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.
Hope can elaborate the backpropagation of RNN much more. BP through time is a bit tricky though we do not need to think about it during implementation using most of existing deep learning frameworks.
por Nachiketa M•
This course was good but in comparison to the other courses in the deeplearning course series, this course lacked adequate depth.
The course is a good course because the lecture Ng.W ,but the exercises is not easy for our beginers for such tools like kears.
por Seng P T P P•
The programming assignments in this course are difficult to implement. The detail descriptions are needed inside the notebooks.
por Thomas N•
Good subject, but a lot of the course material (like lecture slides and problem sets) was either unavailable or out of date.
por Vinjosh V•
The videos are great - however it would be useful to provide some help on how to implement the concepts programatically.
por Søren M•
Not as good as the previous courses in the series, and some of the assignments where broken, and super hard to debug.
por Laurent B•
Only on NLP applications, it would have been great to apply GRU or LSTM on numerical data like finance for example.
por Devansh K•
The content covered is interesting, but I feel like the explanations are not as intuitive as the previous 4 courses
por Sandeep P•
Nice but little stressful. After completing 5 courses in a row, really feeling exhausted. Thanks for the good work.
por Rudolf S•
Quite a lot of bugs in the first week examples. It took me too much time until I browsed the discussion forums.
por SHALEEN A•
the videos are programming assignments need some serious updates, too many typos and wrong information present
por Maysa M G d M•
I think you have to know more keras than is explained in the course. The keras documentation it is not enough.
por Raghav G•
An average course, it is detailed though some of the ending materials get too difficult for me to comprehend.
por Mikey K•
Assignments are very buggy and instructions misleading or incomplete. However the core material is excellent
por PANKAJ R•
Require a little depth, considering the complexibility. At least 4 Week course should be their instead of 3
por Gargi V•
There were a lot of issues with the notebook especially, for the week 3. The concepts were well explained.
por Mikko L•
Would have required more of the "intuition" building material. Worst of the 5 course series, but still ok!
por Shengyu H•
Contents are way too easy and the video recordings are often a bit broken (repetition, blank audio, etc.)
por Alexander B•
incredibly boring. I mean at some task you literally asked to type in "= False" instead "= None". Really?
por Jinxi W•
There are some mistakes need to be correct in the assignments. Still a lot of improvements can be made.
por Yao G•
The assignments should be improved. More prep on Keras will help improve the efficiency of learning.
por Kabakov B•
The practical tasks is bad. You are simply needed to rewrite formulas to python most of the time.
por Benoit D F•
Very interesting topic but coding exercices and quizzes were a bit clunky and in need for ironing
por Andrei M•
The content is super interesting, but the assignments are more of the same 'fill in the blank'.
por Lars O A•
Put to much focus into getting the Keras code to work instead of truly learning the algorithms.