Mr Andrew Ng and his current team did it again! I really liked the modules used especially the interactive ones, though it depends on how fast the system on where it is being ran through, it made understanding it relatively easy.

Though it was fairly easy to understand, the programming task is still fairly challenging. I like how the coding part is structured. It really focuses on the algorithms not just building everything from scratch.

I really hope I get into the next part of this course because with this part 1, I can already tell that I am only going to get better moving forward with this specialization.

Thank you!

I enjoyed learning the topics in this course. The material was presented effectively and the instructor Mr. Andrew Ng presented the topics in a way that was easy to understand. The quizzes weren't too difficult to complete and I like how we had optional labs. One thing I would say for improvement is to possibly have a video going over the coding assignments, just to verbally walk through things. The hints provided were extremely helpful but it would have been more effective for my learning to have audio guidance as well. Overall, this course was great and I would recommend it to others.

I recently completed the "Supervised Machine Learning: Regression and Classification" course on Coursera, and I'm thrilled with the experience. The content was well-organized and easy to understand, making complex concepts clear. The instructors were adept at simplifying intricate ideas, and real-world examples added practical value. The balance between theory and hands-on exercises, including valuable lab programs, enhanced my skills effectively. I wholeheartedly recommend this course to anyone wanting a solid understanding of regression and classification in machine learning.

Really nice and a beginner friendly introduction course, you could easily understand the content by no means is it difficult. The same goes for the optional labs and graded assignments. It tells you a lot of information on the topics. Only thing i wish to see changes around is to make the assignments and labs a bit difficult and thought provoking. I also wish there was a end-project to be submitted by us of some sort to have first hand experience ourselves without any training wheels.

Also I'm just curious the Vectorization and it's implementations in this could've been more?idk

The structure of the course is good and so is all the information presented, but you could probably pass it without understanding any of the math/code and just copy pasting from the lab + checking the hints.

Suggestions:

1) break up week 3, or at least the assignment. Week 3 took twice as long as the previous weeks combined.

2) have some additional (optional) math/coding quizzes or create a more difficult version like you have 229 & 229A at Stanford. The youtube lectures are fantastic and so are the problem sets, but none of the rigor is found here.

Love the professor by the way!!

The course is conceptually great and Andrew is an absolutely amazing instructor. Just didn't give it 5* since I felt the great theory (perhaps sometimes even a bit too deep on calculus for a "beginner" course) was not complemented by proper modern practice - I'd expect to have at least one Notebook where we'd go from A-Z in how to build a model (eg. data cleaning, preprocessing, model training with Scikit-Learn, model inference) so we could get a clear understanding of the baseline for building regression and classification models. Apart from that, I highly recommend it!

Glows: The videos were excellent. They were short, descriptive, and very clear in breaking down complex topics. I watched them at 2x speed and was still able to understand everything clearly. The labs were very helpful and ensured I actually needed to write the code myself. The quizzes built up my confidence and ensured I took away the key points from each video.

Grows: The only thing I'd add to this is to have some quiz questions in the lab too. Or instead of hints showing some of the solutions, the hints being guiding questions themselves.

Andrew is a very nice to listen to person and you know he is passionate and talented in what he explains by the fact how easy he breaks down such a complex topic into small easy-to-understand and on the point chapters. What I critique are the programming exercises. The course says it's not necessary to be able to code but it's absolutely impossible to do the coding challenges without having at least a bit of Python knowledge which was the case for me or by simply copy+paste the code from the lectures.

It's an incredible course, clearly made with knowledge, passion and virtue. It's clearly a great challenge to design such a course to be understood by complete starters. Anyway, one thing I wished for were more credible test questions and programming exercises. Right now, anyone can do it, which is not bad but on the other hand does not help to really get the hands on experience you wish for when applying it in real world. But maybe it's a trade-off situation. Thank you very much for your hard work!

The Course sheds light on the two machine learning algorithms: Linear Regression and Logistic Regression. It covers the overall intuition and the algorithms quite clearly. Some maths is also covered. The programming assignments and optional labs are quite helpful in experiencing the machine learning algorithm in practice. The course is for intermediate learning who have a basic know-how of linear algebra, calculus, plots, python programming, python libraries and data handling.

It is an amazing course if it's your first time entering into amazing world of machine learning. This course has lots of knowledge to give which is perfect for beginners. One thing that It lacks is, practical knowledge. The lack of more assignments is where it lacks. Yes, it has optional labs but you have to figure lot of things by yourself in that lab if you are a beginner. Overall, It's a great course and I want to thank Andrew Ng and Stanford Online for this course.

