Very nicely explained the mathematical topics, even for people like me with some phobia regarding large formulas. Useful hands-on experience with MATLAB coding, which I would have had to learn anyway.

So much like it. It gave me starting push in this interesting topic. And one important thing that after this course I figured out I need to continue dive into machine learning.

Excellent Machine Learning Lessons which need little advanced knowledge of mathematics.

It would be nice if it's taught in either python or R. So I do need to take extra effort to learn octave.

This course is absolute garbage. You get no feedback on your quizzes or assignments and the professor is one of the most boring I've ever seen. It's absurdly frustrating to repeatedly fail without any feedback as to why you're failing.

The lectures are clearly from a math perspective, as the prof simply draws what he's talking about on the slides. His hand writing is poor, and he does a lackluster job of explaining what exactly he's doing.

Finally, pure lecture with no notes is almost impossible to learn, as there's nothing to read and study.

I'd rate this course a 1/10, take the course on iTunes from Caltech instead.

However good the material and lectures may be, the use of an outdated version of Octave (which is not Mac-friendly and exceedingly brittle, to the extent where the supplied code requires manual patching in Windows and Linux) is a complete turn-off and makes it nearly impossible to complete the assignments on time unless you're prepared to spend at least twice as much time debugging your setup as doing the actual assignments.

I'll come back when this is done with R or Python.

good course; just 2 suggestions: improve the skew data part (week 6) and furnish the formula to evaluate the number of iteration in the window from image dimension, window dimension and step (week 11)

Very nice course,. Give a fundamental knowledge of machine learning in a clear, logic and easy-to-understand way. Suitable for those who has relatively weak background of math and statistics to learn.

so useful

This course could be a nice introduction and overview of the Machine Learning field.

However, the video transcripts are TERRIBLE — do not attempt to find any traces of grammar in them ! After a while I figured there were lecture notes (seriously, why hiding them under Resources ??? some people don't want to or simply can't watch the videos), but some of them lack information needed for the quiz so for some sessions you still have to watch the videos or endure the transcripts anyway.

But MOST OF ALL, the course has an incredible number of (acknowledged) errors, sometimes critical for the programming assignments, and you have to dig into the forum and Resources Erratas to figure them. Given that this lecture has been online at least since 4 years and some people actually PAY FOR IT, I find this utterly disrespectful, hence my low rating.

Furthermore, note that the validation script for ex5 is too permissive : it accepts wrong linearRegCostFunction implementations, which makes the second part of the assignment quite painful to debug…

Too many trainings and assignments without enough practice, exercise and examples. This can be very confusing for a person taking the course for the first time.

Truly an exceptional class. Not often will someone with a deep proficiency in a discipline have the time or incentive to share their insights and teach to others; this class is a rare exception, and given the vital importance of machine learning to the future, I have a great appreciation and debt to Andrew Ng.

Great class! Should be recommended for every individual who wants to learn machine learning and don't have time or oppotunity to take a class at their own univerisity, this class is a guidance for the basis of machine learning and gives me instructions where to go next. Thank Ng really much.

This course was very well taught. There was a impressive focus on the basics and fundamentals of each topic. The lecture slides encapsulates the topics well and thus there was no such need of making my own notes which speeded up the learning process ;).

This is course just awesome. You get everything you wanted from this course. It covers on all topics in detail, helps in getting confidence in learning all the techiques and ideas in machine learning.

The course will give you the incites to understand the data driven mathematical functions to write softwares that can behave or change its behavior, based on stimulus (data).

Andrew Ng is excellent

sehr gut!

If it was in python, then it would have got 5 star from me.

This course was very difficult, coming from a non-math/matlab background, but did teach me a heck ton about the world of machine learning, for which I am eternally grateful. Life got in the way big time, and it took a lot of time and energy to complete the programming exercises. There was also a lot I didn't understand, and I did wish there was maybe another week of getting used to certain concepts, particularly maths issues like double summing. I appreciate that this would complicate things though. I found that I am not geared towards the forums - my learning style involves conversation and not really experimenting on my own (which I can do once I understand a concept). As helpful as the mentors were, only relying on the forums with my time schedule meant that that taking this course dragged on longer than I would have liked. I also got a bit overwhelmed by the lack of centralised information. I know that it would require a complete overhaul to sort such out, but it did make looking up information time-consuming. Nevertheless, I am grateful for all that I learnt, and appreciate that I plunged into the deep end. I don't understand everything, and of course a little knowledge is a dangerous thing, but I know enough to know what to refer to should I ever need ML in my next job. Thank you.

