Lectures/Videos were excellent, the assignments were very poor (loads of errors in the code not corrected over 7 months since the course went live)

The course videos were very lengthy and difficult to follow. Many topics discussed in course video were not part of programming assignment

Good introduction to the concepts. Really poor quality videos and exercises. Very frustrating when working on the assignments.

Good lectures. Programming assignments are useless fill-in-the-blank exercises, you don't really learn much from them.

The programming assignments really are like pulling teeth. There's not really enough guidance leading up to them.

The course videos and the programming assignments were lacking. And there was no support in the forums.

Spent more time trying to work around a buggy grader than learning the underlying concepts.

Too hard to understand compared to the previous coursed in this specification.

Was very difficult. please add more expiation of mathematical equations.

Little unsatisfied with the final part of the specialization.

assignments are very hard and needs lots and lots of search

Lack of Keras training made it often hard to do layer code.

This course needs more instruction on Keras.

Poor explanation for alot of things

boring and uninformative

Too difficult.

Needs work.

I feel sad.

sucks

The course overall taught me new things, but I am still kinda unsure how to exactly use it.

The exercises and explanations weren't as enlightening as earlier and unfortunately left me rather confused, despite passing 100%. You definitely need to consult a lot of other sources for understanding the topic.

The last transformer exercise left me stunned though in how bad it was. When I understood something it contained obvious mathematical inconsistencies. It was the first time I needed the forum help, which is outside the coursera website and they force you to sign up in addition to coursera.

The tutor reacted fast but extremely patronising, going so far as pretending mistakes in the exercise didn't exist, but very eager to blame me for using an outdated version, that I wasn't using.

Did not enjoy the experience.

Oversimplifying material, such as not showing any math foundations and proofs, does not lead to an intrinsic understanding of the material as well as fill-the-gap assignments do not enhance comprehension.

I understand that the course is intended for the broad audience but will one be able to implement those Keras and TensorFlow algorithms on a moderately complex problem, which is the ultimate goal of these courses? Highly doubt it because the code is pre-written for students and step-by-step guide is provided. In my opinion, one could go straight to assignments and induct / deduct the answers.

I love Dr. Andrew, I seriously do. He has inspired me in the field of Deep Learning like no one else did. But I detest how this course is made so expensive and in a wrong direction. I subscribed and paid $225 and I still was not given a decent amount of time to finish the course, even when I asked for extension. If this is the way these courses are, its better of learning from youtube. It is not worth the money

Dry and uninformative. Immense space for improvement. Corrections should be made to videos instead of having numerous revisions comments after lecture. Some variables introduced haphazardly. Notation not explained well, some clashing with linear algebra conventions. Coding exercises are elementary hyper guided.

Grader is the worst and no help even in the forums inspite of getting the same output the grader is still failing and no one is telling why. Forced to drop out of this course now

Clearly the less structured and more confusing Course within the DeepLearning Specialization, a bittersweet end to an otherwise great set of courses. Quite disappointed.