Google Cloud による Art and Science of Machine Learning の受講者のレビューおよびフィードバック

Now that's what I am talking about. Great survey on nuts and bolts of ML practicalities. The how and why of model generation and manipulation. Very excellent. Super library of reference models and materials.

great

This course is of specialization is the most applicable in the case of my work. If customer estimator was explained in the earlier courses, many other experiments with our own custom estimators could have been tried.

Advanced and detailed course for accurate tensorflow models

good lessons and in depth coverage of a range of issues

Really good course with a lot of practical examples.

Nice tutorial

Nice course however I think it suits folks who have good exposure of ML to take complete advantage of the techniques

Very good course, but probably requires some more hand-on practice

great

best course in the specialization!!!

It would be nice to have more complex datasets where predictions would be more meaningful.

Excellent Course, in the Art and Science of Machine Learning, I quite enjoyed the Hyperparameter tuning in the Cloud and all the advanced tips to improve the models performance, thanks Coursera and Google

The course is quite good and have balance of theory and labs. It is useful course for beginners.

Many notebooks contain some typo/erros.

There are some lessons where the concepts are exposed in a too fast way

I felt that hand-on or explanation was not sufficient. Coverage is good.

Some tough concepts !!!

Labs were very confusing. Explained theories well but in practice didn't really learn much. I wouldn't recommend if you're a beginner. Google has a very interesting way on teaching.... On that note they should stick to building tech, never teaching. Didn't really learn how to build anything in ML, sort of skimmed on some API's they offer. In reality, the first course was probably the best... The rest of the specialization was just a rinse and repeat sort of thing.

Pros: Tensorflow is an excellent framework for deep learning

Cons :

1- The way this material is designed is 10 X SHIT

2- Either teach properly or don't teach at all.

The notebook based demos are unfortunately pretty useless as labs. All of these courses would be much improved with real labs that require the student to build the system.

poor labs