Full disclosure: I am a mathematician, and therefore already well-trained in linear algebra, and I'm only 6 weeks into this course.

This course has been a near-perfect introduction to neural networks. Great pedagogical decisions were made to gradually bring the student from basic linear regression to motivating why a neural network is a logical next step to improve this process. This course has made me fluent in important terminology to deep learning and data analysis like bias, variance, precision, recall, and so much more. Not to mention, I've learned MatLab/Octave from scratch, which has turned out to be a nice programming language to add to my collection.

A caveat for non-mathematicians, or for that matter anyone not fluent in linear algebra: the neural networks will be a struggle. Some of the formulas relating to these may also be frustrating because I expect you won't understand why they work, or how to debug your code. I strongly recommend that you consider a rigorous linear algebra course, as a co- or pre-requisite.

To mathematicians: this course is a great starting-off point for learning about neural networks and other machine learning concepts. I already see applications to and from my research. In addition, I am able to explore the literature and decide on avenues for further exploration. Andrew Ng has truly provided a gift here to us.

I had always heard great things about this class during my research on what online courses to take next in my path towards becoming a data scientist. I was hesitant because it used Octave, a program I didn't think was going to be useful in my future roles. Then I completely bombed a phone interview in which they asked me the specific steps behind linear regression, and about gradient descent and the cost function. And I realized I didn't really know much about how these algorithms worked, although I used them in my day-to-day projects as a data analyst. So I finally decided to take this class, and after 11 weeks I can say that I experience WAY LESS imposter syndrome than before. I've still got a lot more to learn, but I'm confident that with everything Andrew Ng taught in this course, I will be able to hit the ground running on many other courses, with a thorough understanding of tools to use and the best ways to use them. In the end, Octave was just a little tiny component of a very scope of knowledge you'll attain after finishing this course. So if you're hesitant to take this course because of that, please don't be! I'm really grateful a course like this exists in a way that is easy to understand and is buildable. I'd consider this one of the best uses of my time outside of work, and I'd do it all over again now knowing what I have to gain from it.

This was my first on line course and the experience has been amazing. The lectures by Prof Andrew Ng were clear and the follow up programming exercises helped reinforce and enhance the concepts covered in the lectures.

The entire course was very well organized - videos, notes, discussion groups, suggestions and tips by the mentors was very easy to follow.

The focus of this course is on the practical application of machine learning techniques (supervised learning mostly but also some non supervised learning). Prof Andrew tries not to get into the advanced mathematical concepts but instead provides good intuition and then shows one how to apply the different ideas underpinning machine learning with some practical examples. In my view, this is an excellent way to quickly become familiar the concepts and to see machine learning in action. A student of the course will gain very good insights and can then follow up with the underlying math as needed.

The final two lectures on how to scale machine learning to large systems and a suggested systematic framework for figuring out which aspects of the design to focus on were very instructive.

In summary, i would highly recommend this course to anyone interested in the area of machine learning. Be prepared to work through some challenging (but very worthwhile) programming exercises to get the most out of the course.

It is a very nice introductory course in machine learning. It teaches a good range of machine learning algorithms and good advices on how to implement them effectively. At the end of the course I feel like I am ready to tackle some machine learning projects on my own and I am sure many others who finished will too.

For someone with a strong mathematical background like me (Have a undergraduate degree in maths and theoretical physics), the maths component is lacking. There are little derivations on equations and feels like I could've understood some of the algorithms deeper and instructor cannot teach it here. It feels especially true in supper vector machine. Also if you are strong in linear algebra and really familiar with matrix multiplication rules you can vectorize some implementation very effective and reduce what could be five lines of codes to one.

For someone without a strong mathematical background, I think the main difficulty is going through the messy indexing in equations and actually implementing algorithms with a lots of for-loops. It is also hard to fully understand some concepts behind some algorithms like support vector machine and relate the resulting algorithm with the concept.

I enjoyed the course a lot and really have learnt a lot. Now I feel ready to start some machine learning projects on my own and dive deeper into this field.

