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).

I think this course is both suitable for beginners who has only basci programming / ML ideas or for someone who wants a review of what they've learned in school. No matter where you stand right now, you come out as capable of applying the algo on real datasets. The course mostly about the application of regression, classification. No endless details or math theories and focus on the big picture. Very practical! The coding assisngmnets and quizzes are very on point, and literally an application of the algorithm, with step by step guidance. Instructor has made the learning easy! Andrew can explain an algowithm cleraly within 5 minutes, which shows he's knowledge and understands the mindset of learners instead of experts. Thanks again!

This is a great introductory course to Machine Learning. It reaches the fundamentals of Machine Learning, starting from Linear Regression and then showing a variety of techniques to improve our models.

I really liked the way in which everything is explained. Andew Ng has an amazing ability to explain concepts in a didactic and simple way.

Even though knowing calculus is not necessary for necessary for completing and understanding this course, it is greatly recommended to know some calculus in order to better understand what is going on at a mathematical level. I really liked that the course shows the mathematical reasoning behind the learning models.

Overall, this is a great course and I highly recommend it. Can't wait to start Course 2!

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.

Perfect course by Andrew and Coursera team. I have been searching for AI and ML courses for last few years. I even subscribed some other courses before but they were not well organized, content was not good, in fact, basic introduction and real applicability was missing. So I did leave them in the middle only. I then found out about Andrew and his expertise in AI and found out this specialization. This course if perfect because: 1. It gives foundation of AI and ML, real uses cases. 2. Andrew explained algorithms in very easy language. 3. Course is very well organized 4. Options labs are really good. (No need to setup anything in your computer for practice) I am honored to learn from Andrew.

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 entered in the specialization and I just completed the first course and it was amazing!! The concepts really flowed well together and it gave me a solid pattern of application. This was math heavy but you don't need any math pre-requisite to do any of it. The math is all explained and it is all derived for you with explanations for each step. There was coding in python but the coding examples were problems to show you how to code the actual algorithms and not anything else. Like this course says it focuses on Regression and Classification and the coding examples reflected that. Overall I enjoyed the material I learned from this course and will be doing the rest of this specialization.

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.

Andrew Ng’s Machine Learning Specialization stands out because it provides clear, accessible teaching, hands-on learning, and real-world strategy, all while being led by one of the most respected figures in the field. For those in the Face and Emotion Recognition (FER) space, the specialization offers: - A strong foundation in machine learning fundamentals. - Practical coding skills to develop and refine FER models. - Strategic guidance to iteratively improve and deploy robust solutions. This combination of theory, practice, and strategy ensures that learners not only understand machine learning concepts but are also prepared to apply them effectively in projects like FER.

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

I started taking the NVIDIA track to learn how to set up the hardware. Although those courses were excellent, there were many gaps of knowledge that I didn't understand. After searching, this course hit bullseye - explaining all the concepts from the ground-up. I highly recommend this course as one of the first courses that any AI student take. It will make the AI journey much easier to understand. I've seen a lot of instructors and Dr. Andrew Ng and the curriculum developers behind the scenes are an amazing staff. It's rare to see such a refined and polished product. All I can say is 'thank you' and you offer an invaluable service to students.

I am currently a third of the way through the last course in the specialization. So far this course has made machine-learning concepts very comprehensible and easy to understand. Having been working in a student organization whose main focus is on AI, I felt as though I did not have adequate experience to help lead the organization. This course broke things down for me in a way that I needed. If machine-learning is of interest to you at all, I highly recommend this course as it will take you from a beginner who knows nothing at all, to someone who can hold their own in the world of ML. Thank you to the amazing team that put this course out there.

I have completed Supervised Machine Learning: Regression and Classification and in this course I learned plethora of topics and all 'ML' topics is covered regarding Supervised. On top of that, each algorithm is demonstrate very neatly through mathematical equation behind algorithms. Which help to assimilate the how each model is work and goal behind to develop to predicate the expected output. However, I face some difficulty to solve the assignments but by revisiting the lecture help me to score full grade in it. Now, I am so enthusiastic to complete the other two course of Machine Learning which is taking by "Andrew Ng" very nice lecturer.

The ourse design and way the instructor explains the subjects are perfect. I've graduated from high school this year and just know the basics of calculus, like some basic derivation rules, but it wasn't hard for me to follow the math and understand intution behind the math. Also, instructor points out how important it is to use parallel processing capabilities of modern computers and shows how to do that with numpy library and it's a really important best practice to code sustainable machine learning algorithms. I appreciate everyone who put an effort in this course, I'll definitely proceed with the second course of this specialization.

Participating in this course has been an absolutely wonderful experience. Andrew Ng's exceptional teaching style and approach made the complex world of machine learning remarkably accessible and comprehensible to me. His ability to break down intricate concepts into easily digestible components truly facilitated my understanding.

One of the most remarkable outcomes of this course was how it ignited a deep passion within me to continue delving further into this dynamic and fascinating field. Andrew Ng's guidance not only imparted knowledge but also inspired a genuine enthusiasm for exploring machine learning's boundless possibilities.

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.

Professor Andrew Ng explained every topic from linear to logistic regression in such a clear and simple way that i could not help but smile at the fact that i was understanding everything that he was teaching. After completing the first week I felt as if i can contribute or solve any machine learning task. Word of advice, Spend time really understanding the concepts from the lectures and solving the assignmens will be much easier. The same way i couldn't way to log in every morning; i can't way to take the second course.

i can't believe i am limited to only give five stars! maybe like (5!)^100

Thank you so much!

Great course. I really enjoy how is goes more deeply into the mathematics compared to other ML courses. I also love the way Andrew teaches; he really makes you feel excited about ML. The one problem I have is that they use terms like 'fairly big', and 'works almost all of the time' when explaining some topics or in the quizzes. I understand why they are doing this as it is a beginner ML course, but as a Math major myself I think it is bad practice. ML falls under applied mathematics so I think the choice of words in the course should be more rigorous as this will prevent any confusion later on for a learner.