Highly recommended. Great practical overview of machine learning approaches.One shouldn't expect the underlying implementations from this course due to the time strain - only a few weeks, and should take Andrew Ng's machine learning class for that.To go even deeper for some methods, one should take more machine learning classes.

Very interesting and engaging course. I liked graphical comparisons of different models and their params. Module notebooks were very handy while doing assignments. All homeworks were not trivial, developing and demand attention to detail. Big plus for teachers posts at forum - they help a lot while doing quizzes and assignments.

An excellent overview of current machine learning knowledge and practices. This course is very information dense and requires additional reading and time for the assignments. It is challenging for an 'intermediate' level course. Some prior knowledge of machine learning is recommended, and strong Python skills are required.

Very applied course, while still teaching you the basic concepts. You can start using machine learning solutions to your problems right away with confidence. The course covers a lot of ground, so expect some topics to be treated rather superficially. It provides a lot of material if you want to expand your knowledge though.

Very good course for either an introduction to machine learning or to refresh old skills. It's also very good at putting emphasis on topics that data scientists may overlook / not pay much attention too, so having this as a reminder to look deeply into each algorithm and its application or limitations is incredibly helpful.

excellent, practical introduction to (mainly) supervised machine learning in scikit learn. Next to Python specific handling of models, also conceptual issues like parameter tuning, feature pre-processing and - very nicely - data leakage are explained. examples can get tricky without solid grasp of numpy and pandas packages

this is an interesting machine learning course

can quickly understand the basic idea of machine learning and know how to build different models in python and select models based on different standards

it is a very good course to start with machine learning and can arouse the interests of learning more in this emerging field

The course covers a many topics of the ML world.

The exposition of the arguments is well organized.

The assignaments and quizzes are difficult enough to force you to really understand the lessons and learn the arguments but are not impossible to be accomplished.

The teacher are always ready to help you in the course forum.

Good course, but take it with a theoretical course also, (I suggest Learning from Data, Caltech, the lectures are on youtube and assignments are put up online). This one goes well with it, because LFD teaches to code up classifiers and regressors without libraries and this one teaches us practical use of scikitlearn.

this course may be the most challenging one I have ever met, those concepts and examples I have never thought would met in my life. but after intense learning and excellent course arrangement, I may get a little sense of machine learning now.

Thanks for the great job, dear applied machine learning in Python team!

I did this course only from the entire specialization so it was a little hard to catch up but the difficulty made me even more excited to keep going and finish every bit of the course. I really appreciate the amount and quality of content, quizzes and assignments. Totally worth my time. Thanks UoM and Coursera!

Lots of material to cover in this course. From supervised learning to the optional un-supervised learning schemes. A good introductory course to all theory there is to know on applied machine learning. The professor gives a glimpse of internal mathematics too. Interesting course, but lot of material to cover.

An ambitious but systematic overview of a wide range of machine learning techniques using scikit-learn and other Python libraries. Prof. Collins-Thompson is a steady and clear explainer of somewhat complex topics. The exercises and quizzes can be challenging, but are very worthwhile.

Overall, very well done.

Good course. It's not heavy on math. This course is a good starting point for machine learning if you have basic python skills. I would recommend doing Assignment 4 in the online jupyter notebook that is part of the coursera course. The online jupyter notebook uses the same import versions as the autograder.

Good introduction into the scikit learn package, took way more time than advertised but I also learned more than expected.I contrast to course 1, the assignments were easier, but the quizes were harder. Distribution of materials could have been better: week 2 has by far the most material to digest and learn.

I have been confidently guided through the complexities of Machine Learning through perfect mix of lectures and reading materials. Quizes and programming assignments served as very helpful tool to zoom in on specific details which in further assignments will make the difference between success and failure.

Brief but in-depth introduction to many modeling methods and using them in python. It provides a great foundation for the rest of the courses in this specialization, but I wish other courses would be developed in collaboration with this intro course, rather than a series of independently designed courses.

Very interesting and informative! The material outlined in the course, difficult to understand, IMHO, but the organizers and the teacher managed to present it in an accessible form. Special thanks to Kevyn Collins-Thompson for his lectures and Sophie Grenier for her work and attention to the forum.

Coursera has made possible for millions of students worldwide to access the best quality of education through their medium. An opportunity to learn and develop as an individual changes a person's life substantially and most importantly Coursera is providing this opportunity to millions for free.

A great crash course in some of the basics of machine learning on Python. Although not explicitly covered, the assignments helped me gain an understanding on the Jupyter framework & pandas.

The final assignment was definitely a cherry on top that let me gain a very vivid insight into the field.

Fundamental, but still thorough, course in applied machine learning using Python. The lecturer is really good, and the quiz/problem sessions are challenging, but sufficient information is provided in the videos -- a HUGE improvement compared with the first two courses in this specialization.

This is a great course. Content is highly organized. The amount of lecture material was just about right. The professor is an excellent lecturer. Assignments and quizzes really helped reinforce my learning. If the Autograder is less demanding, this course would have been better in my opinion.

The Applied Data Science with Python specialization continues to deliver with Applied Machine Learning. Both quizzes and assignments are challenging but exceptionally well architected. I'm walking away with a great deal of beginner to intermediate skills in machine learning and scikit-learn!

Gives a good overview on ML-Techniques. I liked the evaluation part. "Applied" means - they provide no technical/mathematical details of the different methods. You should get it somewhere else.

Everything is well set up. You need the knowledge of the previous courses of this specialization.

The course was very good. It has covered a lot of topics in a small time and has provided a good insights about all of them. It would be good if some hints can be provided with each question during the assignment as while facing confusion or problem it can help us to progress further.