Chevron Left
Back to Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

Learner Reviews & Feedback for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization by DeepLearning.AI

56,647 ratings
6,498 reviews

About the Course

This course will teach you the "magic" of getting deep learning to work well. Rather than the deep learning process being a black box, you will understand what drives performance, and be able to more systematically get good results. You will also learn TensorFlow. After 3 weeks, you will: - Understand industry best-practices for building deep learning applications. - Be able to effectively use the common neural network "tricks", including initialization, L2 and dropout regularization, Batch normalization, gradient checking, - Be able to implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence. - Understand new best-practices for the deep learning era of how to set up train/dev/test sets and analyze bias/variance - Be able to implement a neural network in TensorFlow. This is the second course of the Deep Learning Specialization....

Top reviews

Oct 30, 2017

Thank you Andrew!! I know start to use Tensorflow, however, this tool is not well for a research goal. Maybe, pytorch could be considered in the future!! And let us know how to use pytorch in Windows.

Jan 13, 2020

After completion of this course I know which values to look at if my ML model is not performing up to the task. It is a detailed but not too complicated course to understand the parameters used by ML.

Filter by:

376 - 400 of 6,427 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Neil S

Jun 17, 2019

Wonderful course that teaches one the intricacies of training better models. It's also great when learning to implement a neural network through Tensor Flow for the last assignment and realizing that you have a good understanding of whats going on "under the hood".

By Andrey M

Apr 9, 2020

This course is very thorough and detailed. Now I can clearly and confidently say that I can perform good research and obtain formal information and data on any topic, as opposed to just surfing the internet for genuine knowledge. Great course, well done to Andrew.

By Michael S

Aug 4, 2018

Overall, this is an excellent course, although it is not perfect. Trying to understand what is wrong when full credit is not earned for quizzes or programming assignments is sometimes "challenging". It would sometimes be useful to have more informative feedback.

By Ertu S

May 18, 2018

Great course., excellent well to the point, Only nuisance I observed is during submitting coding assingments required multiple tries since at first time, all the code somehow does not go thru. So needed to save and restart notebook and cut& pasted again. Thank you

By Белоусов А Ю

Sep 23, 2017

Great course. I really like it as it get more and more practical.

Few things might be missing from the class - it might be worth to encourage students play with algorithms a bit more. Say get back to the previous stage and add regularization to get better results.

By Christos Z

Apr 30, 2018

Grate course, only criticism is that week 3 didn't thoroughly explain how batch normalization parameters (gamma and beta) get updated during gradient descent. (i.e. how to get dgamma and dbeta). It could have been an optional lecture for the mathematically savvy)

By Siddhant A

Sep 23, 2020

One of the most comprehensive course for people who want to learn the logic, implementation and conceptual understanding for deep learning. Programming exercises are a great starting point for learning implementation and they are perfectly made for the learners.

By Abdelrahman A

May 19, 2019

it is wonderful course i learned more in Deep learning and how to apply regularization

and how to optimize cost function also programming in Tensor flow

i thanks all teaching assistant for there efforts to learn us

and i recommend this course to DL beginners

By manish m

Apr 28, 2018

I recommend everyone to go through this course if you really want to learn detail about hyperparameter tuning , optimizers and regularization used to make neural network better. It helps to open black box of Neural network and know in detail about how all works.

By Lee

Sep 5, 2017

Some very useful insights into practical implementation and optimization of neural networks, and a very welcome introduction to TensorFlow. After coding networks in numpy you both appreciate the framework, as well as understand what it's doing behind the scenes.

By Sebastian E G

Aug 18, 2017

Again, fantastic. Great way to explain how to tune your algorithms to improve bias and variance. Great explanation of what optimizers are used and how they function. Glad to know the nuts and bolts of the parameters usually defined in machine learning frameworks

By Harsh B

Nov 6, 2017

This course is a must for understanding hyperparameters and their tuning and choosing the best ones for your model. Prof. Andrew explains everything very simply and precisely. This course is intended for intermediate users who have knowledge with Deep networks.

By Aman D

Sep 8, 2017

I think the most important course of the 1st 3. It tells about all the different optimizations and practical aspects of training a deep neural network. I would keep referring to its content in the future too. Thank you team for creating such a wonderful course.

By kunal s

Aug 14, 2017

This was one the best course as it has made me capable to increase the efficiency of a project as it has taught me various techniques of selection of data size ratios, tunning hyper-parameters speeding gradient checking using different techniques and many more.

By Beltus W N

Jun 1, 2020

The gentle transition from NumPy based implemented deep learning functions to the Google's TensorFlow framework is so smooth and easy to comprehend. My understanding of the concepts has been solidified by the course. Thank you Andrew Ng and the Coursera team.

By Tú A N

Oct 28, 2017

Extremely useful course . I highly recommend it . This course give me some helpful tips to tune hyperparameters , some optimization techniques that never heard before . The intro to Tensorflow in third weed is great . Assignment also proves to be insightful .

By Ka W P N

Apr 7, 2019

The course materials are well-designed. However, I have to say this is not an easy course as I spent a lot of efforts in order to understand how to do the assignments. Overall, I strongly believe the course has taught me what I need to know about this topic!

By Joshua D

May 18, 2020

This was an interesting and challenging course. Andrew gives good intuitions about the fundamentals of improving deep neural networks. I recommend having separate optional sections explaining the math behind some of the concepts for those who are interested

By Jude N R

Nov 2, 2017

This course brought to light a lot of the more intricate topics in deep learning. Compared to my knowledge before the course, I now feel like I have a sound understanding of all the small nuts and bolts that work in a deep learning system. Loved the course.

By Nazmus S E

Apr 18, 2020

This is one of the best courses on Coursera. Cleared a lot of concepts. Before this course, I was always thinking, what to do if I had to classify among multiple classes, but the explanation of softmax was actually very helpful in answering that question.


May 25, 2019

This was a very interesting and different course from others. I found it very helpful

for improving the NNs and the techniques taught with assignments give a well insight so as to how the problem should be dealt with.

Thank you to teachers and to Coursera.

By Vivek V

Nov 6, 2017

A perfect course on Deep learning. Mathematical analysis well put forward by Andrew. I am looking forward to finish Deep Learning specialization. I would appreciate if he provides reference to textbooks to learn more about the fundamentals.

Thank you,


By Jiani S

Jan 4, 2020

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.

By Satyam D

Dec 12, 2018

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!

By Kyle L

Dec 23, 2017

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!