Good review over modeling issues (bias and variance) and excellent course on mini-batches and SGC.

Liked a lot the training parameters section

Most of all - Liked the TF intro.

Looking forward to continue.

Eli

It is good to learn about the things that go under hood of NN programing frameworks; but sad that using the higher level programing, you are going to lose/forget those mechanics unless you are in research.

Very good course. Was able to grasp the concepts very well and now I have a strong understanding of this part of deep learning in optimizing the hyper parameters to create a effective neural network model.

Thanks Andrew and your team for teaching DNN to me. Then I will keep moving forward in AI industry based on your guiding afterward and aggressively build up personal AI research ability after courses.

Gary

Excellent course, helped me a lot.

The only problem I see is that for people with poor background (math/programming) it can be still challenging, because of the amount of information needed to be learned.

step by step teaching the core concepts of parameters tuning. Pretty good! One suggestion might be putting the parameter tuning exercise into coding exercise -- e.g. how a tuning may be like in code level

Good starter-level course, but in my opinion, the third assignment is not so well-designed. It does not even contain the content of the third-week course, for example, BatchNorm and hyperparameter tuning.

I don't have much to say about this course except for hats off to team coursera on the yet another amazing material and delivery. I highly recommend it for any enthusiast beginning their DL study journey.

This is an excellent course on practical aspects of Neural Nets and Machine Learning. As always Prof Andrew Ng is brilliant in elucidating complex concepts and techniques in simple and intuitive language.

Of course, it's a wonderful teaching approach that I would recommend to everyone. The course provides a much deeper understanding of Deep Neural Networks for how to build model that works at its optimum.

Andrew has an exceptional gift of simplifying the math. I finally understood momentum and Adam. Also, my understanding of batch norm improved. Happy with my progress based on the materials in this course.

Excellent course - Andrew's teaching is what's so needed in the machine learning community. He explains concepts properly so that one truly understands them, and thus knows what to do when applying them.

It is an axcellent intro on how to tune hyperparameters of a neural network. The level of details seems to have decreased from the previous course of the specialization, but still is an excellent course.

This course had valuable information about hyperparameter tuning, regularization and optimization. Now I have a better understanding of more advanced criteria to improve my neural network implementation.

very practical thing is learned from this course. Often we developed machine learning algorithm but if algorithm has need some polishing to improve the performance where this course will really helpfull.

I figured out what could I do when the model is overfitting. I learn lots of optimization methods, liked mini-batch gradient descent. RMSprop. momentum. Adam, and I started to learn TensorFlow Framework.

In this course, I learned some of the best practices used to increase accuracy and decrease training time of model. I was also introduced to Tensorflow, and now I can create different projects by myself.

This course simplifies how to improve neural networks. It provides systematic approaches to hyperparameter tuning which is very important and helps the time and effort required in developing good models.

Excellent instruction on the most highly utilized optimization algorithms and how to implement them. Also provides great intuition on hyperparameter tuning essential for tackling complex neural networks.

However important the Neural Network model is, its exactly equal importance to create Parameters that make the NN perfect and usable, this teaches the In and Out of the Parameters selection for NN models

Prof. Ng makes you understand all the hard subjects with ease. I'm starting to believe he's actually a neural network specifically trained for teaching people - Never seen a human teach this good before.

You know what, this guy and his team know the best way how to keep you indulge and make you understand every bit of code you write.

Great course, just needs some upgradations when it comes to TensorFlow.

This course is excellent that helps us know how to implement one deep learning model, how to optimize it, and how to avoid a few issues in coding. I also learned a lot about Tesnsorflow from it. Thanks!

Really good basic theory explanation, I took Udacity Deep learning NanoDegree too, this one actually gives more detail explanation, Udacity is more like a higher level and more advanced project practice

Great course to learn basis of the DNN, Tensorflow, and especially direction of hyperparameter tuning will be very useful knowledge on my job. It will help us escape from maze of parameter optimization.