I love this course. It's my highly recommendation to everyone who wants to learn machine learning. Machine learning is definitely the state-of-the-art topic, but it would be difficult to learn because it combines the linear algebra, calculus, programming skills, algorithms, etc. There are tons of threads for learners to get distracted from the main theme they need to focus on. That's why I am amazed by Andrew's machine learning course. It's so amazing that Andrew just makes a very complicated topic very easily understandable and very easily to learn. What's more, whether learners have learned calculus or programming or not, they can still easily understand the mechanism of various machine learning algorithms even though some proofs of the formula are not discussed. Moreover, this course does cover many most well-known machine learning algorithms. I enjoy this course a lot and I am so eager to learn more in the last few lessons. Thank you very much, Andrew. You definitely give me one of the best courses in my life.

這是一門我非常喜歡的課程，誠摯地推薦給每一位真心想學習機器學習的學員們。雖然機器學習絕對是當代最新穎、極重要的議題，但它結合了線性代數、微積分、程式設計及演算法等學問，機器學習其實是並不容易讓人親近，有好多的面向須顧及，所以自學時往往容易失焦，而不很能夠明白機器學習的作法及重點何在。而這也是我對吳恩達老師感到欽佩之處，吳恩達老師的教學，簡言之，深入淺出。即使學員沒有相關的背景，不曾學過微積分或是程式設計都無妨，幾個重要的機器學習的方法仍是能清楚明瞭，即使有些證明在課堂上並未提及。難能可貴地，幾個重要的機器學習方法，這門課程都有含括。我很享受這門課程，而且當課程將盡時，渴望著學習更多相關的事物。感謝您，吳恩達老師！感謝您給了我人生之中一門美好的課程。

Andrew Ng’s ML course is a great introduction to ML. The course covers fundamental learning algorithms in the right amount of depth for the student to gain an intuition for mathematics and applications of the algorithms. While the course can be completed without much knowledge in either Linear Algebra and Calculus, to truly understand the learning algorithms a solid foundation in both is necessary.

The video lectures are succinct and focus on a singular topic which makes it easy to make progress and pinpoint the exact material that needs review. Andrew is honest about what you need to know and provides extensive explanations from problem motivation, intuition, mathematics, and applications.

The assignments are challenging but not overwhelming (except for the Neural Network assignment). The test cases, tutorials, discussion threads, and handouts provided enough support to make assignments enjoyable.

The quizzes are short and the ability to retake the quizzes make them stress free. The questions are derived from the course materials so a quick review of the videos and lectures were sufficient preparation.

By the end of the course, the student will feel comfortable diving deeper into learning algorithms of interest and applying them to projects. I highly recommend this course for those who are new to ML and want to get up to speed quick!

Exceptional course. Demanding in terms of time required to complete properly, but worth every second. Future students beware: going through this course is a double-edged sword. You'll suddenly want to solve any problem you have at work/school with some application of ML. If this course is your first comprehensive introduction to ML then expect to utter the phrase "...well now this changes everything" on multiple occasions. Next thing you know you'll be buying books on Amazon trying to learn Python in your spare time so you can REALLY do some ML damage with all the importable libraries.

Structure of the course is perfect. He segments the lectures into a reasonable length, allowing you to bite off a little at a time. There is even the option to roll over into the next class if life throws you a curve-ball. You get the sense that he wants you to succeed and finish the class, and him giving students the chance to extend their enrollment indefinitely supports that assumption.

Take the class. Expense it. Count it towards your annual training budget. Your boss [should] be VERY enthusiastic about you asking for training that costs under $100. It's an easy choice: you can pick 12 weeks of in-depth lectures, notes and hands-on learning OR continue trying to sell your boss on that 2-day, $2500 conference in [whatever city it is this year].

Machine Learning from Stanford by Andrew NG is the cornerstone of online courses for Machine Learning - for multiple reasons.

As a non-technical founder looking to further my knowledge and comprehension of the complex AI landscape, AI for Everyone from Andrew felt not enough. Andrew's Machine Learning course finally gets our feet wet with algorithms and the fundamental, underlying mathematics to Machine Learning.

