Great intro to TensorFlow Framework. But the last programming assignment was still giving low percentage accuracy without any notable fault in the code.

The content was perfect but last programming assignment was excruciating! But I thank everyone involved in making this course, it was unbelievably good!

I feel like the second course was better then the first one. But there are a couple of typos in some assignments and the assignments are still too easy.

The intro of hyper parameters was from mathematical point of view as good as the basics of week 1, however practical relevance becomes not really clear.

As always - excellent lectures by Andrew Ng. However, I think that the programming assignments tend to be a it too easy and a bit too much "copy/paste".

Really enjoyed the course. Only suggestion is to talk about the programming side more in the lectures but overall I'm really happy Thank you very much.

In the last exercise of last week, we have to use TensorFlow v1 which was quite annoying if you already have learned tf v2 other than that great course

I wish prof. Ng provided more intuitions into underlying math particularly why gradient optimization techniques help. But like it anyways, very useful!

Great material, few minor errors that need fixing throughout. Noted in forums. I expect this will improve as more take the course and feedback applied.

Week 3 programming assignment required notions not touched in the training or mentioned in the instructions. Required lot of time to find information.

This course has to be updated!!!!! TF 2.0 is what we are using now, and especially for new users, it is important to start from the newest frameworks.

I missed in the course an explanation and possibly a programming assignment of different tuning algorithms, such as random search and Bayesian search.

The coverage on the subject was adequate but it will really help to make a pdf supporting document to highlight the hyper parameter tunning approach.

Probably a little too follow your nose at this point in the specialisation. But none-the-less very good. Would give 4.5 stars if that were an option.

Still some flaws + inaccuracies + video sequences that should be cut out. I think the organizers should really do it as people are now paying for it!

Last Tensorflow assignment has some output typos and bugs when using operators like @ and +. Course was ok, but that assignment took me way too long.

Great course to deepen my knowledge after first course. However, I would like to access more programming exercise for practice. That will be perfect!

I think this course would benefit from a little more explaining. There are a lot of new concepts and some explanations were too quick in my opinion.

The introduction to TF felt rushed, but maybe that's to be expected given the goals of this Course, which didn't include a kickstart of learning TF

A very good course but I had high hopes for a practical session (Assignment) with application of hyperparameter tuning, with Tensorflow or without.

Теория хорошая, но практики во первых мало, во вторых на устаревшей версии тензорфлоу. Но зато в теории все разжевали. Очень круто все объясняется.

Enjoyed this course, especially the material that goes a bit deeper (different optimization methods, parameter tuning) and the intro to TensorFlow.

Less exciting than the first course, but this course is important to understanding the parameters that could affect a neural network's performance.

I feel like the course is a bit too easy. I would recommend making it more difficult by letting the end-user try more hyperparameter tuning tests.

what I did recognize in the deeplearning specialization that there are now further reading suggestions or reading syllabus like the other courses.