This is really a fantastic course as it provides hands-on machine learning experience, but also a lot of intuition as Andrew is so brilliant at explaining complex concepts in very simple and understandable language and visualizations.

It is very friendly to non-math students as well as high school math such as basic linear algebra and calculus may suffice to get a lot of intuition yet without being too overwhelmed by the formality of math.

I also really like the structure of the course, and I now understand very well concepts such as the loss of a single data entry, aggregating losses into an overall cost function, and using the gradient descent algorithm to minimize the cost function to find optimal parameters for learning a curve that fits the input data.

Very simply and wonderfully explained - the contribution of this course is really the way it provides a gentle introduction of concepts that eventually promise to be applicable the same way for far more complex algorithms. Provides a good balance of intuitive understanding and the math behind the concepts.

I do wish the course were a little less gentle and went faster in places, delved into the math a little deeper (e.g., for logistic regression), the intuitiion in places a little deerp (e.g., regularization's impact on mean square cost) -- but, I perfectly understand the difficult tradeoffs that have to be made here to appeal to the broader audience.

Bottom line - Andrew and the others that helped him with this course have done an outstanding job.

This is an excellent introduction - I love Andrew Ng's courses! - it is exceptionally clear in defining terms, concepts and algorithms and steers a very sensibke course with respect to the associated mathematics making it the perfect first course in Machine Learning. Moving the course to python was essential and it is good to see a lot of example notebooks with supplementary material in. I'd recommend students look at Geron's OReilly Book (Hands On Machine Learning ...) afterwards to see more coding examples in the book and associated github repo. One gripe was that you didn't make students do vectorised code for the two programming asignments. I commented out the example code in week 3 asignment and substituted vector code (which runs fast).

Hi,

I already took Andrew NGs "Machine Learning" course a few years ago.

Taking it again (in Python this time) was a great refresher !

Although I understand the need to make the course more accessible I feel like the math was oversimplified at times( standard deviation, probabilities, core math functions).

Moreover I think the course should have covered EDA and feature selection before introducing supervised algorithms.

Finally, I was a bit dissapointed by the scikit learn optionnal lab, I expected more.

Still, I feel like this is the best introduction to machine learning there is.

There is a great balance between theory and practice and I like how Andrew calls upon our intuition.

This is why I give this course 5 stars.

I highly recommend the 'Machine Learning - Regression and Classification' course to anyone looking to deepen their understanding of these important concepts. The course is expertly designed and delivers a comprehensive overview of both regression and classification techniques in a clear and easy-to-understand manner. The instructor is knowledgeable and passionate, and they do an excellent job of explaining complex topics in a way that is accessible to students of all levels. The course materials and assignments are top-notch and provide plenty of opportunities for hands-on learning. Overall, this is a fantastic course that will leave you well-prepared to apply these concepts to real-world problems.

I would like to thank Prof. Ng and the overall team for creating a truly incredible course. This is undoubtedly the best course to learn the basics of machine learning.

Prof. Ng is well known about his pedagogical teaching style, so I guess I do not need to say more. But I would like take this opportunity to acknowledge the behind-the-scene members who designed the homework problems and organized the course. The homework problems are very well thought of and they made this course highly effective.

A small comment: I think it will be useful for the curious and math-inclined students if references for some mathematical concepts/derivations are also provided at the end of each lecture notes.

The course helped me to explore the beauty of Machine Learning and has definetly laid the foundations of Machine Learning for the further courses in the specialisation. I would also like to thank humbly and from bottom of my heart to the proffesor Mr. Andrew Ng who made me fall in love with the fundamental building blocks in Machine Learning. The train started from simple Linear Regression which stood so fundamental throughout the course, and gradually by the end , I completed the course without even realising it! There is so much to ;earn and the most fun part of the course were the Optional Labs, where initially I had a hard time, but they proved to be the stepping stones in the course.