Though intimidating at first, Andrew's Machine Learning class is properly paced, and has the necessary tools and resources to get you through the class without feeling lost. The pacing is adequately supported by quizz that force the learner to conceptualize his learnings to deduct proper reasoning.

Don't kid yourself, this course remains a beginner entry into the AI field and one should expect to take a further dive into more advanced courses of Mathematics, Data Science, Python, Machine Learning & Deep Learning with the ultimate goal to have the ability to create your own ML/DL systems.

The programming assignments in Octave were a bit bleh - as they will unfortunately not translate to production / prototyping environments which are for the most part in Python.

Andrew is a great teacher and makes the complex field of AI feel attainable for driven, smart people from any background.

Best of luck in your journey!

An approachable introduction I recommend to anyone and everyone that at the least has matrix algebra under their belt. I took this with the intention of reviewing material, yet many concepts I had previously been exposed to were approached in such a clear manner that it felt brand new to me. I'm shocked at how much more clarity this course offered than my university! Moreover, it is absurd that I did a lot more work in my machine learning university course, yet never saw it pay off in an interview. This course was far less work (i.e. less time-consuming), but the pay-off knowledge-wise for interview questions has been demonstrably far far more time-effective. I highly recommend this course if you are limited on time and want a course to give you an edge in interviews. The big downside of this course is that there is no term project. In my case that was fine since I already have ML projects under my belt and needed to review all ML concepts at a general level, but if you don't have any noteworthy ML projects and are looking to dive into one, I'd still highly recommend this course (so many problems I can point out now with my ML projects in interviews for instance!!) but know that you'll want to move onto another project-focused course or a personal ML project after this for sure to get yourself ML-interview ready ;)

This is by far the best Coursera (or any MOOC) class I've taken. The production values are low, but the content is excellent. Professor Ng explains everything very clearly. The best part is the homework. Each assignment is explained in detail and the assignments lead you in small steps to make measurable progress as each step is accomplished. The 5-6 page PDF that accompanies each programming assignment provides all the information needed to fully understand what you are being asked to accomplish. I have had MANY other MOOC's where the information in programming assignments amounts to a few sentences embedded in a Jupyter notebook and students are forced to search through numerous forum questions and answers to get an explanation of what you are really being asked to do. Not in this course! Everything is explained very well. I might also mention that while most other machine learning courses are taught at a very high level, using Python and Scikit learn or other ML packages that do the heavy lifting, this course has you actually implement ML programs at a very low level, using linear algebra and vector math so that you really get to see how these higher-level packages implement the detailed algorithms. No black boxes here. I HIGHLY recommend this course to anyone interested in machine learning.

First of all I'm so thankful to Andrew NG for this wonderful course and I'll always be in debt to him for this masterpiece. At the very start, when I was just starting out, I was really unsure whether this would be the right course for me as this is an 11 week course. I was also concerned about the usage of MATLAB/ Octave over Python. But choosing this course, I realized it didn't really matter given that you know how an algorithm is working under the hood. I love how Mr. NG has the special ability to teach such complicated topics with so much ease. I can never expect the same from any faculty I've personally come across. Yes, the programming exercises were sort of a pain but there are github repos that let you do the same in Python. What I've learned over these 11 weeks, I believe, is immensely valuable and probably very few courses out there are capable of that. This perhaps has been one of the best decisions of mine so far. I plan on moving on to deep learning after this, thanks to Mr. Andrew NG.

Also, over this course of 11 weeks I felt attached to Mr. Andrew NG and I can proudly say that he's been the best teacher I've ever come across. It was a little hard to watch the last and final video knowing its the end of the road. So thank you sir for this wonderful work of art! I'll forever be in debt.

