g

G

a

Course is excellent in content. Not heavy in mathematics (altough, I would recommend reading how models are supposed to work), the objectiv eis to have a practical understanding of how machine learning is applied and the important concepts to consider for a succesful model building. The focus is to have hand-on experience with the sklearn library.

I don't grant 5 starts (I hesitated for 4), as the course was designed back in 2018, therefore, you sometimes struggle with legacy libraries. Another issue, is that there are some hiccups when it comes to assignment uploads (for instance, the address of csv files!). As a student, this will make you hesistate and question wether the instructor screwed up with the autograder or not, which IS stressful.

Quiz 4 suddenly became non-forgiving, multiple choice answer have to be answered with 100% certainity to score full point. Quite anti-climatic, considering that previous quizes didn't work like that.

Final assignment is quite challenging, and might make the new student suffer.

I appreciate the instructors and Kevyn Collins for this great course. Now that I have a better picture, I get insights on how to focus my research efforts in sensor research and development.

My actual rating is 3.5 stars. This is the best course yet in this Specialization.

Pros: I prefer Professor Collin-Thompson's delivery compared to Professor Brook in the previous modules. I think he gives a good overview and sufficient depth for an applied course, compared to Professor Brooks which I find to be quite superficial most of the time, and weirdly detailed in other parts. Assignment is good enough for reinforcement learning and definitely better planned. I also appreciate the link to additional readings which are quite informative.

Cons: Assignment auto-grader. This is still the biggest letdown of all the courses in this specialization Codes which work on your laptop or suggested elsewhere on Stackoverflow etc fails to pass the autograder, so 30-40% of the time of the assignment is spent on wrangling the code to pass the autograder.

Note: If i haven't taken a Machine Learning course by Professor Andrew Ng, this course would definitely be much harder. This course doesn't go to much into the background knowledge,and they mentioned this many times. But I appreciated the applied aspect, since this was what I was looking for.

I had no ML background, although I have the math the models are based on. The material seemed more than week's worth for a couple of weeks. The quizzes make sure you don't miss the key points you need to take away and need for the assignment. Most information or key words are in the slides, but course expects you to be independent enough (intermediate) to learn closely related ideas on your own via StackOverFlow and discussion forums. The discussion forums were especially helpful for this course, but then online discussions makes it more studying alone. Discussions helped me trouble-shoot and get better ideas how to approach the problems generally. I can explore and use ML and sklearn on my own, which thankfully seems to be a goal of this professor. No material could be left out, but when more videos, better longer time estimate for the week would be nice.

This course involves lots of concepts and algorithms in machine learning. As it is said by the teacher, for time, effort and aim limitations, this course only involves basic concepts and usage of sci-kit learn. It is a good hand-on course for beginners. Assignments are not so challenging compared with the previous two courses in the same specialization. I just finish assignments by following the module code in the course. I feel like not study as much as I expected through the assignment. I hope assignments can be changed by varieties and difficulties to let students know how a machine learning project is like and how the evaluation works but not simply call the precision/accuracy/recall function and the assignment finishes. Generally, you still learn a lot if you want 'applied machine learning'

I personally enjoyed this course much more than the previous 2 courses in the specialisation. Overall, this course is ambitious and covers a lot of different algorithms. For each algorithm, a brief intuition is provided and we are taught how to code in Python. For this course, I felt that the assignments were a closer fit to the content covered in the videos (unlike the previous courses where the assignments required much more independent learning). However, this course will not provide the mathematical rigour that some learners may expect. Furthermore, the amount of content covered could be a bit overwhelming. It would be useful if the instructor could summarise the different steps we should take when faced with a ML problem, esp. for deciding which algorithm to use (since so many were covered)

if you have a conceptual knowledge about Machine Learning algorithms, or at least supervise learning, this course would be very helpful for you. Otherwise, you are wasting your time.

This course is a programming session , helping you to implement the complicated machine learning algorithms using simple tools, without diving in any details or explain any mathematical backgrounds. So you supposed to build these fundamentals before coming here. For me, I took the wonderful course of Andrew Ng before this.

Furthermore, the course is very structured and organized, and its material, quizzes and assignments are greet , thus I consider their notebooks such a good reference I'll back to it every time I solve a ML problem.

Very good course. The content is excellent. You can get a good understanding of many popular Machine Learning algorithms. Maybe the most valuable concept you can learn is how to evaluate a classification model. It is also an applied course, so anyone more concerned of the applications than the theory will enjoy it.

The only drawback is that the evaluation of the assigments is done automatically, and you can have frustrating limitations for an answer that is correct but that is not EXACTLY as expected (I mean even the data structer have to much perfectly). The server also have quite restrictive memory limitations and the error messages are not always very helpful, but the staff will help you if you insist enough.

