Very rich with information on various ways Neural Network training can benefit from optimizations. I'm sure there are many more optimizations to explore, and this serves as a great introduction to some of the more common ones.

The optimization algorithms and the the introduction to tensorflow were the topics I liked the most. Although hyperparameter tuning is important, this seems to me to be still very empirical. Also, more interviews would be nice.

In this course, Professor Ng shares great guidelines on tuning deep learning hyperparameters, which are a lot compared to other machine learning algorithms. This will surely help any deep learning projects to be more effective.

This course is talking about how to improve your model using many optimization algorithms + techniques to ensure that your model learns correctly with avoiding overfitting and underfitting. For me, this course learns me a lot.

The material is definitely not easy and may require a certain amount of self-study for mastery. But the lectures as well as the Discourse resources are more than sufficient to provide any additional resources needed, however.

Good course to teach you more about how to optimise your neural network, to speed up training, dealing with overfitting etc. This course assumes you know the basics i.e. done the first part of the Deep Learning Specialization.

Got many ideas on how to increase the accuracy of the model. Introduction to tensorflow was much essential instead of programming all the stuff from the scratch. Now I am much more encouraged to learn more about tensorflow : )

Excelente material, muy pertinente todos los temas del curso. Hay un error en la forma de calificar el examen de la segunda semana.

Por mejorar: Ojalá los cursos dieran las diapositivas que usa Andrew Ng para dictar las clases.

Adjusting parameters are highly essential skills for deep learning programming that most of my friends lacking. Great lectures and assignments around the topic, many thanks to the lecturer and assistants for their great works.

The course will make all concepts about improving deep neural network understand in excellent manner by Andrew Ng.Must complete the course on deeplearning.ai.Mathematical concepts along with applciaitons are clearly explained.

This course is an absolute necessary for anyone who wants an in-depth knowledge of optimising their deep learning solutions. Loved the course work and I could easily relate the course contents with the practical aspects of AI.

This course provides a detailed description on parameter tuning and also deep mathematical aspects behind it. This is a must-take course to understand how neural network parameters operate inside and the way to optimize them.

This course helps me a lot to learn about tuning hyper parameters of deep learning, efficient optimize for gradient descent. Personelly, I love the idea of momentum for gradient descent.

Thanks for giving intro to TensorFlow.

Excellent follow up to the first course. Lectures and lessons are well matched to reinforce the material. A few minor errors in the programming assignments that have been pointed out in the forums that need to be corrected.

Really great course by Andrew. I am marking all of them as 5 stars. But these are not fake reviews. These are really great. As I have mentioned in other comments. I really like the style of Andrew of writing while explaining.

Learnt a lot about the different of the Hyper-Parameters & the different kinds of Optimization algorithms. Was really beautifully explained & made intuitive to understand. Loved to have an introduction to Tensor-Flow as well.

A little less technical than the first machine learning course for the Deep Learning Specialization, but very valuable nonetheless, don't hesitate to try! It truly is a good course and Professor Andrew Ng is a great teacher!

The content is generally great and well worth it. Perhaps the only frustrating aspect is navigating to the Jupyter notebooks. I wish the links to the notebooks were on the same pages as the Submission and Discussion links.

Again Andrew Ng did a fantastic job explaining complex problems in a simple terms which make the course fun to follow. The quiz and the practice exams also help better understand the problem and the concept behind the video.

Very helpful course that sheds light on the inherent parameters of popular 'black box' DL libraries. After passing the course you will be able to understand and variate the majority of those small but important coefficients.

Very helpful! This course helps me step into the details of deep neural networks in practice, and teaches me how to fix those issues, as well as Tensorflow which is a popular deep learning programming framework using Python.

Great course, sometimes you might get lost but its understandable due to the complexity of the topics, but doing the programming assignments helped me to solve my questions

Thanks to the mentors, discussion forums and Andrew

this course was much easier for me to follow, i am really grasping the core coding. really enjoy this course and the others from deeplearning.ai

but the notebook crashed again... but luckily only one line of code was lost.

It was a really good course, like the first one. The only problem is that we got the idea of hyper parameters. We haven't still figured out how to automatically set values of all hyper parameters. That was a bit sad for me.

Thanks a lot, Andrew. Now I know Batch Norm and Adam very well. With the TensorFlow assignment, I can say I have enough basic knowledge to gain more. The practice assignment was very well organized to gain TensorFlow basics