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...

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 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.

The video and Jupyter notebooks were both concise and of excellent quality. However, the versions of dependent libraries are somewhat outdated, which makes it quite challenging to run locally.

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

The final assignment needs to be more user friendly.

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

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

Amazing material but very outdated. I was able to figure things out on my own but those not as good at debugging may run into very difficult to over barriers. That said the course is fantastic. If it gets an update I'll raise the score.

If you want a surface level overview of most of the machine learning algorithms out there, than this course will do that. But I'm not sure that it does a much better job than what you could learn by watching youtube videos for free. The "practice notebooks" are extremely disappointing. 1) There's nothing to test you on any of the material you learned in the videos, you're just running cells in a Jupiter notebook that have all already been coded (which you can do for free on the Keras website). 2) The data they use in the notebooks is just randomly generated numbers most of the time, which is absurd considering the numerous free data sets out there that contain real world data. 3) The machine learning models that they put in the notebooks are sometimes broken and do not even train properly to accomplish the task that they claim to do, which makes parts of this course honestly worse than the free material you can find on the Keras website. Overall I am very disappointed that this is the kind of material being put out by IBM. It makes me feel like they paid a few interns to slap together a machine learning course so that they could make a quick buck on Coursera based solely on their name recognition. If you want to learn deep learning, I'd recommend DeepLearning.ai courses instead. Some of the DeepLearning.ai video quality is a bit lower than I would like (I don't know why Andrew Ng uses such a bad camera lol), but the videos are much more in depth and you actually have to code and interact with the Jupyter notebooks that the DeepLearning.ai courses provide, which is the #1 most important thing in my opinion if you want to get into deep learning.

Many of the small doubts are not solved and its hard to understand from lab .

The course provides a nice and comprehensive overview of the neural networks (shallow NNs, CNNs, RNNs) and their applications. The most abstract and foundational material is prepared for the beginning of the course with the concrete implementations of the networks later on in the course. Just one thing to mention is that the Lab dedicated to transformers and autoencoders was not quite comprehensible as the code complexity did not really match how deep the topic was discussed in the video.

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