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
63,296 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

AS

Apr 19, 2020

Very good course to give you deep insight about how to enhance your algorithm and neural network and improve its accuracy. Also teaches you Tensorflow. Highly recommend especially after the 1st course

XG

Oct 31, 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:

3376 - 3400 of 7,270 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Deepak S

•

Mar 30, 2020

This course has valuable content! Well satisfied. :)

By Bao N

•

Mar 26, 2020

Thank you so much for preparing such a good content!

By Francesco

•

Mar 24, 2020

The part on optimization algorithms is really great!

By ARCHIT J

•

Mar 18, 2020

This course will help to optimize your model quickly

By Albert H M

•

Oct 25, 2019

Very deep material and clear explanation. Thumbs up!

By Rushabh A D

•

Sep 15, 2019

The last assignment is the Best Intro to Tensorflow!

By José A

•

Jul 17, 2019

I love these courses. I recommend them to anyone! :)

By Yelan T

•

Jul 17, 2019

This course is amazing! I will recommend my friends!

By Suraj J

•

Jan 1, 2019

Andrew Ng. That's all that needs to be said. Thanks.

By Thibault R

•

Dec 15, 2018

Thanks you very much, this is really a great course!

By Arnavesh .

•

Oct 14, 2018

Great intuitions and explanations by Prof. Andrew Ng

By Thomas S

•

Sep 2, 2018

Great for gaining deeper understanding on the topic!

By Javier M M

•

May 25, 2018

Worth the time if you're interested in deep learning

By Juan D B

•

May 7, 2018

Muy útil para entender cómo tunnear una red neuronal

By 王子铭

•

Mar 30, 2018

the tensorflow programming exercise is very helpful!

By Rahul G

•

Mar 14, 2018

Speechless. The best specialization I have had ever.

By Soumya B

•

Mar 5, 2018

A great high level overview of the methods involved.

By Benjamin C - 陈

•

Jan 30, 2018

very thorough discussion of tuning and optimization!

By John Y

•

Jan 18, 2018

Andrew Ng is one of the best teachers I've ever had!

By Wenzhi

•

Dec 21, 2017

Wonderful course! Thank you very much, Prof. Andrew.

By Pamin R

•

Nov 10, 2017

Provide a well intuition of the optimization methods

By Ekaterina T

•

Nov 9, 2017

Very good for people with some background in Python!

By Michael M

•

Oct 29, 2017

Explanation of basic principals beyond excellent !!!

By Andres R

•

Oct 25, 2017

Very interesting topics to extend NN from course one

By Pedro

•

Sep 28, 2017

Very practical approach to improve learning results.