This course taught me a lot of new concepts and tricks to speed up the training process as well as ways to reduce overfitting and biasing in a neural network. I would've liked the course even more if the instructors took a deeper dive in frameworks.

I learned a lot in this course but I feel like the assignments should be little big and less informative. The assignments are designed are good for then who are at base level but too short for someone who had their hands on once in neural networks.

One again the course is a great follow up from the previous one. The only little detail I wish had been done was for the assignment to cover a scenario where we had to improve some hyperparameters by applying different approaches covered in class.

The course itself is great, but something out of the course is not so good, e.g. I can't see the video easily in China, and also the pictures in the exam can't be shown always, so I must take some guess to pass the exams, which is really a regret!

Not like the first course which was kind of "trying not to touch the details", this course is more organized and I felt I've learned something. Still I would improve TF training to get more into the details (what does reset global variables do?!)

Interesting, but the quality of the exercises in not so good. There are at least 3-4 mistakes in the expected output that make you loose time double verifying. Mentor only seems to reply it is know, sounding like it has been like this for long...

It mixes a review of Neural Network tuning techniques, and brief intro to TensorFlow. Those are really two very different topics, but I guess it's just designed to fill about a month of the specialization.

NOT recommended as a standalone course!

This well-structured course guides you in understanding the importance of tuning hyperparameters as well as some regularization basics. I would give it 5 stars but for coding with Tensorflow < 2.0, what is really outdated in my honest opinion.

This is a very good course, but the content of the hyperparameter adjustment mostly stays in the theoretical analysis. The latter experimental course does not involve how to implement the program. I hope that it will be improved in the future.

Great course. I learnt a lot again. Perhaps the programming exercises can be a little harder. Some things were quite literally spelled out which meant that you could theoretically copy/paste them into your code with only trivial adjustments.

I liked the optimization lectures, and Andrew's style of teaching. Anyway, I feel that I didn't learn enough in this course, and that it is not on the same level of previous courses we got used to, like the original Machine Learning course.

A good introduction to the important details that go into training a neural network and why they are important. I appreciate how they explain it all from first principles, but I'm going to need to do some more courses to learn tensorflow.

This course was better than the first course in the specialization. The assignments were more sophisticated (though repetitive at times) and required more thought and work. The only down side is the monotone way of presenting the material.

Some lectures seem to have inconsistent/unexplained differences in the math written. For example, I am a bit confused as to whether normalization is done as (x - mean)/variance or (x - mean)/std.dev. Otherwise, excellent content as always!

In some other courses there was a pdf document at the end of the courses which very good if you want revisit them but in these courses its not available. Please make them available here which will be a very time saving for quick revisions

In overall, the course content is helpful and inspiring as normal, and can be used to real life straight away. However there are several typos/mistakes in the assignment, especially in assignment 3 which I had bad time to experience with.

The best course in deep learning: Hyperparameter tuning, regularization and Optimization. The course is best among all the available courses over internet but it lacks availability of study materials (or reference to reading materials).

Very good content. Professor Ng covers a lot of material in a gentle and steady way. A few errors in the assignment and less clarity on some texts and quiz make me give 4 stars, but overall it's a very useful, important course, I think.

Great course for in-dept understanding of parameter tuning and optimization, +tensorflow. I would recommend increasing the complexity of the programming assignments. At this point we should be controlling more of the basic python setup.

Maybe not as exciting as the first course of this series (Neural Networks and Deep Learning) as this one delves more in the "technicalities" of NN. The presentation of the topics, however, is always very clear and easily understandable.

Struggled a bit to grasp the batch nomalization, Initially Regularization was also hard to grasp the first time, subsequent viewing made it clear though but batch norm still is a bit hazy. I am happy though we are in to Tensorflow now.

The material was excellent for this class and so were the lectures. I think more programming assignments could have been optimal though. There are so many concepts, and I think there are several pieces we didn't implement in practice.

There were still a few times where I felt some clever editing could have hidden math errors but I felt the second part was already more polished and accessible than the first. I hope the rest of the series continues in this direction.

One of the best and most technical course in this Specialization: I enjoyed learning a lot on optimization algorithms. Really good practical hints on tuning and on bias variance analysis, that are very difficult to find in textbooks

Indeed this is an awesome course for any beginners in deep learning.One suggestion could be is why you have selected Tensorflow framework.Will it be possible to get same assignment in Pytorch framework which out institiute follows.