This is my first online course and I am so happy I selected Andrew's Machine Learning course as my first. The material was well presented, provided plenty of information about why and how you should use each Machine Learning method and importantly he spends time time providing the intuition for why certain mathematical formulas are used. The quizzes were challenging and gave you ongoing feedback on wether you were grasping the material in each section. When you get one of the questions wrong it helpfully points you back to the appropriate material in the lectures to review. Finally, I would like to thank Tom Mosher, a mentor and the author of most all the programming assignment tutorials and a constant presence and help on the discussion boards. I didn't have to ask many questions but that was primarily because someone else already had and Tom provided the answer, often times within minutes or hours. Even though I have little experience with online courses, the amount of support and attention to detail throughout demonstrates how good this course is and I can only hope is held up as a model for other courses. Thank you Andrew and Tom. I am truly grateful and can confidently say it was 10 weeks of work well worth my time and the knowledge that I gained will be used at my employer immediately.

This is an excellent course covering the fundamentals of machine learning with a wide breadth of subjects as well as, in my opinion, a reasonable depth into each as well. My only major qualm with the course (and this is just personal preference of what I would like to have learned) is that the programming language used for this course (that you must do the assignments in) is Octave/Matlab. As Dr. Ng mentions in the class, Octave/Matlab is an excellent way to prototype your machine learning algorithms, and after having used it for this course I agree. However, I believe it would have been much more useful (personally) to do the programming parts in a more industry standard language for your final product such as python. Point being, having completed the course I feel that before I can apply this as a final solution I must still learn how to implement these algorithms in a different language with different libraries, so it doesn't feel quite as if my journey is 100% finished. That being said, I do feel that Dr. Ng gave a great mathematical understanding of the algorithms and I do not believe that it will be terribly hard to implement them in another language. I believe the only barrier would be learning the Matrix Algebra and other ML related libraries standardly used in that language.

Hi. This is a great course which would be made even better with the small change I describe below. I was referred here by Nicole who was handling this as Support Case #1188060. I understand the mentors have been seeking this improvement for some time. Please let me know if I can clarify or assist in any way. Thanks in advance.

---- Support Case #1188060 ----

Hi. I'm writing regarding the Machine Learning course taught by Andrew Ng of Stanford. I have learned there is a compilation of "errata," known errors in the videos and course materials for each week, which has been made available in per-week links like the following:

https://share.coursera.org/wiki/index.php/ML:Errata:_Week_7

I found these links only after digging through discussions. In my own discussions afterwards, I learned that I wasn't the only one having trouble finding the errata. Apparently it's a long-standing problem which creates extra work for mentors as well as slowing down students. Would it be possible to provide the errata links, or a link to the Machine Learning Course wiki, in a dedicated section of the Course Content? This would help a lot of people. Please see the discussion below for more perspective.

https://www.coursera.org/learn/machine-learning/discussions/RQNTlee5EeWTdBIkpCpI1Q

Thanks for your consideration.

Tom :-)

Gently-paced and reasonable in terms of course work load, even for a busy person. This course greatly demystified machine learning for me.

Alvin's lectures are friendly and easy to follow, and progress smoothly from one point of interest to the next, always taking time to briefly recap on precursor topics that were previously discussed.

I really appreciate how the assignments focus on the core algorithms and their implementation. Ancillary implementation steps and a scaffolding for testing and viewing the results are already given for the learner to use, play with, and go back and reference for educational purposes if need be, for refreshing on use of tools such as plotting methods. The way the assignments are structured, putting emphasis on filling in the gaps with implementation of the important algorithms, makes completing assignments a very satisfying and fulfilling experience. I feared I would get caught up in preliminary steps, i.e. getting plots to display correctly or cleaning up the data, but that's all taken care of so that one can focus on practicing the techniques most relevant to the topic and algorithms.

I only wish there were more assignments to complete, both to cover more of the course's material and to have more chances to practice algorithm prototyping in Octave/Matlab.

This course in Machine Learing was challenging, but do-able... and very rewarding. This is the first on-line course I've taken. It has been many years since my last formal college course, so I was a little rusty at the math (I'm 55 yrs old, ancient compared to my peers in this class. My last math class was over 3 decades ago, probably before most of my classmates were born. Damn, I'm old). Even so, with Mr. Ng's teaching style, I was able to finish the course with both a good grade and - better still - a good grasp on the subject material. I will certainly continue to pursue additional learning in this area.

