest assured you're learning from the best!
Great course to begin machine learning, using MATLAB archive assignment. Although it does't provide enough theory, it gives an intuition of machine learning. After this course you will be more comfortable to learning some deeper class in this area.
This course is very helpful as introduction to Machine Learning. Mr Ng did a great job! The best course on Coursera I took so far. I hope to see another, more deep course related to Machine Learning by Mr Ng.
Great course, Dr. Andrew takes baby steps approach to advance in the course. What I really like about the course is it's greatly organized and the mentors will have all your questions answered. In addition to that all the previous courses of this course were used as lesson learned, so you will find a long forum of errat, best practice and tutorial that 85% will have your issue solved before you think about using the forums. One thing to the new learners, this course requires a bit of time commitment so keep that in mind. I am planning to continue the learning and I am taking Neural Networks for Machine Learning now from the Univ. of Toronto.
Join our mailing list for course updates, discounts and more.
Enter your email address here.
Student rates this course 10/10 starsCompleted
This is the best online training experienced. The method of Coursera app on online training is amazing. It never felt like remote learning. A complex subjects is made easy by Prof Andrew. Many thanks for this course and all the effort by everyone involved including prof Andrew.
Prof Andrew is the best!
Wonderful introduction to Machine Learning. Andrew Ng takes you step by step through the processes and even without any prior experience or knowledge of MatLab, within 5 weeks you'll be building neural networks to recognize faces. Each project is extremely well organized and Andrew is great at explaining complex concepts and gives you great practical advice. I highly recommend his course.
Excellent course for people who start in the machine learning field. It covers the necessary basics that you can continue to study by yourself in the future. Prof. Andrew explained the concept and workflow really well. I do highly recommend this course for any new ML starter.
I have to say that Andrew Ng is one of the best teacher I have ever had. He makes difficult subject very easy to understand. Content wise, I think it is a good introduction to machine learning algorithm.
I took this course without previous knowledge about Machine Learning. I found it very interesting and motivating. The content is very useful and the progress in the topics is very well given. Along the course some mistakes appear, but they are corrected in the errata webpage.
This is a very good course for someone who has no prior knowledge in machine learning. The course is really hands on, you will get to internalize the material by doing the weekly assignments. Although the course doesn't require any pre-requisite knowledge but you should have good understanding of matrices in algebra to really understand the proofs.
This was my first course in Machine Learning and am really glad to have taken this course to get introduced to ML. The instructor was excellent and inspirational. The best part to me was the intuition behind the algorithms. There was the right balance between mathematics, concepts and practical implementation. The programming exercises were interesting and at the right level of complexity. All in all, a great introductory course to Machine Learning and I will strongly recommend it to all ML / Data Science aspirants.
The course is a "Life - Changer" ! Andrew Ng is the best professor I have ever had. He is the reason I have decided to pursue my masters in machine learning. He breaks a complex concept down into chunks which are simpler to understand and thereby explaining that concept. I feel like I can apply this knowledge to any domain, be it robotics, finance, biology, etc. Do go for this course, because it'll change your life. It has changed mine.
This is the best course on Coursera. I'm happy to see it become a self-paced class for everyone, but I believe that it should run regularly as well, since the course like this deserves to go live. The self-paced look of Coursera courses isn't as good as the live one, and this course focuses on Octave/Matlab programming assignments, which are a better fit to a live course. However, this is just a platform-choice critique, the course itself is simply amazing. However, watch out - it's not a beginner's course. Previous experience in linear algebra is strongly encouraged, and programming experience is required, otherwise you'll get stuck in the beginning. Huge recommendation!
One of the best ongoing online course on Machine Learning. Covered almost all aspects related to machine learning. I have studied Neural Networks during my masters but this course helped me a lot to understand basic concepts and other Machine Learning techniques.
Its a good course for someone that never learned Machine Learning (like me :)). The workload is pretty small: about 2-3 Hrs a week (if you complete the course in 11 weeks), and you get exposed to a lot of ideas and algorithms in the field. I really liked the fact that programming assignments where presenting real problems that seems not trivial at all, in example: character recognition and image compression.
On the downside - the programming assignments requires very little thinking and give only a taste of the topic, and not a practical ability. overall - I enjoyed this course :)
A great course! The lecturer is very thorough, patient and encouraging. The in-video quizzes are challenging and very relevant for knowledge acquisition check, just like the programming assignments.
It would be good if the course was even more encompassing, so it would cover Bayesian learning, decision trees, ensemble models, etc. Otherwise, an excellent choice for anyone into machine learning and data science.
This was an awesome course! I am a computer graphics software developer and my objective in taking it was to understand enough about machine learning to solve my own problems. The course exceeded my expectations.
It is not terribly math-intensive so you can follow most of the material if you have some understanding of linear algebra. (As compared with the CalTech "Learning From Data" course which is more mathematical and actually goes thru proofs of the formulas that are just given to you in this course.)
The exercises use MatLab (or Octave) but you are given enough information to solve them if you are not familiar with these languages. If you have been looking for an excuse to find out more about MatLab this course is perfect. If you want to know how to program neural nets in C++, you won't learn that here.
Covered a broad range of topics in modern day machine learning; but most importantly it started from a fairly simple concept - how to iteratively solve a derivative - that anyone having done higher level maths in high school would have been familiar with already. From there on it once you get that then it is just adding on various tweaks and related concepts. You get a focus in this course on the practical part of doing such analysis - that is the problems/pitfalls of each technique, what are its uses/misuses, how to "tune" the parameters of each technique to your liking etc. So all very useful for someone looking to actually implement this stuff, in real life!
Prof Ng is first and foremost an extremely good lecturer - I have never experienced US-style education but thanks to this course I badly wished I had done my undergrad in the US. Always breaking down difficult/annoying concepts to its basics, going through carefully each equation - he is exactly who you might need to get through such a technical topic.
Coursera might not be as polished as EdX but it has some good courses. This
one which is the grand daddy of all of those is no exception. Very engaging
and interesting - even if you are not a programmer.
This is one of the best MOOCs out there, folks. If you're interested in
Machine Learning, have the tenacity to install and learn how to use Octave or
Matlab, and have at least 10 hours a week to devote to watching lectures,
doing quizzes and programming assignments, I can't recommend this highly
enough. I'm sad that this class will be over for me in just a few short
Rankings are based on a provider's overall CourseTalk score, which takes into account both average rating and number of ratings. Stars round to the nearest half.
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.