Have to give a star so I will give it one. Others rate this course highly. I don't know why.

Course states no requirement for knowledge of linear algebra. However this is not really practical and seems disingenuous. I have spent a lot of time re-learning linear algebra.

I have spent much more time on the work than the course states and unless you are currently involved in similar work you probably will too.

I have never received any response to the feedback I provided.

Many times I have been frustrated because the math material is treated casually but then later success on quizzes and assignments are based how well you understand the math. So while the instructor and content can treat the math as casually as they wish, unfortunately, you cannot be so casual.

I would rename this course as Programming Octave with Application to Machine Learning rather that Machine Learning. Once you start the course you will have to focus on Octave rather than on ML topics if you want to do programming exercises. There is no degree of freedom in programming. You are provided with a lot of weird Octave codes which you will have to complete instead of writing yourself from scratch. More than 50% of my time was spent in order to learn Octave and understand (guess!!!!) Octave codes.

So, if you really want to learn ML and try it in practice this course is not for you. However, you could just watch the videos whose level is not more that elementary introduction to ML.

To set some context: I am a graduate (PhD) in Computer Engineering from the University of Texas at Austin with over 10 years of experience in both academia and industry. My goal in taking this course was to learn the basics of Machine Learning, and understand what the current excitement about ML and AI is all about. I dedicated 3-4 hours every week, over the last 12 weeks, towards learning this course — and watched all the videos, reviewed all the lecture .pdfs and completed all the project assignments and all quizzes in the course on time.

About the course: This is one of the best courses I have taken (and I have taken more than 10 courses on coursera, edX and Udacity). Dr. Andrew Ng needs no certificate of approval from anyone. He is clearly a wonderful teacher, and I felt I struck a chord with him. There are few people who can explain complex concepts clearly without over-simplifying. Some people don’t have the ability, and often those who do, don’t care enough. The difficulty often lies finding that boundary — the boundary where the complexity of a computation or a problem or a strategy can be abstracted out (with a black-box, or an analogy) and a student can make progress in thinking about the problem without getting bogged down. Dr. Ng does that very well in several places and my deepest respects to him for doing that.

Clearly, Dr. Ng is a pactitioner in the field. The material was very well structured, very well paced and presented in bite-sized modules. The project assignments were both challenging and quite realistic. I feel a tremendous sense of confidence having completed this course, and I hope to try out some ML challenges on the web in the near future.

Last, but not the least, I cannot appreciate Dr. Ng more for the effort and dedication he has put into the subject and into his teaching. I felt a touch of nostalgia as the course ended suddenly with the last video (which was very moving, btw) and there was no NEXT button to click on. Being an educator myself, I know it takes a LOT of time and effort in developing a course. After completing this course, I felt I owed it to Dr. Ng. to purchase the course. I feel proud and happy to be certified as his student.

Thank you, Dr. Ng.

Thank you coursera.

Extraordinary course for beginners (as well as for people with experience)!

If you are a beginner (as was I before taking this course), then this course is the perfect way to start learning Machine Learning. Even if you have some experience with ML, it'd be useful to learn about the recommended practices for choosing the right approach for a problem or something like debugging an algorithm.

Dr. Ng presents a huge amount of information in a structured manner, bundled with questions within videos that keep you focused. The quizzes and programming assignments complement the lecture videos. The programming assignments are in Octave. This is not necessarily a negative point (as other reviews are saying). If you are familiar with Python (or C/C++/Java etc), then it won't take you more than a few days at maximum to grasp the syntax of Octave. There is a lot of helper code in the programming assignments, so you mostly focus on the actual implementation of algorithms and such. Dealing with vectors and matrices in Octave has been a relatively better experience for me as compared to in Python. If you're stuck with programming exercises, then there are elaborate tutorials in the Resources section.

