Building a team to follow together the new Datascience Coursera courses starting next week

coursera            jhu_new_logo_large


Hendrik D’Oosterlinck is taking the lead to organize this initiative.


Coursera and Johns Hopkins University starts a full Data Science training. Why don’t we build a teal and do this together. Please comment on this post if you want to participate.


Let’s do this together !

Learn Data Science from one of the world’s top universities.
Johns Hopkins professors developed the Data Science Specialization to guide you from fundamental principles to advanced competency.
  • Gain hands-on Data Science experience with a Capstone Project
  • Showcase your knowledge with a Verified Certificate on your LinkedIn profile and resume
  • Adapt to your schedule with courses repeating monthly
  • Have unlimited retries for up to two years while available
Happy learning,
Coursera Team

18 thoughts on “Building a team to follow together the new Datascience Coursera courses starting next week

  1. Completed third course of the specialisation track this week. Insightful if you’re new to DS and R. If you start with R from scratch and you really want to learn/understand the principles it takes you more time than the recommended 3 hours per week (except the first course, that can be finish in a couple of hours). Interesting course however for those new to R, DS and programming!


  2. Very good idea. Participating together will be stimulating and hopefully increase the chances that we complete successfully. As an alternative, and probably a bit less ambitious, we could form a group and follow Andrew Ng’s Machine Learning, also on Coursera. I’ve just completed the first two weeks, but it’s still possible to register.


  3. I’d be happy to participate as well, if time allows. I’ve done a few of these courses already. my goal wouldn’t be to complete all (or any) course. Just share what we’ve learned and help each other out if needed.


  4. I actually did the first two with certification in December, “getting and cleaning data” and “Exploratory data analysis” this month with certification and “statistical inference” without the certification that I plan to certify next month along with “Regression Models”. I also plan to follow at least machine learning in the future.
    As a particle physicist, willing to move to business, with a data science background but used/trained to specific tools (developed by CERN) or self-taught tools, I found it really interesting in the full R continuity. It allows to develop a certain R expertise on all the data analysis related steps even if sometime the technique/content behind is not new to the “student”. (Introductions to some file formats, …)
    I would not recommend to take the first one with certification (unless to validate the full specialization ), as it’s really introductory and a description of the specialization lectures+git manipulation and R installation.
    To a newcomer to both DS and R, as said by other, some weeks may require more time than the announced one. (As time is needed to do some projects but you also have to review at least 4 other students projects the week after)

    I would also recommend to have a look at the very good ” Analytics Edge” by the MIT on edx.


  5. I’m completing courses 4, 5 and 6 this month.

    Overall I’m pleased with all the courses except #6 “Statistical Inference” which is very difficult to grasp from the lectures in the course. You absolutely need to first study the topics (eg from the book “OpenIntro Statistics”) and then watch the video lectures.
    (unless of course you have a statistician background).

    Somebody here mentioned “Andrew Ng’s Machine Learning”, and that’s a MOOC that I can recommend! Best MOOC ever!


    • Have you completed it? I haven’t got around to it (between work and the DS specialisation). Now starting the Data Mining specialisation from University of Illinois. I understand Andrew Ng explains his course matter very nicely.


      • I’ve completed the Andrew Ng’s MOOC, and indeed I can recommend it as the best!
        If you would separate the documentation of the exercises from the rest of the course, you would still remain with a great course!
        (so well documented and explained are the exercises).

        The only downside I find is that the course uses Octave (Matlab), and I would have preferred R. But you can easily pick up Matlab.

        Liked by 1 person

      • I agree with Willem – Andrew Ng’s course is very clear, very well presented. Where I do not agree with Willem is his preference for R. Though I am an R user myself, I like to learn new things, and Ng’s course is an excellent way into Octave.


    • That’s me, feel free to email! We’ll look at setting up meetups and how we can tackle this thing best.

      My background: Physics & Astronomy, Weather and Climate Modelling at the UGent. For 1 year I’ve been a Computational Scientist at, a Belgian food-tech startup predicting novel foods & drinks pairings.


  6. Just discovered this thread, count me in.
    I am about halfway the Data Science specialization, now in “Reproducible Research”.
    Did several Coursera Courses before (>30), some data science related (see my linkedin profile), also doing some courses on other paltforms, ie edX The Analytics Edge, Stanford Online – Statistical Learning, Information Visualization MOOC – Indiana University.


    • Hi Ronny, can you say some more about those other courses? Specifically, what were the qualities of the videos, and how advanced were the classes? I’m looking at more than just this Coursera Specialisation track and want to make sure I don’t do 90% of the basics again.


      • edX The Analytics Edge: very high quaility course, beginner to intermediate level, excellent video quality, very engaging examples, somewhat longwinded exercises, examples and exercises in R
        Stanford Online – Statistical Learning: intermediate to advanced level, good quality videos, feels like a more traditional university course with 2 instructors. Examples in R
        Information Visualization MOOC – Indiana University: intermediate level (they claim advanced graduate level), limited to visualization only, video quality is good, theoretical concept videos are ok but the hands-on ones are rather boring. They use their own toolset Sci2. After the final exam there is a client project you do together with on-campus students, I guess this is quite unique. Very few (<200) MOOC students.
        Coursera Machine Learning (Andrew Ng): one of the first Coursera courses by one of its founders and still one of the most popular of Coursera. Excellent material, examples and exercises in Octave (Matlab)
        These are just my opinions, not necessary your truth.
        Have a look at where you can find all major available MOOC classes including reviews.

        Liked by 2 people

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.