The course is an excellent tour of machine learning methods. The best thing is that it provides the python codes for various applications of machine learning. These can represent a great starting point for real applications. The significant parameters of each model are explained and the usage of the main models is well depicted. However, the course is very dense and I think it should have been divided in 6-8 weeks. At least the unsupervised learning part, which is optional in the Week 4 should have a dedicated week, with assignments. Before doing this course I recommend something like the course of Andrew Ng (without that one, for me it would have been more difficult to follow this one).

I found the course content ideal to start my journey in machine learning. It was a bit much for me to understand so much within so little time but now, I know where should I emphasize more and how to have more concrete idea and knowledge about ml. The course would have been the best if the content were scaled down to less and had been a bit more easygoing but people with high processing and patient brain might get the best output from this course. I did not understand a lot of things and had to self study a lot but thanks to it, I got a good start. Thanks

I found the course to be a little bit too much of a whirlwind for me to get much more than the broadest strokes out of it. A lot of the topics covered were mentioned very briefly without much explanation of when or how they should be applied - especially week three felt like a barrage of "this exists, this exists, this exists..." without much explanation, and I don't think I'll retain very much of it. The Week 4 assignment, however, was adequately challenging and did give me cause to go back, review and dig deeper into many of the topics covered previously.

Overall a good course! It was really what I was looking for: main focus is on how to apply algorithms and pros and cons of each model, instead of exhaustively explaining the theory behind each one, like some others courses do. The downside was the grade system. The platform has a lot of potential, but crashes all the time and there are many errors to troubleshoot when submitting assignments. The time invested to troubleshoot these problems was really frustrating, and probably the main reason i won't continue with the specialization.

The course is excellent and Professor Kevyn Collins-Thompson goes to the lengths and breaths to explain various machine learning algorithms and also provides a hands-on the syntaxes for the code to provide a deeper intuition to the problem. The course has a lot of info to be digested and one must go at his/her own pace to grasp all the details. There were some issues with the grader but thanks to the excellent mentors on the decision board, they helped me sort out all the issues. So thanks to the entire team once again.

Pros:The course provided me with a very good introduction about Machine Learning(in Application level), for example, the relative terms that be using, differences in classification and regression models, the validation metrics and methods, the related tools using in Python. It fulfills the application goal as the Professor said in the week1. I can utilize a lot from the course into my current work. Cons: The auto-grader could be improved better which can save learners lot of time debugging it.....

There's obviously been some reordering of videos that can be confusing and repetitive and the quizzes are not carefully worded which leads to misunderstanding of questions and answers. The material though, unlike in the two previous classes in this specialization, actually help with the assignments so that the assignments help what you learned in the classes. The material is also presented mostly at a reasonable pace (except at the beginning of the second week).

More detailed videos/maybe case studies on applying the algorithms in real-life jobs would be good. The assignments are generally fairly good, but can be pretty easily cribbed from the course module notebooks. While this is okay since knowing exactly what syntax to write is less important when there are a lot of examples online, it would be good to have the assignments maybe incorporate more thinking about the models and what they mean.

The course content was good and the assignments were designed brilliantly. I learned more while completing assignments and reading discussion forums. The auto-grader should be improved, it's time wasting and frustrating experience. No response from discussion forums even on technical issues can keep you waiting for weeks unless you solve the issue by your own by reading 2- 3 years old post and meanwhile lost money, time and patience.

Great course with the first three assignments being relatively easier and straightforward compared to the first two courses. The fourth assignment required more individual studying and comprehensive understanding of all course materials in building and evaluating prediction models. Having finished this course, I feel much more confident in my ability to work with machine learning algorithms with sklearn and panda libraries.

first of i would like to say thanks for my Almighty God for being with us all the way we do next i want to extend my thanks and appreciation to Coursera and my applied machine learing professor kevyn collins Thompson, i got this course it is very helpful for every body working on any technology apart from this i want to say a little about the course content that it was very nice if more practice added on it

thank you

Good brief explainataion of supervised algorithm , its working and how its put to use with 'sklearn' . Jupyter notebooks on each module gives you a baseline of how machine learning is done with 'sklearn'. Quiz arent bad either . May be the last assignment on the final analysis of given data to provide a prediction could have been made more challenging by including grade on the EDA and explaination of model results.

I enjoyed this course. Many people comment on the lack of theory, but I think as important as theory is, it is even more important to be able to practically use ML algorithms.

This course will set you up to start doing Kaggle competitions quite adequately. In fact, the final assignment is very similar to a Kaggle competition and open-ended enough to make you really feel like you need to harness what you've learned.

Great course for beginners to start with Machine Learning in python. With sufficient paraphernalia about the concepts, the course dives straight into the guts of ML and helps a lot in applying ML concepts to datasets. The instructor is clear and concise and provides enough auxiliary reading for familiarizing ourself with previously-unknown ML concepts. Thanks to both U Mich and Coursera for organizing this course.