Nice and practical. The assignments could go a step further in trying out different things to get better results.

Tensorflow exercise was not good , it could include some basics first. seems like only runnig it for no purpose

The contents are explicit and adequate but I think It would be better if I could get more exercise about coding.

It was great course, however, I would have liked it to be a lot slower with more time being spent on Tensorflow.

A great course!

I do feel that in order to become really good I now must apply the learned concepts myself soon.

Very well explained, but the Tenserflow explanation is shallow for those that have less programming experience.

This Course Helped me a lot in learning how to get best-optimized models by tuning Hypermeters.I really like it

A good course that provided more intuition on which models to work with and how to tune parameters effectively.

The Jupyter notebooks had a lot of mistakes which wasted a lot of my time otherwise the course content was good

Good lectures, but the jupyter notebook examples are inconsistent and sometimes use deprecated Tensorflow code.

I particularly benefited from the explanations of dropout, batch normalization and the RMSProp/Adam optimisers.

Many high level concepts are not explained in details so it felt quite difficult as a newbie in Deep learning.

Despite completing the course, I feel there is much more that I could be tested on to cement my understanding.

TensorFlow needs more time dedicated to it. I didn't completely understand the concepts behind this framework.

really loved the course material but would have loved it more if it gave more in depth tutorials on tensorflow

Nice and clean; with nice focus in the framework; but they also could be more in depth regarding the exercises

Great course by Andrew. The exposure and the length of what I had to learn changed the circuitry of my brain.

Some of the programming exercises weren't as polished as part 1 of this specialization. Still great overall!

Really helpful in terms of practical application and tricks/tuning for DNN. Also starts on TF which is bonus!

Quizes as part of middle of lectures help to check the understandings. For many lectures quizzes are missing.

explanation is very good but assignments need to be done comletely by student not like filling missing parts

The tensorflow portions need to be updated. Otherwise it's a great module, building on the previous courses.

-1 : Serveral bugs inside the assignments, causing 0 grades in auto grader

That said, a perfect intro to DNN.

sometimes the teacher speaks too fast to follow, but the content itself is very good and easy to understand

Maybe providing some video or reading resource for back propagation processes for batch norm would be good?