The best thing that I get from these courses is to learn about intuitions all the time. Although I really enjoyed that part on optimization and parameter tuning , the same standard wasn't kept in TF part. What is tf graph? why do we need it? why session? .... Unfortunately the tf docs fail on explaining these concepts as well. If I don't get answer to those questions here, then where?

I am slow on the uptake on the maths side of the equation, while the repetition of the class lectures is most appreciated. No, it is not repetitive, Andrew keeps expanding on our prior knowledge for each week.

Even with 30 plus years since I did Calculus I am able to follow and understand thanks to the team.

Though, they do need help with correcting some minor mistakes in the webpages.

i learnt a lot about tuning Neural Networks through various optimization and regularization methods in this course. this helped me a lot in understanding the working and derivatives of optimizing neural networks through various algorithms. this course is making the foundations of deep learning look easy and understandable than other sources to the person who is taking up this course.

I appreciated the whole course, particularly when Andrew NG explains step by step a new topic (for instance Adam algo).

This course has a very good level.

However I wish some general functions from SkLearn of Tf... were presented to go from from-scratch functions written in this course (essential to understand the pedagogy) to generally used ones (in particular by ML-DL engineers).

Well structured course. It shows a great overview on hyperparameter tuning.

It would be great if the lecturer could keep the voice tone as he speaks, especially in long explanations where you can feel how his voice tone is going lower and lower, and then suddenly on the next video cut it goes back to normal exploding you ears ( as you had to increase the volume of your speakers)

Great course on hyperparameter tuning. Some of the code projects used the same variable names repeatedly in different contexts, which, to me, at least, is a bad practice to encourage in students. Also, in the Tensorflow project, some additional numerical calculations would have made it easier to catch issue earlier. But Andrew Ng was amazing, as always - clear and informative.

Excellent content provided by a world-class expert in the field whose didactics is on point. Great selection of applications. Not much mathematical formality and programming assignments not really challenging as an assessment tool. It's definitely the theory one might need to amass upon the first course's content, however what was previously easy enough is now even more so.

The course is well organized and I've learnt quite a lot related math knowledge. The only thing I felt need to improve is that the assignment was too easy and I can easily pass even though I didn't fully understand all the concept and details. Hope we can make it hard and more opportunities for the learner to make mistake and correct in order to learn more.

Thanks

Martin

Good coverage of the practical aspects of Neural networks. Happy to be introduced to the latest research on the topic. Not the course's fault but there seems to be reuse of the same variable names in different papers. Wish the course introduced some consistency.

The introduction to TensorFlow was useful. However, wish there was more coverage / exercises for this topic.

Andrew Ng's courses are a real delight - he's a natural teacher that explains well and can get students excited about a subject. In this class there were some problems with the last exercise (the TensorFlow tutorial) - it was too simple and yet cryptic, with some unaddressed errors and a lot of loose ends (thus only 4 stars - all his other classes are definitely 5)

Only detail is that programming exercises are way too simple, copy-paste kind of things. I could understand that being the case for the first, introductory course, but it would've been nice to have a little bit more of a challenge to get used to the programming implementation details. Also, it is outdated in the sense that you are using version 1 of TensorFlow.

This course subsumes relevant contents in Stanford Machine Learning Course. Some useful addition to the Stanford Course are briefs on Gradient Descent With Momentum, RMSdrop and Adam as well as elementary practices on Tensorflow. People with basic knowledge of linear algebra can complete this course in a day (i.e. 10 hours) by skipping less important videos.

The final lab is somewhat confusing in that the TensorFlow syntax is poorly explained and the results for the final module would be well served by noting what your first epoch should be as well as the 100th (I spent a long time trying to find non-existant bugs because I had misread the output of my model as epoch 100!!).

Other than that excellent as ever.

This course provide very deep and good knowledge that how to increase speed of your neural network and how we do hyperparameter tunning. But one thing lags in this course is that it won't provide much knowledge about frameworks like Tensorflow and people face difficulty while doing programming exersice because tensorflow knowledge is not provide in depth

I wish more of TensorFlow had been included in the course content. Aside of that major point, I wish the complex mathematical portions had been explained with more precision and codes like "X[0][0]" had been explained with more precision as well. But overall, I think it was hugely worth learning all the thoroughly taught concepts and I am very grateful.

Topics are explained very well. There may be a false sense of accomplishment coming after doing the assignments, which are pretty straightforward. I am going to add in personal tasks which might help me understand the topics more in depth. On a similar front, could you add in a video explaining what to do next. And I don't mean the next course in line.

gain quite a lot of insight into the deep neural network, the tunning, regularization and so on.

one remark on this course, we talked a lot about tunning processes in wk3. However, not much practical exercises on this part, e.g. we didn't try to implement the batch normalization ourselves and to incorporate batch normalization with other parameters etc.

Although I loved this course, I believe there are certain parts that could be broken down into even simpler intuitions. If such a change a possible, this course will be the best one out there. Anyway, I really enjoyed the course and it was a great learning experience. Tensorflow was introduced very finely and it aroused my curiousity to learn more.

Really informative course to learn about the various kinds of optimizations and the differences between the optimization techniques. Learnt how to tune the hyper parameters for effective training . Also got a chance to learn about mini-batches and the corresponding gradient descent and the difference between batch and mini-batch gradient descent.

Un curso muy bueno, el instructor tiene dominio del tema y sobre todo el final del curso es muy bueno en cuestión de poner en practica la teoría que al principio te explica. En ocasiones el instructor va un poco rápido en los términos teóricos y puede llegar a abrumarte. Creo quería ideal poner más ejemplos prácticos cada que explica un concepto.

Materials are good and Professor Andrew presents the course in the really understandable level, so I still learn a lot throughout the course even if I have taken similar mooc courses on other platforms. Programming Assignments are much easier than the fourth course (Convolutional NN), but it gives many inspiration to me. Great thanks to the team!

Great material, very clear and pleasant teaching, good software environment for the programming exercises. The exercises are a bit boring at times (cut and paste without much thinking) but maybe this is a quick way to memorize the material...

Some long known problems in the exercises should REALLY REALLY be addressed! (would have given 5 stars)

Great course! The labs were very useful in seeing the concepts applied in practice. Something that I think would help all the concepts and practice take hold even more would be a second lab session per week with much less guidance, where the student is required to come up with most of the algorithm themselves. Overall great and solid course!

Content is great! A good introduction to a lot of hyper-parameters in neural net. However, there are some bugs in the evaluation system of programming assignments. For example, the system does not recognize Pythons '-=' operation and gave me a fail, which I did not figure out until I saw the forum where people were having the same trouble.

Much better than the first course. Math is still quite shallow (simple and not going into too much detail), and programming assignments are still mostly one-liners with copy&paste. But the general techniques demonstrated throughout the course are very helpful, and the given intuition about why and how something works helps understanding.