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:

6076 - 6100 of 7,216 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Samuel C

•

Oct 12, 2018

Great course, although I felt that introducing TensorFlow in week 3 was quite ambitious. I think it would have been better to have an additional week, during which we could have just learnt about TensorFlow. I found the third week challenge difficult, because I didn't know why we were using some of the functions, and it took me a while to figure it out - and I'm still not certain why what I did worked

By Farzeen H

•

Mar 25, 2018

I would love to give 5 stars but I have reduced one because of the typos in the assignments. I 'managed' to waste my time to check my code many times as my answer was not matching the expected output. Later I figured out that there was an error in the expected output.

As a course, it gives a thorough understanding of playing around with hyperparameters and fine tuning the NN to get better accuracy.

By Jerry H

•

Nov 27, 2017

As usual, the course material, videos and programming assignments were excellent. However, as I am currently not utilizing large datasets, the material on Batch Normalization and Hyper-parameter tuning is not useful to me ( now and in the foreseeable future). The introduction to TensorFlow and the tutorial was very useful, and has certainly whetted my appetite.

Look forward to the next course.

By Kamran K

•

Apr 11, 2021

Very good lecturer, but there have to be some ready-made slides also for those who can not take notes during lecture, because my self taking notes also, and can not carrying both listening to lecture and taking notes.

Please Andrew Ng sir!

Make some slides, with a few details for studying whenever facing problems and clearing doubts in the future. please sir

Thank You

Sincerely yours

Kamran Khan

By Ashwani S

•

May 6, 2020

Mentors don;t seem to collaborate, its been 3 days i posted a question in discussion forums but no reply has been received yet. It was a terrible experience. If you got stuck at a problem then only way is to get help from other students because mentors don't give a shit, about your course. I have given a rating of 4.0 only for the teacher Andrew Ng Sir. His teaching style is very impressive.

By Tim C

•

Jan 22, 2018

Good course that covers a lot of practical topics that are rarely given much consideration in an academic setting. Be careful in week 3 as there are a couple of mistakes that someone who has gotten to this point should catch, but it is possible that they will slip by. Overall though, another great class from deeplearning.ai where I learned a huge amount that has a very practical application.

By Anton D

•

Oct 24, 2017

The course content was of very high quality. There were just some issues in the notebooks that are already covered in the forums. I think it's worth fixing them. In the videos there are also some small mistakes made but nothing serious. Also, about the programming assignment, I think it would be useful to have some in which less of the code is readily written and more is left to the student.

By Varad P

•

Apr 6, 2020

As usual this course was really good, but at some parts I had a feeling that Professor Andrew Ng was a bit vague in explaining some concepts. So, I had to spend a lot of time on thinking about it (which I feel could have been avoided). It will really help if the instructors are able to provide additional references regarding the hyperparameters and the other topics discussed in this course.

By Ryan M

•

Oct 29, 2020

This course did a good job of covering much of the material. I felt like the explanations of most of the concepts in the videos were good. The last programming assignment, on TensorFlow, felt like a lot of guesswork for me. The basic ideas of TensorFlow were not really covered well in the lectures. Other than this assignment, I thought the programming assignments were generally helpful

By Frankie P

•

Jul 17, 2023

A very good, in-depth course. Only small complaint is some of the slight nuance in the final programming exercise, where some details (i.e. the from_logits parameter) being a little bit unclear. Personally, a bit more clarity on how to use that function specified, and the fact that the inputs required transposing should be highlighted more clearly. Other than that though, brilliant!!

By Mahnaz A K

•

May 30, 2019

The best thing that I get from these courses is to learn about intuitions all the time. Although I really enjoyed that part on optimization and parameter tuning , the same standard wasn't kept in TF part. What is tf graph? why do we need it? why session? .... Unfortunately the tf docs fail on explaining these concepts as well. If I don't get answer to those questions here, then where?

By Race V

•

Nov 26, 2017

I am slow on the uptake on the maths side of the equation, while the repetition of the class lectures is most appreciated. No, it is not repetitive, Andrew keeps expanding on our prior knowledge for each week.

Even with 30 plus years since I did Calculus I am able to follow and understand thanks to the team.

Though, they do need help with correcting some minor mistakes in the webpages.

