There was no exercise on hyper-parameter tuning so the course seemed incomplete. I think week 3 should be split into 2 weeks with first week focusing on hyper-parameter tuning and second on TensorFlow.

Ng is an excellent teacher, and it was fun to learn about programming frameworks. However, the programming exercises are very simple, and the videos about numerics go very slow, thus 4 stars and not 5.

Very good course, useful and smart. Some of the example are on tensorflow 1 but I think that they will update them soon to keras tf2 Thank you!

I will pass on what I have learned here to undergrads :)

very useful course, especially the last tensorflow assignment. the only reason i gave 4 stars is due to the lack of practice on batchnorm, which i believe is one of the most usefule techniques lately.

Assignment in week 2 could not tell the difference between 'a-=b' and 'a=a-b' and marked the former as incorrect even though they are the same and gave the same output. Other than that, a great course

great and practical insight. carefully crafted assignments. still coding in python and the quirks coming with it are sometimes of equal difficulty if not worse than understanding the explained theory

Excellent content. The grader seriously needs to be updated thogh. For example, it needs to be Python2 and Tensorflow2 compatible and also needs to be robust in handling common syntaxes such as "-=".

Would have liked to see the math and more complete explanations for all the things that Prof. Ng glosses over by saying "you don't really need to understand XYZ". Even if this material was optional.

Could have increased assignments and some more indepth knowledge of tensorflow and proper installation way of tensorflow cause mine is showing error when iam trying to practice as shown in the video

I think this course is great. Because we learn about some definitions about hyperparameters, optimization which are frequently appears in papers or in the functions in some Deep Learning frameworks.

very good course with deep knowledge of each parameters. Little bit stretched at tensorflow. A bit of overview on tensorflow API and tensorflow architecture could have been better before exercises.

Great teaching from Andrew Ng as always. Would've loved to learn the math behind optimization techniques, but nevertheless Andrew gave intuitions of the algorithms which cleared up a lot of stuff.

few minor errata within the assignments that haven't appeared to be fixed even 1 year after reported. But otherwise learned a lot and enjoyed the course style and will continue to learn this spec

one remark for the last assigment, the neural network to read the hand signs, once finished and validated , I tried with my own pictures from my webcam, and it never worked (always predicting 2).

Having a good understanding of tuning the Hyperparameters is key to build powerful neural networks.

The course helped me to keep a focus on tuning and understanding the relationships parameters.

very quick moving but the assignments were too easy - they give you too much of the code (both the surrounding code which is fine but also the precise code for running optimisers for example.

This course helped me a lot to clear my confusion regarding various Machine learning jargon of words. It gave a intuitive understanding and helped solidify my foundation in Machine Learning.

I like this course a lot! 4 star due to the programming assignment. It is well designed, but hope the assignment could be more challenging instead of just giving us a taste of deep learning.

There were a couple of bits of maths that weren't fully explained and the very final programming assignement definitely had missing explanations but otherwise was really engaging and useful

The concepts were explained in a very understandable way. I would give it 5 stars if it treated the subjects in a deeper mathematical way and if the tensorflow version used was 2 and not 1.

The course is interesting but I am not sure that the best learning strategy is to fill in some lines within a program. I am disappointed that I can not download the material for future use.

With the basic knowledge I earned in course 1, it was very helpful attenting this coruse on improving Deep NN and I took a lot of notes during the course, to which can refer in the future.

Nice course for improving deep neural networks , they will show the all the paths available to improve a neural network , all you have to do is explore it based on your passion and need :)

The course content is great but the ending lacks tensorflow implementation of regularisation, hyperparameter tuning, learning rate decay, etc. and aslo still not confident enough in those.

The final programming task might contain minor bug, passed all sub-sections, but the final one result didn't match with the provided results, better provide more info for easier debugging.