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.

The course was very helpfull and the instructor made the course very easy to understand ,I wish i could thank him in person .But, the challenge was in the jupyter labs it was hard to understand the skills in visualizing the data given and the codes was tricky hope to see more videos of coding in the future.

Thank you coursera.

Thank you sir\Andrew.

Some classes are not understandable. Please add a contact form or something similar to reach out for guidance and clarification. One more thing: I think this course is designed for someone who already knows calculus and algebra, which is why it is very difficult to understand the classes. Overall, I learned a lot, but with the help of GPT :D

Andrew's explanation of the different aspects of ML is excellent. The only thing I think could make the course even better is if the optional labs were replaced with tasks based on real-world ML problems and scenarios, and if there were more focus on using libraries and tools that are commonly used in development and production environments.

The content is very-well explained. I would have liked the practice labs to be a little more difficult. The labs fill up almost all of the code and leave very little to be done by the student, so the labs were not sufficient for me to get a good grasp of the coding skills required to INDEPENDENTLY write code for my own ML projects if any.

Overall good starter courser, but have been good have a little more videos on using the scikit-learn library. Also an exercise is needed where one implements the entire regression solution from identifying variables, creating cost function and the gradient descent. Doing everything from ground up, even if it is for a small training set.

The course was very good. Well-structured and the concepts were made simple enough to understand. The only drawback was the minimal use of libraries such as Sci-kit learn in practice labs and assessments. However, will definitely recommend to people who are interested in understanding core concepts behind Regression and Classification

A very good course to understand Regression and Classification. However its just about the introduction of it. Would have been great if the talk on Mathematics of Regression possibly from R-squared, SSR and such things could also have been there. Same goes for Logisitic regression such as Accuracy, Precision..etc. Good for beginners.

Very good overview, although as a mathematician I found the lack of rigour in the analysis 'disturbing'. It's a bit frightening to think of hordes of people (or, worse, machines themselves...) using tools like this to reach potentially incorrect conclusions without a clear appreciation of the limits of the techniques they are using.

I really like this course. Though for more in depth learning how to apply logistic and linear regression i would recommend Andrew NG older course also still available on coursera. It goes more in depth of how to evaluate a model when implementen and comparing them. Anyway thanks to all the contributors to making this available.

Consolidates all of the essential beginner information for types of regression and gradient descent. Worth it for busier professionals. Wish there were more hands-on "throw you into the pool and let you swim" types of labs, everything is very hand-held. That is what other resources and personal projects are for, it seems.

Was a great course and the visual representations really helped a lot in understanding key concepts, my only suggestion would be a little more depth in coding know how and video explanation of it than just notebooks to read from. Overall a great course to learn in-depth about regression and classification from ground up.

I would have liked a bit more hands on coding and going a bit more deeper in the math and coding. Having said that, on the following course, having these understandings and intuitions have been very helpful to better understand how neural networks work behind the scene. I do recommend this course.

This first part of the course is probably suits a freshman student in engineering who has limited knowledge of numerical methods or computer programming. While I hold great regard for Mr. Ng, I find the pace of the course to be somewhat sluggish, and the depth of the material covered to be modest.

Overall, the course was remarkably insightful and presented in a way that made it easy to follow. In the future, I think it would be beneficial for the lessons to delve deeper into the programming aspects of machine learning, as this area demanded a lot more independent research and self-learning.

The course is great and offers a wealth of details, both theoretical and practical. However, as a first course in machine learning, the coding in some labs could be simplified. The labs could have been designed using simpler code, particularly by utilizing NumPy instead of looping over vectors.

This is a really really great course which provides the fundamentals of Supervised Machine Learning and also math concepts used in Regression and Classification. Ones who don't have basic math knowledge and basic python programming knowledge will face some difficulites in this course I guess.

It was really insightful, learned about all the theoretical as well as some practical knowledge, Andrew sir's way of teaching is definitely the best way to teach something this challenging, really loved the course, Will surely recommend to someone who's starting out on Machine learning.

This course was very helpful for me to understand the mathematics and intuition behind those machine learning algorithms. However, I believe the assignments could be slightly more challenging and demanding, and it would be great to have a small project as a culmination of the course.

Amazing coverage of Linear and Logistic regression! There is a significant attempt to lower the math bar for this course, which is appreciated and admirable; but then the labs require implementing equations in code, which requires some focus be paid to that portion of the learning.

Lectures and assignments are well very curated, but assignments are far too easy and encourage explicit imperative programming (for loops and mutated state) rather than vectorisation, which goes against the taught material. Very odd - that's the reason for the 4 stars only.

Great course. If you would improve something I had a little hard time completing the test's because the code implementations were different to the ones seen in labs. the name of the varbiales changed and some thing's changed so I think this could be difficult for beginners

It was my first specialization which I completed from Coursera and it was worth my time. The knowledge shared by Andrew Ng is just incredible and I enjoyed the course a lot. Thank you Coursera for making such courses available for us and financial aid was also very useful.

One of the best Courses on the internet on ML, I am thankful to this course for existing. But if I had a single dislike was that, there was not much hands-on practical practice. Its more theoretical. I would have loved for Mr. Andrew NG to teach us code side by side too.

Great course for mathematical fundamentals of Machine Learning. However, I would like the optional labs (that introduce and describe the necessary Python code) to be better explained and walked through. It is hard for me to understand how the passage from concept to code