Machine Learning is a fascinating field. I was interested in this area way back in the late 80's when I first heard the term "Neural Network", but there were no on-line courses in that pre-internet era, so the availability of information about the subject was very limited. It was mainly in breathless magazine articles about the coming "AI" revolution. It took a few decades for that promising spark to mature into a practical reality. Now, with the appearance of Coursera and other on-line education portals, much of this information is readily available to all with the curiosity and perseverance to learn about it.

I am grateful for this opportunity to learn about Machine Learning!

An exceptional journey through this vastly mind-boggling domain that is Machine learning. What a ride it has been! I must admit, before I started this course, I was pretty skeptical about it. Back then, Machine Learning seemed like magic to me. Only after this course did I realize that Machine Learning isn't as intimidating as it seems. In fact, if you have basic arithmetic skills, you can learn Machine learning to a very reasonable extent. Prof. Andrew Ng, hats off to you! You have cemented yourself as a role model for me since these past few weeks.

Just as an aside, I wanted to let all the readers know that I am working a 9-5 job in IT. Not to be a humblebrag, but seeing that I took time out to complete this course just goes to show that if you put significant effort and planning, you will be able to complete this course (rather, any course) in the stipulated time frame.

The curriculum that this course offers is challenging - You don't get spoon-fed answers when you want them. Just a little hint - Pay very close attention to everything Prof. Andrew says in the lecture. Don't open other tabs and listen to the lectures in the background.

Overall, a fantastic course! Very excited about what ML holds in the future. Prof. Andrew, we need more series from you! Thank you so, so much!

Amazing course. I'm on the founding team of a payments startup, where my role consists mostly of sales, digital marketing, and 'growth hacking'. At university I studied law so I had completely no knowledge of linear algebra or post-high school level mathematics, or programming. Yet I found the material digestible and engaging. At times the material was very challenging but I was usually able to understand after rewatching the videos several times and/or Googling alternative explanations. The programming exercises were not easy for someone with no programming background, but again, Andrew Ng did an excellent job of teaching the basics thoroughly and efficiently. The forums have some useful tips on completing the programming assignments in case you get stuck, which I did make use of occasionally. I did find that towards the end of the course, as I started becoming much comfortable with Matlab syntax and programming logic, I was able to complete most of the assignments without having to look for help in the forums.

All in all, this was a phenomenal course for anyone interested in machine learning. It takes a lot of patience and time to work through all the material and programming exercises (probably 100-150 hours for someone with no stats / CS background) but well worth it!

This course is suited for you If you don't have a background in Linear Algebra and Machine Learning.

However, if you do have a background in Calculus and some Linear Algebra you will understand the intuition better (i.e. You can go to the lecture notes for the proofs and math explanation.).

I rarely pay money for a course , but this one worth my money! Specifically, the programming exercise were so helpful to fill in the gaps and give you a real understanding of the concepts been explained. At first you will struggle with the exercises (specially if you don't have a background in MATLAB), then you will get to used to it (i.e. you will ended up solving an exerciser in one day if you are used to it). Added to that, these exercises can be used to create your own Machine Learning Systems. In fact, I was sad that the last two weeks has no assignments. Also, you can learn from the written code in the assignment to visualize your own data. Finally, those exercises are what make the course balanced between the theory and practice! My advice for you: "If you have the money, go for the paid course. You will benefit from it even after you finish!"

I would like to thank Andrew Ng for his effort explaining the concepts and giving me the courage to continue further

About me: I studied computer science in Dortmund, Germany in the 90ies. I recommend this course to everyone who wants to have a very good understanding of machine learning. A little bit of advice, if you have never learned linear algebra on a university level, you should at least try to get a basic understanding of it before starting this course. I was happy that I remembered stuff, learning it from scratch in 1 or 2 weeks would be difficult, I assume.

+:

* Mathematical basics of machine learning are very well explained

* Andrew Ng is a very good professor, he explains the topic very well and thoroughly

* It is not limited by using a special framework or language

* The support in the forums, and the transcription of the talks, and all the material that is given to you is really excellent.