By KISHOR

•

Mar 29, 2020

i learnt a lot about tuning Neural Networks through various optimization and regularization methods in this course. this helped me a lot in understanding the working and derivatives of optimizing neural networks through various algorithms. this course is making the foundations of deep learning look easy and understandable than other sources to the person who is taking up this course.

By Pierre C

•

Dec 13, 2022

I appreciated the whole course, particularly when Andrew NG explains step by step a new topic (for instance Adam algo).

This course has a very good level.

However I wish some general functions from SkLearn of Tf... were presented to go from from-scratch functions written in this course (essential to understand the pedagogy) to generally used ones (in particular by ML-DL engineers).

By Guillermo

•

Jul 15, 2020

Well structured course. It shows a great overview on hyperparameter tuning.

It would be great if the lecturer could keep the voice tone as he speaks, especially in long explanations where you can feel how his voice tone is going lower and lower, and then suddenly on the next video cut it goes back to normal exploding you ears ( as you had to increase the volume of your speakers)

By Roy W

•

Sep 13, 2019

Great course on hyperparameter tuning. Some of the code projects used the same variable names repeatedly in different contexts, which, to me, at least, is a bad practice to encourage in students. Also, in the Tensorflow project, some additional numerical calculations would have made it easier to catch issue earlier. But Andrew Ng was amazing, as always - clear and informative.

By João P B D

•

Sep 23, 2020

Excellent content provided by a world-class expert in the field whose didactics is on point. Great selection of applications. Not much mathematical formality and programming assignments not really challenging as an assessment tool. It's definitely the theory one might need to amass upon the first course's content, however what was previously easy enough is now even more so.

By Martin P

•

Dec 23, 2017

The course is well organized and I've learnt quite a lot related math knowledge. The only thing I felt need to improve is that the assignment was too easy and I can easily pass even though I didn't fully understand all the concept and details. Hope we can make it hard and more opportunities for the learner to make mistake and correct in order to learn more.

Thanks

Martin

By Supriya S

•

Sep 27, 2017

Good coverage of the practical aspects of Neural networks. Happy to be introduced to the latest research on the topic. Not the course's fault but there seems to be reuse of the same variable names in different papers. Wish the course introduced some consistency.

The introduction to TensorFlow was useful. However, wish there was more coverage / exercises for this topic.

By Ido S

•

Nov 26, 2017

Andrew Ng's courses are a real delight - he's a natural teacher that explains well and can get students excited about a subject. In this class there were some problems with the last exercise (the TensorFlow tutorial) - it was too simple and yet cryptic, with some unaddressed errors and a lot of loose ends (thus only 4 stars - all his other classes are definitely 5)

By Sebastián J C

•

Sep 15, 2020

Only detail is that programming exercises are way too simple, copy-paste kind of things. I could understand that being the case for the first, introductory course, but it would've been nice to have a little bit more of a challenge to get used to the programming implementation details. Also, it is outdated in the sense that you are using version 1 of TensorFlow.

By Shuai X

•

Dec 15, 2017

This course subsumes relevant contents in Stanford Machine Learning Course. Some useful addition to the Stanford Course are briefs on Gradient Descent With Momentum, RMSdrop and Adam as well as elementary practices on Tensorflow. People with basic knowledge of linear algebra can complete this course in a day (i.e. 10 hours) by skipping less important videos.

By Crawford F

•

Dec 7, 2020

The final lab is somewhat confusing in that the TensorFlow syntax is poorly explained and the results for the final module would be well served by noting what your first epoch should be as well as the 100th (I spent a long time trying to find non-existant bugs because I had misread the output of my model as epoch 100!!).

Other than that excellent as ever.

By Satyam k

•

Aug 18, 2020

This course provide very deep and good knowledge that how to increase speed of your neural network and how we do hyperparameter tunning. But one thing lags in this course is that it won't provide much knowledge about frameworks like Tensorflow and people face difficulty while doing programming exersice because tensorflow knowledge is not provide in depth

By Vishak A

•

May 14, 2020

I wish more of TensorFlow had been included in the course content. Aside of that major point, I wish the complex mathematical portions had been explained with more precision and codes like "X[0][0]" had been explained with more precision as well. But overall, I think it was hugely worth learning all the thoroughly taught concepts and I am very grateful.