I'd tried the original version of this course twice and never completed it due to other commitments cropping up. This time around they've upgraded to Python and gone lighter on matrix algebra, although there is still a section on vectorisation for those interested. Most of this first specialisation was revision for me so I sailed throuh it in a week. I found the jupyter notebooks a bit noisy, being a software engineer and not a data scientist, and tended to delete the skelton code implementations and replace them with the vectorised versions as I actually found this easier. All in all, the video quality has been upgraded and the explanations by Andrew Ng are still clear and insightful.

This was by far the best course for learning supervised machine learning using python as a tool. The optional labs and assignments were to the point while simultaneously taking care to enable students learn the subject with proper hints on various exercises periodically. The visualisation technique for various aspects like gradient descent, sigmoid function etc...via the means of coding ensured that students understand what they are actually doing. Thanks to Andrew Ng sir for personally taking efforts to educate the students.

I am eagerly looking for continuation of this course further on advance machine algorithms which would boost my confidence in carrying out my research work.

This course is excellent! Andrew Ng's enthusiasm for the subject is infectious. Labs are very instructive as they are well-documented and connected with the lectures. Advanced math isn't required but helpful. If you have deeper math background (calculus, linear algebra there are sections of the course where the math behind the lessons are explained further. Andrew focuses a lot on teaching intuition, which is a great way to deepen one's understanding of the material. The interactive graphs are very helpful in this regard. One nit: the Jupyter notebook sections after code blocks get corrupted when errors are made in the code blocks. This was a bit annoying but not a blocker.

One Word : Excellent.

I am unable to find appropriate words to express my vews about this course. This course is so well planned and well executed. The funadmental cocepts of machine learning and deep learning are explained in such a manner by Andrew Ng sir, that it feels like 'cake'. His style of teaching is so good that I sometimes feel that I already know a particular concept while I am learning it for the first time. Anyone... Anyone who is strugling to learn what are biases, what are weights, what the hell is this gradient? he should take this course imediately.

Highly recommended course. Take this course to start your mahcine learning journay with full confidence.

Terrific !!! This is an excellant course that give you in-depth intuition behind the famous regression and classification algorithms. Though most of these algorithms are now readily available in scikit learn, however it's better to understand them before using them blindly. This could also help you to reate an algorithm of your own.

None the less the exercise are good and the jupyter labs are exceptionals with interactive examples.

I would highly recommend this course specialization to anyone who wants to start their machine learning journey.

Respected Andrew Ng and his team are incredible. I am really grateful and learn a lot of good things from this course.

This course is well taught, its both an upgrade and downgrade to the old version of the course. Improvements are that you will be using Python rather than MATLAB/ Octave, smoother video quality and ease of understanding, with smaller bitesize chunks of videos that the longer videos in the old version with quizzes in between taught section rather than at the very end of a week. Only dwonside would be is that less mathematics is needed and doesn't go into the detail that the old course would have, however the course was designed for people with a less mathematical background. Honest;y loved the course so far and cannot wait to dive into the next two courses.

A+

The course is very well explained, there is nothing more difficult than to make very abstract concepts understandable to everyone and it must be said that thanks to this course, you are really armed to face the challenges that will come to you in ML; the course is fun, instutitf, clear, both very advanced but also very well explained, I recommend, to all aspiring ML enthusiasts or to those who would like to make a career in AI to follow this specialization! but also the others offered by DeepLearning. AI, thanks to the DeepLearning.AI team, special mention to Dr. Anderw Ng, not forgetting Eddy.

Thank you all for your dedication

Orson Typhanel Mengara

Fantastic content. One of the problems with other courses is that they don't teach any of the wisdom gained from years of experience. Andrew does. He teaches us what we need to know and avoids teaching what might be a red herring. The true value of an education might be measured by our ability to make better decisions. Andrew delivers on this, the most important outcome of a course. My only criticism is that some of the language used in the labs and assignments is misleading due to incorrect grammar. I spent far too long thinking that what I read meant the opposite of what was intended. This is infrequently a problem, though.