The present course content is relatively relaxed, i.e. whatever is covered in lecture videos is directly asked in the assignments and labs, which makes it a bit boring. A humble suggestion is to make the course content challenging and include brainstorming assignments and some questions requiring deep thinking and concise concept clarity. But honestly, a lot of effort has been put in, be it interactive simulations in optional labs or lucid explanations.

The course in general has been great! I think it covers perfectly the main topics and skills of supervised machine learning. Nevertheless, I find the practical exercises maybe to easy to accomplish even without properly understand what your are doing. Maybe as a final project would be interesting to propose a less guided exercise. But congratulations! It is a great course, really useful to have a taste on this wonderful world that is Machine Learning!

NOT EVERYBODY CLEARLY UNDERSTAND WHAT THE CODE SAYS. THERE IS NO VERBAL EXPLANATION OF CODES, IT WOULD BE BETTER IF VERBAL EXPLANATION OF CODES WAS AVAILABLE. BUT NONETHELESS I THINK THIS IS THE BEST COURSE I HAVE TAKEN ON SUPERVISED LEARNING. EXPLANATION OF THINGS ARE REALLY TAKEN INTO CONSIDERATION AND BEST POSSIBLE EXPLANATION IS PROVIDED. I HOPE THEY ALSO LOOK DEEPER INTO SUPERVSIED LEARNING AND VERBAL EXPLANATION OF CODES.

the course was good I learned a lot in that course specially I like the fact that I am not writing just an one line scikit function I am writing whole blocks of codes my self which boost my confidence and motivation the statistical part coding and math part was all good and explained well sir andrew ng I thank you deeplearning.ai to give me financial aid for this it means a lot to me again thank you

The course design is so excellent and I really enjoyed the course. However, I gave it 4 stars because I would really appreciate it if there are some information about the real-life use of this. I am the kind of student looking for some real-life implementation to understand the course more efficiently. Overall, thank you so much to the team and Teacher Andrew Ng for the kind guidance. Best of luck.

This gave me a really good overview of how to solve Linear Regression and Classification problems. I learned a lot about prominent Python-based machine learning tool-kits, applications and libraries. It comes with some extremely valuable insights from one of the AI field's experts. Being an introduction, this course does, from time to time, skip the specifics. I thoroughly enjoyed it.

The course is great regarding content and explanations. On the other hand, it could have more practice tasks that one should do on their own to better understand the topic and grasp knowledge in the field. In the last practice task in the section for user's input, there is a suggestion to use inefficient code without vectorization which is in ML crucial as professor Ng mentioned.

The content covered is interesting and explained thoroughly and in a very clear fashion however I find the practice labs a bit underwhelming, they have too much assistance and also the pre-existing guiding code can lead to avoiding vectorized code which supports slower algorithms, I feel like this course could have better practice so as to be easier to apply in other applications

Andrew Ng surpased himself as far as his teaching skills. I am amazed by quality of his lectures and the way he explains things. However I found that quizes were to too easy. One should just pay attention to what was said during lectures and 100% grade is guaranteed. That's why I'm giving 4.0, although I think 4.5 would be more appropriate. All in all - great first course!

It was a great course for introduction to Machine Learning. I enjoyed the course very much. One thing I would like to add is there should be an exercise to write full code, because that would enable us to understand better what variables to take and what algorithm we should follow without any existing template and all. Otherwise I liked this course very much

The content was good, but I think the quizzes and assignments weren't designed focusing the development of intuition and a deeper understanding of the content. The same goes for the optional labs. I would say to take some inspiration from the courses offered by Imperial college. But overall the topics were covered in depth and effectively by the instructor.

Great Intro to ML. I did not find it challenging enough or offering extra info that we can study on our own (like generalised linear models). It also doesn't mention that there are other parameter optimisation algorithms other than gradient descent. Overall a very beginner friendly course, but left me wanting for more, which isn't exactly bad I guess ;)

I appreciate the example-driven approach toward these complex topics. One thing I feel missing is the practical sessions on the coding part, although the coding part is provided in the optional labs times it feels a bit confusing and requires some further explanation on it. An overall, very useful course for those who are looking for the fundamentals .

The code need to be explained because there are many functions student doesn't know. I searched and knew these functions but sometimes I couldn't understand why we used this fun while there is another one can do the same. and many things wasn't clear to me in the optional labs.

But the videos were excellent and I recommened the course to my friends.