-:

* I would be happy if the programming exercises would be a bit more fun, currently it feels like translating / transforming math formulas into octave, which is fine, but not very fun. Having said that I am only in week 4, perhaps this will happen later

* some text questions in the multiple choice quizzes require a precise understanding of the english language, especially in regards to math, I am not a native speaker, so these questions feel especially hard for me

This is my first online course that I have ever completed and this feeling of completion is so immense! It took me one year to complete this. This was because I studied it part time while working and at the same time had other commitments pop in along the way. Nonetheless I'm really glad I made it through.

I would recommend this course to anyone who would like to learn about machine learning. It gives you strong foundations into the subject. You will realize right from the beginning of the course what machine learning is really all about. Though some of the assignments were quite tough especially on Neural Networks but you will eventually figure it out. Once you do, the feeling is tremendous! You will learn much about machine learning in two main aspects in supervised learning namely regression problems and classification problems. There is also unsupervised learning whereby you learn to form some sort of structure (patterns) in a dataset using K-means and also detect anomalies (e.g. fraud detection) via anomaly detection algorithms. You will also gain tools on how to analyze the performance of your system and what should you do next such that you will best make use of your time. Overall, this is a fantastic course! Thank you Prof. Andrew Ng!!

a. very good coverage of standard algorithmic approaches.

b. good suggestive guidelines on specifics of algorithms like issues / details one need to be careful, need not to bother etc..

c. broad coverage of examples..

d. tricky questions...good to experience...

Overall I liked this course content and the breadth of coverage. Based on the difficulty i experienced let me place some points of improvements that would help every student....

e. could have dealt some specific examples in full (from definition to implementation) as part of video lecture which would helped better understanding of the problems, algorithms, impact of specifics, implementation issues, analysis methods, inferences that could be derived, final expected solution.

f. expecting feedback on exercises.... not only correct or incorrect but reasoning for the responses could be of great help in better understanding....

g. downloadable videos could contain in video quiz...

h. Octave content could be increased.....

i. audio of the lectures needs fine tuning, hissing sounds could be filtered. For some of the lectures subtitles does not match at all...

Thank you very much for coursera....

Thank you very much Prof. Andrew Ng.....

Looking forward for mor courses related to ML by you....

The course specifically I rate at four stars. It's a great course, and I learned a lot from it. It's not afraid to get into more advanced details and mathematical underpinnings. The quizzes and particularly the programming exercises will challenge you. Professor Ng clearly knows his stuff. However, there are some serious flaws:

1) Audio recording quality is not good and sometimes he can be hard to understand.

2) Tons of errors in the videos made note taking a pain. The errors typically aren't highlighted and explained until the reading material that comes after the video. So my notebook has quite a few scratched out lines due to mistakes in the videos that are only later corrected.

3) Similar to #2, there are quite a few inconsistencies in the way formulas are expressed. Terms get moved around or written slightly differently often with no explanation. It can create some unnecessary confusion.

I still gave the course 5 stars though, because the assistants on the forums are absolutely excellent. They answer almost every question students have and take the time to explain details and intricacies of the algorithms. Their tireless dedication to helping students more than made up for difficulties caused by mistakes in the videos.

The best Introductory Course on ML ever. No Pre-requisites allows anyone with the interest to learn ML learn it in the best possible manner. The course not only gives the Theory but also develops Intuition behind every algorithm which helps to retain the essence of the entire material. Not only the Theory but also the Practical Advices that the prof gives helps you to implement a ML Project from Scratch and Diagnose any possible error that may creep in, some of which aren't even used by many Industry Professionals. The prof is very humble and teaches you more like a friend, giving examples on how simple things may go wrong, also accepting that some of the concepts are not so easy to digest, so don't worry. The course is superbly organised which helps learners learn everything that the instructor wants to teach. The Quizzes, in-Lecture questions, Programming Exercises enable you to step through a path of- learning the theory, building the intuition, getting practical advices, implementing the code and inspiring you to work on your own projects. The Discussion Forum is always very active, you could clear any and every doubt of yours. Thanks and Congrats Prof. Andrew Ng on making the best MOOC ever!!