Possibly what I loved the most about this course is how Dr. Ng always mentions the recommended way of doing things (and how things are done in the industry). He also teaches you real life examples of how ML is currently being used by companies (for e.g. the course weeks on Recommender systems, Photo OCR, etc). So, if you're trying to learn ML for job prospects, this will be of great help.

Even though there's a fair bit of math (Linear algebra and some Statistics), Dr. Ng will help you walk through it and make you understand what you need to know.

Overall, this course has been a great help for a beginner like me. I recommend this to anyone who is looking for a course to start learning ML.

To Dr. Ng, the mentors of this course, and all the people who made this course possible, I want to thank you from the bottom of my heart. It's not easy creating so many hours of content (lecture videos, quizzes, assignments) and providing it online to thousands of people. I'm grateful for all your efforts.

This is a terrific class! The Course is well structured in terms of videos, invideo pop-up quizzes, course notes, programming exercises, and the discussion boards & mentor community. The 11 weeks includes 8 programming exercises, with usually 5-6 "code submittals" per exercise.

The option of OCTAVE or MATLAB is great (I used MATLAB). A key aspect of this course is using vectorized methods in every programming assignment. There was always an option to write a procedure approach (e.g. do loop for summation steps like sum of squared differences for gradient descent or linear regression). The computational advantage, the simplicity of using vectors, and ending with "crisp" code is a great step

I have completed a similar class from MIT (Python or R based) and the exercises in this class were far superior in reinforcing the course materials.

This journey takes you through Supervised Learning models leveraging Linear Regression, Logistic Regression, Neural Networks, and Single Vector Machines and how gradient descent is the cornerstone to determine the theta values needed to optimize your hypothesis. Unsupervised Learning using K-means, PCA, and Anomaly Detection. Specific real life example for Recommender Systems, Character Recognition and large scale machine learning.

The various topics on "advice" by Professor Andrew Ng is invaluable. Understanding how to measure performance of your algorithm is key. Underfitting (bias) and over fitting (variance), regularization, learning curves, evaluation (precision, recall, and F1), and error analysis. Of particular note, is his understanding how to objectively determine how to what to work on next and how to apply "ceiling analysis" in complex pipeline ML applications.

A final note, the course mentors are unbelievable! Tom Mosher and Neil Osgrove are truly special. Their understanding of the material, their patience, and their incredible responsiveness is highly beneficial to the learning experience. You have to do the work and figure it out, but the mentors are there to help you navigate the Machine Learning journey!

Really a great course. It covered a large variety of currently popular machine learning algorithms, along with strategies to do machine learning projects. Professor Andrew really goes deep into how to optimize a machine learning model to reduce bias and improve performance with a lot of techniques, not just simply implement a fancy machine learning algorithm. At first, I complained about programming assignments because it is done in Matlab, but after I went through some of them I really discovered that Matlab is a powerful tool used for a broad range of purposes. The course goes beyond just model.fit(x,y) and model.predict(x,y), because you'll learn the essence and mathematical proof of each ML algorithm to really comprehend how each algorithm work and how optimization work. You can still learn to build ML models in python even by yourself after this course.

However, there are still some problems I want to mention. First, for some algorithm in the second half of the class (e.g. SVM with Gaussian kernel, anomaly detection), professor Andrew didn't sufficiently mention how math works, just giving the conclusion of how we should implement. I understand that maybe it is because the mathematic proof is too complicate here or it is not necessary to know the mathematic for mastering this type of algorithm. But I still hope that I can have a deeper understanding of every model based on mathematics. Another thing is that programming assignments didn't teach us how to plot graphs. Our work is only limited to "backend" implementation, which is the completion of the algorithm using a mathematical approach. I still hope Professor can introduce how to plot different kinds of graphs to really integrate our knowledge on "backend" to "frontend" for further data analysis.

Again, this is a great course, and anyone who completes this course will gain a lot of insights on ML and will have a solid understanding for future ML studying. Thank you, Professor Andrew!