Amazing lectures as usual for Ng's courses. Nevertheless programming exercises are like "drawing connecting the dots": some additional effort would be useful in order to "deeply learn" the subject

Most Amazing Course on CNN. Every Concept Is explain by Andrew Ng is crisp and clear. Programming assignments are well designed and very important for getting the point. highly recommended course

This course has a little jump for using keras and tensorflow. There were parts where i had to look up a lot of tensorflow manuals to figure out. Hopefully there could be more information on that.

Very nice and crisp explanations with hyperparameters , I wish he had explained the segmentation part and other image processing techniques in deep as well. Neverthless this is a 4.5 star deal !

If you are not yet familiar with Tensorflow, the programming assignments are much more tedious than necessary. However, the explanations of the theory are quite helpful in visualizing convolution

Some programming assignments do not have the same level of "finish" as the other deep learning / machine learning courses by the same instructor, but very good in-depth material that helps a lot.

Great material, but the programming assignments feel like more of an exercise in figuring what the author is thinking than a challenge for me to learn the tools necessary to go do this on my own.

The overall course was excellent. It's just that I wanted to learn some more real-life based applications of conventional neural network. Thanks a lot for this course. It was a great help for me

This specialization needs to have a guided challenging final project. The projects are spoon fed and great for learning. However, a certification should require a more challenging final project.

This course is really great, the explanations are very clear and easy to follow. The lab environment uses a very outdated TensorFlow version, making it difficult to find official documentation.

There were some topics which were taught in last chapters, however, had they been in beginning could have given better understanding. Like 1-D 3-D conv, intuition about deep hidden layers etc.

Overall an excellent course, but some hints and guides of the assignments are not clear or misleading. If you work through them however, you will gain a lot (on how to implement these models).

As machine vision engineer, I was most curious for this one. And I haven't been disappointed. "Secrets" of convolutional architectures are revealed in a way that they are no more rocket scienc

Would like to see more of an involved exercise for either keras or tensorflow, perhaps using tensorboard visualizations. Good introduction into CNNs and where the art/science currently stands.

Some bugs to work out of the course content and I think the team should post the slides. The hands-on technical training is very good. I'm looking forward to implementing these in my own work

Excellent course, hope it adds more instructions on tensorflow and keras. wasted a lot of times debugging programming exercise due to tensorflow functions and structures. but fun experience!

The Deep Learning courses taught by Prof. Andrew Ng and his team have laid a solid foundation for me to kick start an interesting career in AI. Thanks to Coursera for this great opportunity.

Good course. Would have been great to see a little bit more of the history of how these filters or convolutional operators came about, and what is the mathematical motivation and properties.

The course is great, but it's almost impossible to learn in China without a vpn. Even if I got a VPN, I cannot connect to the jupyter notebook stably. And the course project is quite easy..

The grader is not robust enough to find out if the code is correct. It fails for semantic differences (not errors) even when the correct output is obtained, the grader still grades is wrong

the projects was not so helpful, even tho i learned by the end of course 5 that this is just the technical stuff, and the coding projects is in other coursers of specializations, so thanks

Great content, intuition, and examples. Some of the logistics and technical components were a bit more glitchy than the previous courses in the specialization - but that's a very high bar.

The course content is very good. I faced some problem in the assignment section. Even though in all the sections I was getting the expected answers I was not able to pass the assignment.

A very comprehensional lesson about convolutional netwoks but there are some little problems of the programming exercises that some of the contents may not be right and not fixed on time.