The mathematics is explained in detail, it is true you don't need much mathematical knowledge, pre-calculus knowledge is just fine and helps with intuition, otherwise, you are taken care of with everything explained in detail. The quizzes are very helpful in checking whether you understood the concepts. I loved the labs because there was a lab for each section which gave me hands-on practice, seeing exactly what was going on and learning to apply the concepts. I am extremely grateful for the opportunity to have all this knowledge available to me across the world, this is a great course, and I loved it.

The education given in the program was one of the rare moments in my life where I felt that I had really learned something. Although some things are offered optionally in this program, it progresses in a very comprehensive and instructive way. In addition, it is not only focused on completing the course, but also has a developer feature about machine learning. The library and tools that are not actively used in the course but used by today's engineers and researchers are also mentioned in the program. I would like to thank you for this effort, your high level of teaching and your kindness. Best wishes.

Starts off easy and then gets a bit more challenging. I enjoyed it. A couple feedback points:

- More questions throughout the videos might be helpful. - I'm not sure the labs should be designated optional, since the final labs expect you to write some code.

- It would be nice if there was more coverage on how to do feature engineering (ie. how do you know when to map original features to higher dimensions and orders? I feel like that might be one of the missing links to actually try to "do" machine learning on some practice datasets.

Outstanding beginner level course that introduces regression and classification with Python. The class is light on the math and coding, but it gives a fantastic overview of the topics, and provides excellent visualizations to build intuition. Andrew Ng also provides a lot of very useful tips for machine learning practitioners (i.e., we don't use linear regression for classification problems!). Very much recommend this course for anyone, whether you are a seasoned ML developer, or you want to just start your journey into the field.

Very well structured course with great explanations in the appropriate pace. The maths are discribed clearly and the connection between algebra and algorithms (Machine Learning) becomes and easy process.

The assignments are in the indermediate level and the student should understand the theory/maths to complete them with 100% grade. They are all explained in the lectures videos but you need to think before you submit them.

Overall, is an upgrade of the previous course that is adjusted on Python and Jupyter Notebooks. 5/5 stars.

While I expected this to be simple Python refresher on the originally taken old course with MatLab/Ocatve, carefully reading into the code before executing it helped to conceptualie what I amd doing more. Also I really appreciate the interative demos, and especially those of gradient descent - they really add so much more to building your intuition -- make sure to click in the horizontal direction more anf more to the right and think why the results are changing in the way they do...

Thanks for this experience!

Thank you for the opportunity to take this course through financial aid! I enjoyed the way the course is structured including the optional practice labs and the programming examinations! Being a graduate student with lots of responsibilities, the flexibility of the course allowed me complete the course at my pace without which I would not have been able to complete the course. I would like to take the remaining 2 more courses in the series to give me a proper grounding in the Machine/Deep learning. Thank you!

I really adore listening to Mr. Andrew Ng, especially when he tells something along this line, "You don't need to worry about that." This course is very beneficial for me, because I am training to become a Machine Learning Practitioner. What I learned from this course will really be what my job will be. Thank you Mr. Andrew and to the whole team who developed this course. You have developed in me the intuition I need to be an equipped and responsible Machine Learning Practitioner in the future.

One of the best course on Machine Learning on the Internet. The teaching methodology of the instructor is amazing. He is humble and explains everything from maths to the implementation of models from scratch and also with the help of libraries. The lectures are so well organized and well planned. This course actually set up the fundamentals of machine learning very strong with all of the insights + maths + coding. It actually helped me a lot about what actually ML can do in reality.

Excellent course! Clear insight given by Andrew on complex concepts using simple examples. Alternative way of teaching this course would be getting into linear algebra and calculus, but then then learners would have missed practical aspects of this course. I liked the fact that the focus is on practical applications. Optional labs were very useful. They gave crisp demonstrations of concepts covered in the videos. As a beginner with python, I learnt a great deal of pythons as well.