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

4.9
stars
62,825 ratings

About the Course

In the second course of the Deep Learning Specialization, you will open the deep learning black box to understand the processes that drive performance and generate good results systematically. By the end, you will learn the best practices to train and develop test sets and analyze bias/variance for building deep learning applications; be able to use standard neural network techniques such as initialization, L2 and dropout regularization, hyperparameter tuning, batch normalization, and gradient checking; implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence; and implement a neural network in TensorFlow. The Deep Learning Specialization is our foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology. It provides a pathway for you to gain the knowledge and skills to apply machine learning to your work, level up your technical career, and take the definitive step in the world of AI....

Top reviews

XG

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.

JS

Apr 4, 2021

Fantastic course and although it guides you through the course (and may feel less challenging to some) it provides all the building blocks for you to latter apply them to your own interesting project.

Filter by:

6226 - 6250 of 7,216 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By P.C. C

•

Feb 27, 2021

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.

By Tristan C

•

Apr 4, 2020

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.

By daniele r

•

Jul 15, 2019

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

By Anwesh J

•

Jul 18, 2020

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.

By Charles S

•

Nov 24, 2017

This course was excellent, however the Tensor flow at the end feels a little bit like the ML field is quickly being overtaken by the frameworks, and the Tensor flow section is a little bit tacked onto this course, maybe in a hurry.

By Ashok T

•

Dec 31, 2019

Interesting practical suggestions regarding hyperparameter tuning and batch normalization, it could be more mathematical with more programming assignments with the effects of tuning. The TF framework was kind of surprise in Week 3

By il K

•

Mar 9, 2018

As always, great course from Andrew: easy to be understood, useful trainings and exercices. The lecture are explained slowly and repeating the important concept, always a good think.

Thanks! I will proceed with my Specialization :)

By Federico A

•

May 29, 2020

The content of the course is excelent and the practice exercises very interesting and helpful. I feel there is missing a written resume of the concepts after each video, or a hand-in of the powerpoint presentations would be nice.

By Shahar M

•

Apr 10, 2020

Pros: The course covers the basics for hyperparameters, tunning, regularization and optimization. The basics that it covers are well presented and explained.

Cons: A much more detailed and intense work with TensorFlow is needed.

By Paramjit S

•

Apr 13, 2019

The course is really good and the explanation by Dr Ng is exhaustive. But I think the assignments were meant for beginner level. You will not be implementing any function instead you be writing the underlying formulas. That' it.

By Hamza M K

•

Jun 26, 2018

This is another great introduction to Depp learning frameworks apart from all the neural network performance upgrading techniques taught. This is an excellent course for building a strong foundation of deep learning fundamentals

By Zahid S

•

Mar 16, 2019

This course was mostly well-designed especially for the first topics, but in my view, the Tensorflow part needs to be extended. It provided a brief understanding of the topics, but I do believe deeper examples might be helpful.

By Joris

•

Feb 10, 2018

better than the first course since it involved breaking into new stuff w.r.t the Stanford Machine Learning course.. However, altogether not yet challenging enough to give 5 stars

Really interested to go deeper into this matter..

By Dr. H H W

•

Aug 8, 2019

Interesting material but a bit complex to follow all the equation derivation. Need to repeatedly watching the video to understand the content. After learning this the hyper parameter setting in the ML setup is clearer to me.

By Jean-Simon B

•

May 8, 2018

I would like to have harder programming assignment, perhaps optional. Because instead of understanding the problem I just had to read the question again, answer were always in questions, then copy paste and change "x" by "X"

By Tom T

•

Dec 4, 2019

Overall, it's pretty good. I did have a problem understanding some of the facts being communicated about gamma and beta in batch norm. Also, I think there is a problem with the last notebook. My cost did not go down as fast.

By Teddy G

•

Nov 17, 2019

I think the last subject, the "gradient checking" looks a bit not connected to the begining of the week 2 course, it may be only me, so I will go over it again and try to understand its relevancy to the rest of week 2.

Teddy

By Tim H

•

Nov 12, 2017

Good choice of topics to cover. I think the central idea of some of the videos could have been summarized much more quickly, in a minute or two, with the rest of the time spent going into more depth if the student needs it.

By Mukesh K

•

Aug 19, 2019

The content of the Course is very precise and assignment truly reflect what is been taught in the lectures. Explanation and presentation of algorithms are what I like the most. Assignment were very engaging and interesting.

By jie y

•

Mar 10, 2018

The class should include more introduction on the current ml frameworks such as tensor flow etc. Possibly it should include one more project for the ml framework. Hope to give students more experience on the ml frameworks.

By Deva C R M

•

Nov 19, 2017

Good and detailed information on how to tune parameters, optimization techniques and regularization. I'm confident that this course learning will help me in training NN to better convergence in a shorter time than earlier.

By Karl S

•

Jan 2, 2019

I would have liked more details on the math. Furthermore, I think that the discussion of TensorFlow was a bit too short. Although I was able to do the assignment I have not yet developed an understanding of TensorFlow.

By Julien B

•

Jun 27, 2018

Excellent. Mon regret est que l'exercice final ne mette pas en oeuvre le tuning des hyperparamètres sur un jeu de cross validation. Un exercice supplémentaire avec TensorFlow ou Keras sur cette notion aurait été un plus.

By wilfried l

•

Apr 11, 2020

Very Interesting

As usual, it is very good from theory point of view. Practical examples are also really interesting.

Do not expect to be autonomous after the course, as you won't be able to use Tensorflow or Keras alone.

By Gil F

•

Nov 3, 2019

I'd make the tesnsorflow section a separate week with much more elaboration, the first time (in both course 1 and course 2) I felt a subject was lacking information. It's mostly noticeable in the programming assignment.