Loved the way the instructor has clearly set the expectations of the scope and breadth of coverage of topics in this course. However, if the course was a bit more deeper into intermediate level concepts, it would have given me more confidence to face interviews. Nevertheless, I would love to learn more from this instructor as he kept me motivated (and not bored) all through the course from start to the end.

Queries are not getting resolved in the discussion forum. So, instructors should participate in the discussion forum to resolve such queries.

The course is OK in the overall. But it has two main drawbacks from my point of view:

1) The final assignments asks for solving the task making use of routines NOT shown along the course: i.e. it's shown in the labs to solve issues in a way, and in the assignment it has to be done in a different one.

2) It was IMPOSSIBLE for me to get feedback from the Staff at any question. I ended up solving the issues by my own and through try and error, which is fine from a self-study approach, but when it comes to technical issues, it can get quite complicated...

The teaching is not deep enough to solve the Week 5 assignment, please take note you need to plumb in other Keras courses.

Details very well covered. I found it very much interesting and well explained.

It is a good Introduction course on Deep Learning using Keras.

The final assignment needs to be more user friendly.

The course does not cover using following concepts with keras - Dropouts, maxpooling, CNN, RNN, padding.

They have been covered in the pytorch course using PyTorch, which is entirely different from how we would use with Keras. It makes this course highly incomplete in terms of examples and assessments and I don't think I have learnt much here. There are way better free courses on youtube by regular data scientists (not from IBM) that include detailed concepts and examples on these left-out important content.

The title is not right. It is more a general presentation of deep learning then a présentation with KERAS.

Lab assignments are really good as they help in building the concepts nicely. IBM has really put together the best instructors. The videos were also very easy to understand. One more thing I would like to add is that previously I have tried learning Deep Learning from other places too but this course is the best.

Interesting course. Forward propagation, gradient descent, backward propagation, the vanishing gradient problem, (+ Regression, Classification, and CNN with Keras) explained clearly.

Quite good course on Nerual Networks. I would only welcome even more practical examples with practice coding but I was happy with this setup.

Really enjoyed the class, felt that the level of challenge was appropriate. Thanks for making this class available!

Excellent i understood the main principles of neural networks and the recomendations were very usefull

Very intractive and benificial course for me .Thank you coursera and IBM for this course

I really enjoyed this course, specially for all the labs and assignments. Thanks much!

Very good course to start with Neural Networks & Keral lib. Recommend for beginners.

It,s a very good course to get grip on keras and artificial neural networks.

Nicely packed in a small course. And the examples are pretty good as well

Super Class course ever I see. Thanks for give such best production.

Nice for start point

Good course for absolute beginners. Would have liked an extra week or two to 'manually build' some of the key neural network concepts from scratch as in the first week.

try to add more case study problems and solve it on lectures so that we can understand how to start (initialize) the coding part when we receive any real world problem.

I really like this course as it has only provided me with the tools that I need to understand neural networks without overhelming myself with abstract mathematics or theories. It is indeed good to be equipped with foundational theories and mathematics, but they do not build much intuition without direct practice. I believe that theories can be learned along the process rather than being stagnant because you cannot grasp them initially. With this course, I have become proactive because this is more concept-based and the mathematics has a good visualization to it. I like the way it is designed and how the final requirement aids you while allowing flexibility.

This course is highly recommended to those who have a background in Python programming, and interested in the basics of neural networks without the exhaustive mathematics.

This was a good course and well paced. But I have a comment about the final project. It was not clear to me if the same model was being re-trained and improved upon in 50 trials - or if the idea was to do 50 trials to capture just how good a model it is, using different splits of the data. Since we were asked to find the mean and sigma of 50 trials - I assumed those trials would be independent and each one performed with a fresh model - otherwise it is odd to find a mean and sigma of a system that is converging to a final result. In that case it's only the final mean and sigma of the final trial that matters. So I think some clarity would help there - without giving it all away with regard to how to do the project.