Great introduction.

I have two suggestions:

1- GraphLab is a great tool but it is commercial and it is not available in all companies. Hope there were some guidelines, slides with sample source code etc. for each session showing how to complete assignments with an alternative free library.

2- In the slides, I found very useful practical hints mentioned quickly by the lecturers (e.g., how to fit a better regression model by using the same feature with higher order such as X^2, X^3, X^4...). There is a high chance to overlook such hints since they are mixed with other materials. It would be nice if such practical hints are gathered and published in a separate document like a cheat sheet for future references.

The instructors are amazing and teach at a pace, which is slow enough for things you are new to but fast enough for more familiar things. I had decent machine learning background but none of SFrames. However, I had no difficulty understanding SFrames from the word go. The assignments are the best part. If new methods pop up in the programming exercises, step by steps instructions explain how to use them and you learn even more that way! (some of the hint/help links in the assignments did not work for me). Instructors used a lot of examples during lectures but I felt that theoretical part was lacking depth (may be it is me because I always like to see more maths :D). Carlos was great so were his shoes :D

This whole specialization is an outstanding program: the instructors are entertaining, and they strike the right balance between theory and practice. Even though I consider myself quite literate in statistics and numerical optimization, I learned several new techniques that I was able to directly apply in various part of my job (ok, not in the foundations course, but in subsequent courses). We really go in depth: while other classes I've taken limit themselves to an inventory of available techniques, in this specialization I get to implement key techniques from scratch. Highly, highly recommended.

FYI: the Python level required is really minimal, and the total time commitment is around 4 hours per week.

This course was not very simple to understand for me, because i'm not a native english speaker and my english knowledge is academic; but thanks to english subtitles and transcriptions of videos i was able to keep pace with teachers as they talked and thanks also to the excellent learning material. The mathematical concepts explained are clear and concise, lessons are not lost in learning theoretical ramblings, but everything is set for the application of the acquired concepts in real life.

Python is very simple programming language to learn, but if you want to deploy a real machine learning application you must study other aspects of the language that, rightly, are not covered in this amazing course.

This is a fun course that gives you a very good overview for different machine learning methods. It is indeed a case study approach which is very nice because you get an idea of how versatile machine learning and its application really is. Plus, you get to solve some meaningful questions using machine learning yourself. This first course doesn't explain how the algorithm works in detail but on a higher lever so that you understand the underlying idea and principle.

The videos are super fun to watch as Carlos and Emily are super likeable, and very engaged and excited about the things they're doing and teaching. Thank you so much, I had a great time doing this course!

I took the 4 (formerly 6) courses that comprised this certification, so I'm going to provide the same review for all of them.

This course and the specialization are fantastic. The subject matter is very interesting, at least to me, and the professors are excellent, conveying what could be considered advanced material in a very down-to-Earth way. The tools they provide to examine the material are useful and they stretch you out just far enough.

My only regret/negative is that they were unable to complete the full syllabus promised for this specialization, which included recommender systems and deep learning. I hope they get to do that some day.

The course gives an excellent overview of the main types of algorithms in Machine Learning. The lecturers are both very clear and I like the combination of annotated lecture slides and jupyter notebooks.

My only problems with the course were with the coding/assignments sections. Because of the choice to use GraphLab, I was forced to install a virtual environment with Python 2 to be able to run the jupyter notebooks myself. I understand the choice and agree that GraphLab is a very intuitive and easy to use module, however if it is not going to be updated for Python 3 then the coding sections should be re-recorded using a different library.

This is one hell of a course

This is basically a good introduction to each and every basic ML technique, what makes this distinct from the other courses is that, you really get your hands dirty with writing code on Python, which is really an industry relevant language for Data Sciences and ML

The theory is also, taken in detail and the assignments are cleverly designed, this course was a joy to take. Initially, I thought that I would complete this course in a span of 6 weeks, which is actually prescribed. But, the fluidity of the course content was so great, ended up completing the course within a week

Definitely, taking the advanced courses

I appreciate this course that is one of the best mooc courses I ever done.

Being a computer science engineer, I found the "hands on" approach particularly amazing, it lets you immediately start applying the topics with real use cases.

I started this course after completing the Machine Learning course of Andrew NG (Stanford University), and this made a perfect companion.

I think that if I didn't have followed the NG course, probably I would miss something from the theory, particularly maths and statistic that in this course are missing. (in any case where superbly covered by NG course)

Thanks a lot for the course

Stefano Priola

Turin Italy

Excellent Introduction to the Machine Learning applications. This is course does not cover all the "details" of the method, but rather just prepare/motivates the use machine learning. Only criticism would be that course relies on GraphLab Create, but frankly speaking this is quite alright as I mentioned that the point of the course is to deliver the motivation and show some interesting applications of machine learning rather than explaining every detail of each module. If you want more details, take the entire specialization where you have more freedom to write your own code without the use of the use of Graphlab.

Excellent introductory course on Machine Learning. The material is taught at a level that does not require much in terms of pre-requisites, both in terms of the math and the programming requirements. From my perspective, I have an extensive background in Math, and some background in programming (MATLAB, R). I had not used Python prior to this course, and I found that I could keep up and learn both some Python and ML. I was able to finish the course in two weeks. Well done to the instructors who made the videos fun and accessible. Recommended for anyone who wants to learn something about ML.

Amazing course on Machine Learning.I have tried other courses on Machine Learning but none has made it so simple for me as this course.I started other courses but at some point I was stuck but this course explains all concepts so easily and gradually .Highly recommended for anyone who want to start learning machine learning.Even if you do not have programming experience, its easy to follow.

