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
63,295 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:

6726 - 6750 of 7,270 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Marco v d L

•

Nov 4, 2017

Video's: 5 star

Practice: 3 star (it will test your copy and past skills mostly)

By Han T L

•

Mar 20, 2021

A bit less structured than the 1st course, but still excellent! Learned a lot!

By Biral K P

•

Aug 17, 2020

A great course overall. Implementation in TensorFlow 2.0 would have been nice.

By Andrew P

•

Oct 28, 2019

Wonderful course, would have liked another assignment working with TensorFlow.

By bayu a n

•

May 4, 2019

Need more in-depth about parameter tuning, but it's a very good course overall

By Mohit k

•

Jun 22, 2018

Thanks for such amazing course. Add little bit more on Tensorflow fundamentals

By Lucas O S

•

Dec 11, 2017

Great course, still some issues in quizzes and autograder, and lack of support

By Vladislav Z

•

Oct 8, 2017

Course it good, but IMHO to simple.

BTW I do not have real experience with NN.

By Haim K

•

May 30, 2020

It would be beneficial to give more details on how tensorflow optimizers work

By Ankur D W

•

May 9, 2020

This is an important course to go through for improving deep neural networks.

By Luis d l O

•

Jan 15, 2020

Very nice one. Focus on practical aspects that are quite necessary to use NNs

By Hossein M A

•

Sep 9, 2019

too complicated, many lessens in couple of short videos.

poor video transcript

By Arturo V

•

May 29, 2019

Se podría mejorar mucho la redacción del libro del ejercicio de programación.

By Alexander

•

Nov 21, 2018

more python / tensorflow, as well as data exploration and cleaning is welcome

By Jiri L

•

Jan 3, 2021

Very good. The only downside is the reliance on an old version of Tensorflow

By Damien C

•

Sep 8, 2017

Excellent on the basis. could cite frameworks like hyperopt, hyperas, etc...

By Luigi C

•

Aug 29, 2017

There are still some minor typos to correct, but it's a great course anyway!

By Ashim M

•

Oct 5, 2020

Builds really well. Didn't know about gradient checking before this course!

By IDRIS S

•

Jul 4, 2020

activity at the end used tensorflow 1, support for tf2 would be appreciated

By Samuel E

•

May 27, 2020

Programming assignments can be made more rigorous with more hands-on coding

By Tukaram P

•

May 27, 2020

everything is good, jypyter notebooks are slow gets confused in assignments

By Pranaydeep C

•

Apr 21, 2020

I really liked it because it made me specially under stable with Tensorflow

By Fredrik C

•

Jul 18, 2019

Great, but could be better. Fix the typos. Add summarized video notes. Etc.

By Ahteshaam S

•

Feb 16, 2022

The Last assignment on Tensorflow can be improved and explained in detail.

By Győző T

•

Feb 18, 2021

The Tensorflow part was hard. Pleas add more explaination to the notebook.