Avis et commentaires pour l'étudiant pour Nearest Neighbor Collaborative Filtering par Université du Minnesota

It would be better to provide other programming language such as python in honour assignment. And in the assignment should more emphasis on the algorithm not rely on too much others such as Lenskit.

(+) The course material is good with real world examples and interviews with different people.

(+) Interesting material

(-) The assignments had mistakes.

(-) There is no example provided for practice before jumping into assignments.

There is an error in the assignment week 4 : the spreadsheet normalize by user instead of by item

The course is less helpful than the others in the specialty. The lecture should include an example to help clarify the understanding necessary for Quiz Part II and Part IV. The instructors didn't respond to the many questions in Week 4 forum and I was unable to complete the course.

Some exercises have wrong directions !!!

instructions for assignments are not clear! Lectures are good, but its practically impossible to get the certificate.

Awesome as always, Joe and Michael rock. The interview with Brad Miller was stellar, felt like listening to the legends of rock-n-roll!

Very good course, there is a glaring error in Week 4s assignment. But if you check the forums it can be easily solved

Provides a good overview of item based and user based collaborative filtering approaches.

Extremely informative course! It would be great if the assignments are created on python or R in the next season's offering. Thanks for the knowledge!

Awesome Professors!Great Material.Very thankful to Coursera for providing this course.

All in all, it is a comprehensive introduction to collaborative filtering. It allows the reader which paradigms and what tools to use in specific situations. I still have some complains with the excel assignments though.

very nice

in-depth and well-made to follow

Very good assignments, honors track.

Great course, nice theory and interesting exercise with the sheets and making actual Java programs to implement the algorithms. I would love to see some more in-depth probability theory, and considerations about when the algorithms deviate from the theory, or connections to other theories, but I suppose the course is more accessible and interesting like this. The interviews are probably my favorite part!

Loved it...many thanks Prof. Joe for bringing this content to Coursera

I love it. Would be cool to be able download all materials in one big .zip file (e.g for searching using grep) ;-)

Very satisfied to do this, the videos are too long, very good quality and a lot of practical information.

I love it!

everything best. But technical support in Forum and when a student needs help when he is learning in Vienna alone is the worst

thanks very much !

a great class, I learned some insight in these algorithms

Exercises take time but really helpful.

Thank you so very much to open my eye see more view of recommendation field not only algorithms but use case and many trouble-shooting in worldwide business, moreover interview with noble professor.

Great learning experience about collaborative filtering!

Nice course!