The course is very good and has taught me the all the important concepts required to build a sequence model. The assignments are also very neatly and precisely designed for the real world application.
Great hands on instruction on how RNNs work and how they are used to solve real problems. It was particularly useful to use Conv1D, Bidirectional and Attention layers into RNNs and see how they work.
von Clashing P•
assignments are very hard and needs lots and lots of search
von Arsh K•
Lack of Keras training made it often hard to do layer code.
von Tom T•
This course needs more instruction on Keras.
von Mark N•
Poor explanation for alot of things
von Milica M•
boring and uninformative
von João P B D•
von Martin B•
von Alex L•
I feel sad.
von Selina M•
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patronising, going so far as pretending mistakes in the exercise didn't exist, but very eager to blame me for using an outdated version, that I wasn't using.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.
von Aldiyar K•
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.
von Venkata D R S•
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
von Franjo I•
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.
von Krishnamurthy N•
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
von Inaki O d L•
Clearly the less structured and more confusing Course within the DeepLearning Specialization, a bittersweet end to an otherwise great set of courses. Quite disappointed.
von Deleted A•
I would like to abandon this course and stop paying for a course I want to prepare better before maybe launching a new attempt..
von Hasan A•
many ideas where not clear and more application use cases needed.
von Girish S•
Can't even see the programming assignments without paying money.
von srinivas a•
Not practical, Assignments can drain your energy.
von Khoa L T•
The explanation is not quite clear in this course
von Archideb S•
Glitchy Notebook, Minimal assistance at forums.
von Seyhan E G•
This one is way more difficult than the rest:(
von Jainam S•
Poor and unclear explaination, waste of time
very long with many unnecessary videos
von Mohammad H•
Not practical and just complicated!