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:

1251 - 1275 of 7,253 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Eduardo M O

•

Oct 8, 2017

Amazing intuitions and insights how to tune and understand "hyperparameters world". Thanks again Andrew Ng and Coursera for this amazing journey!

By Rami K

•

Aug 23, 2017

Excellent course, would have loved to learn more about Thiano in addition to TensoreFlow, but overall very happy with the content of this course.

By jyotikrishna B

•

Sep 17, 2021

really impressed by the way of teaching by Andrew sir, and got to know how to optimize the the neural network and improve its accuracy and speed

By shawn s

•

Jan 25, 2021

it's a great course to deep learn the machine learning, it will clearly share how to initialize the parameter. how to quickly coverage the model

By Carlos V M R

•

Aug 31, 2020

Os conteúdos são excelentes, assim como a didática do professor. Perfeito para quem já possui uma experiência na área e quer se aprofundar mais.

By Vidhan G

•

Jul 14, 2020

It was well formed and the instructor had a vast knowledge about the subject , would highly recommend this course to deep learning enthusiasts..

By Shashank D

•

Jul 5, 2020

Whilst the topics were covered with good perspective, as usual by Prof Andrew NG, more sessions on Tensorflow could have made the course better!

By Hari D S A

•

May 13, 2020

FABULOUS!! This course helps build deep neural network with higher accuracy and reduced training time. On top of it you get to learn Tensorflow.

By Federico R

•

May 11, 2020

This is a beautiful course. Andrew is exceptionally good at explaining interesting (but complex) topics in a very intuitive, straightforward way

By Yash A

•

Apr 16, 2020

Really good of learning TensorFlow from basic Linear Function of a small scale Network. Finally got to know the workings of different Optimizers

By Yashveer S

•

Mar 14, 2020

This was an excellent course for learning about hyper-parameter tuning. I really enjoyed this course and look forward to the rest of the courses

By Victor g

•

Oct 23, 2019

Great. Thanks to this course I have gone a bit deeper and understood concepts that I now realize I did not understand them as well as I thought.

By Sonal K

•

Aug 2, 2018

This is really an awesome course. This covers the basics so well and enables to have a clear picture of what is going on. Highly recommended..!!

By roi s

•

Oct 29, 2017

I really like how Andrew Ng is really to the point and really focuses on real world applications. I'm waiting for the other courses to come out.

By Mohankumar S

•

Aug 31, 2017

A Wonderful backdrop on tuning parameters and optimization, culminating with the best fundamental intro ever to TensorFlow. Thanks again Andrew!

By Oshan J

•

May 10, 2021

Great course. The theory videos were very clear and easy to understand. Quizes and programming assignments helped a lot to grasp the knowledge.

By Alexander

•

Feb 20, 2021

It's really helpful for me to get a quick view of neural networks . I have learned how to tune the hyperparameters during the learning process.

By Metin K

•

May 26, 2020

It's perfect to understand what affects a Neural Network performance and how to tune them. Seems short but definitely lots of information here.

By Chandrasekhara S V

•

May 10, 2020

Very good course, Thanks Andrew Ng and team. Mathematical background of each hyper parameter is clearly explained and the assignments are good.

By bhavesh j

•

Dec 27, 2019

I think this course is an important step as we move further in this field since as data and model become larger, optimum performance is a must.

By Mohammad H

•

Dec 12, 2019

I liked a lot that I applied everything from zero-ground. Although it can be implemented much better, but in general, all assignments are great

By Vibhutesh K S

•

Oct 1, 2019

It was really nice to see that Andrew Ng introduces Tensor Flow at the right time. But learning tensor flow's programming syntax was difficult.

By Namkung J

•

Sep 22, 2019

lectures were very easy to follow to new learners for deep learning. especially many practical tips are helpful when analyzing real world data.

By Isabel B

•

Sep 7, 2018

Very well written tests. The assignments are challenging enough to really test your understanding but not so difficult as to be unsatisfactory.

By Ram M

•

Feb 12, 2018

This course is extremely useful since it covers the very recent developments in optimization of deep networks, and best practices to tune them.