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
63,175 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

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

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.

Filter by:

6376 - 6400 of 7,253 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Jag S S

•

Mar 26, 2020

Tensorflow Version used in last assignment is old and syntax has been changed in tensorflow 2.0, it should be updated. But Overall very knowledgeable and insightful course.

By Nguyen X M

•

Sep 6, 2017

The course help me to understand more clearly the optimizers as well as the process of

pyperparameter tuning. I think the assignments should be a little bit more challenging.

By Mike W

•

Feb 16, 2024

An excellent course, Andrew Ng is an interesting and knowledgable instructor. Better course summary materials are all that is missing, as they are mostly copies of slides.

By Sergey N

•

Mar 30, 2021

Very nice course, but the exercises should be more complicated and longer.

How come the last week exercise does not deal with any regularization or hyperparameter training?

By Christopher B

•

May 13, 2020

Kind of short, well explained, good assignments. The tensorflow video is for version 1 of tensorflow, so I was unable to follow along with it. Other than that, good course.

By Kurt B

•

Dec 31, 2017

the course is focused on the main elements - it's a lot of material to work through - it would also be good to elaborate a project (could be an own one) during the course

By Jerome B

•

Dec 11, 2017

This course made a lot more sense to me, compared to the first one. Still a bit excessive on calculus in my opinion, but I guess calculus makes more sense for other people.

By Anson W

•

Sep 25, 2020

It's comprehensive, even covering tensorflow. More details on tensorflow are suggested. Also the theory are more abstract and not quite well explained as previous courses.

By Anish A

•

Jul 19, 2020

Week 2 was very informative, Prof Andrew discusses the concepts behind gradient descent and momentum in detail. The programming exercises could have been more challenging.

By Jek D

•

May 23, 2020

The videos were great! Personally I was lacking some additional reading material and more quizzes. Other than that, the course demystified different optimization technics.

By Nagaraju K S V

•

Oct 24, 2021

Very informative and explained very well. This course increased my enthusiasm and interest in ML further more. Looking forward to learn more about DL in the next courses.

By Roelof v W

•

Jul 5, 2020

A very good course. The current course content related to Tensorflow syntax detail (week 3) can be improved. Future coursework should probably use the latest framework/s.

By KUMAR M

•

Feb 9, 2020

A great course to learn how to make our deep learning models better. The flow of the course is superb. The only thing I felt can be improved was the level of assignments.

By Minha H

•

Jan 1, 2020

Good coverage of practical issues in hyper-parameter tuning, regularization, and optimization of algorithms. Would be better if it covers TensorFlow 2.0 (instead of 1.0).

By Bahadir K

•

Aug 23, 2017

couple of problems in notebook files (especially in the last homework) wasted my time, but it was a great course and to understand the math behind and learning tensorflow

By Harshit s

•

Aug 28, 2020

Some of the Topics like tensorflow should be have some more explaination but even though the course is excellent and as far as for Andrew Ng ,he is best among the bests.

By Nazmus S

•

Apr 2, 2019

Learning a lot. But full of boiler plate codes. It would be great if students were challenged with programming. Writing a formula even in code is easy for most students.

By 2451-19-737-007 N N R

•

Feb 5, 2021

The content is good but I didn't feel comfortable with tensorflow assignment. That could be improved by stressing more on tensorflow syntax and explaining it in detail.

By Alfonso L R

•

Jan 7, 2018

I would like to have a brief introduction to Tensor Flow or a simple beginners tutorial (at least to have it clearer the usage of variables, constants and placeholders)

By Sai s

•

Jun 24, 2020

As always, the explanations are very clear. I would've just preferred if the newer versions of TensorFlow with the eager execution was included in the course syllabus.

By Naren G S

•

Jun 10, 2020

Was tough understanding the concept, but google and maintaining notes really helps this class. All the concepts required understanding the concept exist in the course.

By Sajal C

•

Mar 12, 2020

Gives good information on how to tune your parameters so that the neural network gives awesome results. Really important course for beginners as well as intermediates.

By Ayush S

•

May 26, 2020

This is a very necessary and informative course after knowing the basics of neural networks.

As this course covers all details to speed up the neural network learning.

By Ivan P

•

May 9, 2021

Enjoyed the course information and assignments in the first two weeks, but the last week's assignment needs improvement as it is not well correlated with the videos.

By Ashish K

•

Mar 11, 2020

Very well articulated course and brings out the concepts very well. I wish there was a bit of more guidance to sudden introduction of tensor flow, especially syntax.