Great course. It goes over many practical method to speed up the training process and also does an excellent job at explaining why these algorithm work. The programming assignment notebooks were also nice and helps to reinforce and understand the theory.

Recommend! The parts of batch norm and epoch in mini-batch solved my confusions. And the exercise of Tensorflow is simplify and useful. Without tedious documents, you can easily contruct a neural network for practical problems following the instructions.

Yet another great course from Prof. Andrew Ng and Coursera. Deeply grateful to all involved in the preparation of this course. Absolutely essential to learn these concepts if we want to build and optimize deep neural networks for creating great products!

The conciseness of the course material and interviews with industry experts offer thorough insight and can inspire confidence in new and old DNN learners alike. I look forward to learning more in the remaining courses of the Deep Learning Specialization!

I benefit a lot from this course regarding parameter initialization, hyperparameter optimization, batch normalization, optimization, etc. All the knowledge are well explained both intuitively and mathematically. Always enjoyable to learn from Andrew Ng.

As expected from deeplearning.ai and Sir Andrew Ng, this course was really great!

Choosing between so many hyper-parameters and tuning them can be a confusing task, but this course explains each one in detail and simply.

Thank you for this amazing course!

Not long ago I have been working with machine learning and artificial networks, but without a doubt so far I think my learning curve has been exponential. Themed content is for anyone to fall in love with technology and climb on the shoulders of giants.

I understood the bits and pieces of how tuning particular hyperparameters will lead to a great improvement model being developed. Andrew NG was great to teach everything with examples and deep dive into the concepts. Thanks for the opportunity provided.

Great course on practical techniques to tune hyper parameters. Great to see the practical experience driven lectures with succinct, focussed theory. Learning has never been so exciting. Kudos for the team who put together such as great code scaffolding.

Andrew Ng picks up where he left off with 'Machine Learning' and takes a relatively complicated subject and breaks it down into clear an understandable blocks, providing insight and intuition along the way. But that's what great teachers do well, right?

I'm on the road to improvement with my deep learning skills with the current specialization.

Thank you for providing such a great quality course online.

I also appreciate the mentors who comment to every post in discussion group.

Keep up the good work!

Very wonderful and thought provoking stuff has been provided for learning optimization and regularization. Latest stuff have been used to demonstrate the examples. Thanks to Coursera for providing a good platform to learn all this tools and techniques.

This is a fabulous course for hyperparameter tuning, regularization, normalization, optimization, and other tensorflow framework commands. I have gained immense knowledge from this course. My deep regards to Andrew Ng et. al. for such a worthy course.

This course is good for those who want to learnt about the different regularization technique and the most important optimizer algorithms. The course material is good and easy to understand. I liked this course so much and it teach me lots of things.

Great course by Prof Ng. I had taken his Machine Learning course a few years ago, so expected high standards of content and assignment preparation - I was not disappointed. Staff is very responsive and helpful in forums as well. I highly recommend it.

In-depth learning about Hyper-parameter Tuning, multiple Regularization and Optimization Techniques. This Course makes learning Deep Learning Framework like Tensorflow very easy.

All thanks to Andrew NG and team for building this course so interactive.

Hyperparameters can affect our parameters and how tuning them properly would speed up our optimization is nicely taught. And it was great to know the intuition and mathematics behind other optimization algorithmswhich which was also taught very well.

It's been a great learning through out this course. Even by improving hyperparameters, tuning them and optimizing them, we can increase the efficiency and reduce the execution time very much.

Thank you so much Andrew Ng sir for this amazing course!!!

This course is very useful, a good extension of the first deep learning course. Like the name of the course, on top of the basic neural networks knowledge, this course focus on how to improve the performance of the fundamental neural networks built.

In the course there are lots of impressed optimization strategies that are hard to get outside from here. I was shocked when I saw the performance improvement after I run He initialization and Adam, according to the instruction in the course. Great!

I'm very happy can finish this course. After taking this course, I understand how to optimize deep learning model, how to tuning hyperparameters. Also, by doing the programming assignment I can understand how to do optimization process from scratch

THE COURSE TAUGHT ME DIFFERENCE BETWEEN RMS ,MOMENTUM AND ADAM OPTIMISER.WHY BATCH NORMALISATION IS IMPORTANT.HOW REGULARISSATION AND DROPOUT IS USEFUL.GRADIENT DESCENT AND MINI BATCH DESCENT AND WHY IT SHOULD BE BETWEEN 1 AND NUMBER OF M(SAMPLES).

This course was a great introduction to more advanced topics of deep learning. I was primarily interested in the second week of this course, where different optimization techniques like momentum and optimization algorithms like ADAM were discussed.

Had some issues with the last tensorflow assignment, since these are guided exercises wasn't able to debug my code properly (cost function was giving me a lower value, documentation didn't help me debug it either, will be looking into it further )

Great knowledge on how to optimize hyperparameters and example code is always appreciated. I appreciated the knowledge on effectively using sklearns hyperparameter search methods and knowledge on how to use tensorflow to create my own gpu methods.