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
62,800 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

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.

AM

Oct 8, 2019

I really enjoyed this course. Many details are given here that are crucial to gain experience and tips on things that looks easy at first sight but are important for a faster ML project implementation

Filter by:

26 - 50 of 7,215 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Nimish S

Aug 15, 2017

Having done multiple Udacity Nano Degrees and other deep-learning/AI courses on Coursera/edX, I can say that deeplearning specialization is probably the best and most detailed to master the basics of Neural Networks and deep learning. This course is great in helping understand tuning of hyper-params, various optimization techniques and approaches. Videos do a great job in explaining complex and confusing concepts in easy to understand style. Assignments cement the understanding further.

Kudos to the Prof Andres Ng and rest of the deeplearning.ai team for putting up such a great content.

By Vincent F

Jan 23, 2018

This course provided me with an understanding of the large number of hyper parameters that have to be tuned during a deep learning project. It gave me an insight on when different techniques like regularization and (the many different forms of) optimization need to be applied. The only quibble I have is that the material on the choice of the number of layers and the number of hidden units per layer was thin. Given that these values have a great impact on the speed of progress in a deep learning project I would have liked to have seen a little more emphasis on them.

By Aditya B

Jan 12, 2019

The concepts has been explained in a fantastic way. But few suggestions:

-> After every lesson, I would love to have more pop quizes. This was the case with course 1, but I didnot get any pop quizes for this one.

-> In the quiz assignment, it would be nice to have an explanation or justification section, which will explain that why the option selected is a correct one and why the other options are incorrect. I know we can have the same discussion in the forums, but such an explanation ( one liner should be fine) can provide a good instant knowledge boost!

By Mohanad A N

Feb 25, 2019

I'm actually learning and comprehending the course, I do pause the videos occasionally to research some concepts, write some notes in a copybook but overall this specialty(so far course 1 & 2 ) is really filling the gaps in my mind to build a clearer picture of the topic of Machine Learning and Deep Learning. Andrew Ng explains really well, sometimes he through some good recommendations based in his practical experience and this is really valuable for me because it actually helps in improving the learning process.

Thank you Andrew and Coursera Team.

By Yashveer s Y

Jun 2, 2018

This course is perfect bite for your hunger of Deep learning. Before taking this course I have gone through some books and and some blogs too but there was not that much of clarity to topic so finally I tried for this one and trust me this course is so organised and very informatic so go for this one, I assure you will feel more confident and knowledgeable after completing this course. I would like to thanks Coursera as well as deeplearning.ai community for providing this course and Want to specially thanks to Mr. Andrew Ng for his contribution

By Heshmat S

Dec 26, 2017

This is the 2nd course from Andrew Ng in the "deep learning specialization". Having introduced the building blocks of deep neural networks, in this course Andrew teaches more advanced and practical concepts - like: regularization, advanced optimization techniques, batch-normalization, etc - that can significantly improve the implementation of the models we build.

Also, in this course we get to learn TensorFlow, a widely used and wonderful deep learning framework.

I highly recommend this course.

Thank you Andrew & Co. :-)

By Sebastian C

Dec 31, 2018

Great course! But I am not too sure why this should be placed in number 2, as I feel that topics such as tuning hyperparameters do not resonate well with someone who is not working professionally or is not very experienced in this field. However, still a great course as I will revisit this course when I gain more experience. I also like the last exercise on Tensorflow as there is a lack of courses on Tensorflow on the Internet, so the last assignment on Tensorflow is the most useful which I have found in the course.

By Nkululeko N

Apr 12, 2020

Other than anything I've learned a great intuition about everything that Andrew Ng has presented in this course. Some I somewhat still feel like I still need to do some further readings and understanding because some of the concept from the course I still don't understand them. However, with the first course and this course of the deep learning specialization, I feel ready to work as a machine learning expert even if starting from bottom-up. I feel more than ready to finish the whole specialization certificate.

By Svetlana L

Oct 22, 2019

I liked that the course gradually introduces more and more complexity and concepts without making your drown. Even though existing frameworks (e.g. tensorflow) can be used so that most of the complexity is hidden it is still required to understand why one method should be used rather than the other. This course I believe addresses this (as well as first in this specialisation). I still wish there was more information on details but probably all that is needed are external links to extra material.

By Robert K

Nov 17, 2017

Fantastic course! You can experience short, easy to understand lectures, followed by plenty of opportunities to implement covered material, and most importantly create optimized image classifiers - like cats, dogs. I liked how up until the end of the course you had to implement everything from the scratch, not just using read-made frameworks. Finally, you are introduced into frameworks, but this deep understanding stays with you. 5/5 recommendation. Bye, I gotta finish the rest of specialization.

By Ferenc F P

Mar 8, 2018

Good course explaining the concept of hyperparameters vs. parameters, how you can tune the hyperparameters, as well as different regularization techniques. It also provides good explanation for different optimization algorithms (enhancements to stochastic gradient descent). It is a highly recommended course for those who want to understand what is happening under the hood when using a neural network framework, like tensorflow. In the last week a brief introduction to tensorflow is also provided.