I congratulate both the instructors Emily and Carlos for making this brilliant course.

My most favorite part of this course is when Emily is trying to pronounce the name "Pele" and Carlos corrects here lol.

A very well designed course. This course clearly sets a path for introducing basics and fundamentals in a way that makes it challenging but insightful. It establishes the purpose for more advanced courses in this specialization and the need to dive deep in this fascinating subject (machine learning).

After completing this course alone, I can say categorically, there is no turning back, there is no sitting on the sidelines, there is no learning something peripheral. Doing this entire specialization will make any successful learner a very successful contributor in the world of Machine Learning

A little touch on the basic concepts and a detailed step by step tutorial on applying ML using python packages, this could serve as a good complement to the beloved Stanford ML course on Coursera. For someone who is just getting started with Python, I think this course would be significantly more useful if the packages used are pandas and scikit-learn, since those are more heavily adopted in the industry. The course is well organized and the programming examples are fun. This is a great introduction course to ML and I do expect highly of the subsequent courses in this specialization.

I have a fairly good background in mathematics and have read through major parts of the Deep Learning Textbook by Goodfellow et. al. One year later I wanted to revise ML again. People who are complaining that there is no mathematical or algorithmic rigor in this course need to understand that this is meant to be an introductory course in order to pique interest in the learner and drive him/her to pursue this field further. Heavy focus on math and algorithms straightaway does not work for most people. Hence, I conclude that this is a good intro course which does it's job quite well.

This course provide a very intuitive explanation of different machine learning models. It also has a good blend of hands on programming. Especially the combination of python notebook and graphlab give a unique experience. The visualizations from graphlab are amazingly good. It's really additive.

I would like to Thank Emily and Carlson for their great work in putting the right level of content for this course keeping the audience in mind. I feel bottom of my heart that I could really learn something significant and meaningful.

Overall, I must say it was an awesome experience.

Machine Learning is here to stay. Period.Course content was awesome, gave me lot of insights. The content are very well versed, assignments and quiz are quite challenging and good.

There was a impressive focus on the basics and fundamentals of each topic.

Great overview, enough details to have a good understanding of why the techniques work well in real sectors(especially retail,healthcare,financial services,etc).

Finally I would like to thank the LKM Team of Accenture for giving me the wonderful opportunity to learn this course and upskilling myself.

Regards,

Pratyush

I love the case-based method and the focus on the practitioner. Almost every other competing course and textbook puts too much focus on the mathematics proofs, on the nuts and bolts of the algorithms. I also like the informal attitude of the instructors.

The dependence on Dato, and the fact that Dato does not have a student or home use pricing are bad. After learning all of this, am I supposed to buy software that costs US$ 400 per month (matlab has a student edition for a one time price of $90)

Continuem o excelente e inspirador trabalho! Obrigado Carlos & Emily!

This is an amazing course. I completed my beginner's course in python using Microsoft's resources that were made available on youtube. After that, I took this course, it needs a good amount of patience and some basic knowledge of python to understand the lectures. As you move ahead in the course, the professors make you feel really comfortable with the theories followed by a quiz on theory and then a practice assignment followed by a quiz to check our understanding of the subject matter.

The six weeks of hard work will surely be useful for the rest of my career.

Good overview and introduction to the more detail content of the following courses. If you are not familiar with Python, this will ease you into the language and enable you to follow.

There is a certain style of teaching that you need to get accustomed too in the beginning but when it is done, lessons become very clear and easy to follow. Moreover, it becomes "so what is happening next?" and you are looking forward to the next lesson.

Again, this is mainly an overview (with content) and a lot of the material will be reviewed more in detail afterwards.

I really enjoyed taking this course in Machine Learning. It is my first course in machine learning. The instructors are really great. I like the course logistics, and how it builds up the foundations of the critical thinking in machine learning, rather than learning specific tools. I am really looking forward to complete this specialization with the Capstone project.

I know how hard it can be to prepare an entire specialization like this. I appreciate the time and the effort the instructors have put to make this specialization happen and see light.

This is an incredibly surprising course to me. Learning an up-to-date ipython notebook along with carefully designed instructions helped me have a better understanding of what machine learning is about and how it can be approached. Even though the last part was somewhat challenging to me, I learned a lot from this course and more than anything else, I could have some sort of vision in machine learning. I would like to keep working on machine learning specialization. Thank you for your warmhearted and incredible instructions! Thank you.

This is an excellent course for the starters to get holistic insight on the niche world of Machine Learning.

It is also a revisit to the notebook where you will spent time in evaluating truth tables and drawing planes to derive answer for assessment questions, a refreshing change from the regular work.

I am sure in-detail sessions/courses following this foundation course would definitely be of great learning and look forward to be part of those sessions and get enlightened on the new disruptive technological milestones.

Thanks,

Vaibhav

Fantastic course. A great, high-level, and gentle introduction to the most important machine learning techniques in use. The professors also co-own a market-leading machine learning company that produces a tool for machine learning practioners and data scientists called GraphLab Create. The tool itself is also fantastic as it not only creates and manages the environment for the Python notebooks and neatly installs Anaconda for you, it takes the guess work out of applying some of the more sophisticated machine learning models.

I lost a week getting access to the course materials. Using the coursera iPython notebook did not work because of issues with the GraphLab key you have to individually obtain. Still I have to give this class 5 stars. Because, after that large hiccup, the material is fantastic. Emily is a great teacher and walks you by the hand through all the material. Sometimes I have to watch the videos twice, taking lots of notes, but if you put in the work, you will have a real intuitive understanding of the course material.