By Akanksha D

Dec 31, 2017

The course is great as I expected. It would be helpful if more mathematical background in videos or notes can be attached in each weeks. Moreover, more code could be given to us to write by ourselves to get much better intuition. Rest each of the specializations are awesome as was the first learning Andrew Ng course on Machine Learning. Thank you for providing such courses. This is a great deal for all such students who cannot afford to attend Ivy leagues due to their own reasons.

Great Work!!

By Kévin S

Jul 31, 2018

It explain neural network from the start. After doing all the 5 courses on deeplearning, it is hard to remember normalization formula, and every details. Sometime some hyperparameter look like a little bullshit: You don't know how to do : add one hyperparameter and go for an argmax. But if it is how its work, then it is okay to learn it; Be ready to laugth and do not compare to pure methods like genetics or Bayesian programming that often work good. But every one should follow this course.

By Sriram V

Oct 9, 2019

Insights into best practices and directions for common problems make it an one-of-a-kind material for learners. Andrew, as always, has been commendable with his tutor team, the exercises are well cleaned up and in good shape. May be, if some optional tough exercises are given, it will add more value.

By Artyom K

May 9, 2019

The topics of this course, such as the setting of hyperparameters and the use of tensorflow, are critical topics for me, and in this course they are explained both in lectures and in practical tasks.

By Hugo T K

Jan 16, 2020

Very insightful. it would be nice, however, if the course had more information about Tensorflow 2.0.

By 陈嵘

Dec 5, 2019

体验很棒,喜欢这种有作业有评分的课程

By Tang Y

Apr 15, 2019

very practical.

By David S

Sep 5, 2020

There are both areas needing improvement and places where this course excels.

To begin let's consider what I think needs improvement.

Since this program says that it does not require prerequisites, it really ought to provide backup reference materials specific to course content. Specifically I found it difficult to follow details without the basics of differential calculus, matrix algebra, Python, and TensorFlow. One alternative is to hire a tutor, which is what I did.

Although there is an active community and tutors, support from the course's owner deeplearning.ai can be improved. For example there are comments in the forums about how long it takes deeplearning.ai to fix bugs in the code.

My last suggestion for improvement is how this course is taught. There is so much content that questioning needs to be more frequent. Currently grading is done through ten multiple choice questions and a programming exercise after a week's worth of videos. While the programming exercises are good, learning would be improved significantly by including three or four questions with each video, even if they are not graded.

Overall, I have the sense that deeplearning.ai has not been improving or updating this course.

Nevertheless this course still deserves four stars. The presenter is well organized, articulate and enthusiastic. The entire course follows a coherent plan. This course and its predecessor supplies a great deal of content. Each video runs 6 - 10 minutes on average which is about the right length, However I was always stopping them to write down points to better grasp the content.

As mentioned, there are a few bugs in the programming exercises. However they are rigorous, cover the material, and effort has been made to make them interesting.

Overall, while there is room for improvement this is still a worthwhile course.

By Ignacio H M

Feb 16, 2020

I enrolled in this course without taking the previous ones (I have already done an MSc in Computer Vision and Machine Learning so I thought I wouldn't need the others), but the material has been easy to follow and understand. It is really interesting as it helps you understand important concepts such as bias and variance, or why does batch normalisation work. Sometimes Deep Learning can be seen more as an art than a science, and this course is helpful for defining a good strategy when carrying out deep learing experiments.

By kiran g

Jul 14, 2020

The course began from very basics to complex functions, hyperparameter tuning is efficient in building better models, Kudos to Sir Andrew NG for explaining all of them in the simplest way possible. I would highly recommend this course to all interested in deep learning. But I believe that assignments can be made more challenging rather than just filling up the codes with syntaxes. Logic building is very important.

By Harsh V

Jan 22, 2019

Add more programming assignments to clear fundamentals.

By Juan M R

Apr 3, 2023

It is imposible to do the homeork. The course deserve a note of 0, for that reason.

By Paola d C

Jul 28, 2020

The assignments do not reflect what the learning outcome of the material should be

By KUNJAN M

Jun 12, 2020

Hello. I am Kunjan Mhaske, a graduate student of Computer Science completing (fingers crossed!) the MS degree in December 2020. Currently, I do not have funds to take university courses till August and hopefully, I could secure the co-op or internship for August to December 2020 so that I can fund my remaining semester from it. I am interested in AI and Data Science field and currently, my major is in AI with Computer vision and Machine Learning. I heard very positive reviews about this Specialization course of Deep Learning from my friends and I wanted to complete it this summer so that I could cash this knowledge in my full-time job or internship hunt. Please refer me for any opportunity I am very much in need of financial support for the completion of MS degree as well as living costs. My email is km1556@rit.edu and https://www.linkedin.com/in/kunjan-mhaske is my Linkedin profile. Fortunately, Coursera offered me the financial aid for the first and second courses in this specialization which turns out to be very helpful for me in this situation. I have applied for the rest of the courses in this specialization. Hopefully, I could get financial aid for all the 5 courses. Although I have a 3.76/4.0 GPA, the depth of concepts explained in this course is very good for my level. I have completed this course in 6 days and I am already feeling confident about the field of Deep Learning. Thank you so much for this wonderful course material and your support. God bless you all.