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:

6476 - 6500 of 7,253 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Shreya A

•

Feb 16, 2021

It might help the academic learners if tutorials can be more engaging and rigorous than they are at present. But hey, not bad at all! :)

By Mohamed M

•

Jul 14, 2020

It's really great Mr/Andrew has a good way of explaining stuff even tho i need to search some stuff on youtube for greater understanding

By 2445_Nupur S

•

May 19, 2020

I loved the course, as it provided concise explanations and covered all important topics required in Deep Learning. Thank you Andrew Ng!

By Sidharth W

•

Oct 19, 2018

Would have been 5 star but I found typos in the assignments and exercises -which have still not been corrected which is quite surprising

By Styvens B

•

Aug 26, 2021

Good course overall . The batch normalization explanation were not so convincing. The last assignment on Tensor Flow need improvement.

By HARSHUL G I 2 - B

•

Aug 13, 2021

The course is nice but the tensorflow exercise has a lot of functions that weren't explained before and implementing them was difficult

By Varunraju V

•

Aug 24, 2020

Its good hands-on course but to master it will certainly requires to dwell more into the specifics and need to work on various projects

By Samarth B

•

Sep 11, 2017

Was a great course. Learnt conceptually and implemented Momentum,ADAM & rmsprop. Wish there were more exercises to explore TensorFlow .

By Benjamin J

•

Oct 29, 2017

I would have liked more programming exercises related to regularization and hyperparameter tuning, but TensorFlow was well introduced.

By ISHAN P

•

Jun 30, 2021

Weeks 1 and 2 were awesome. However I think we ned a more intensive programing assignment on Week 3 to get hands on with Tensor Flow.

By Paulo M

•

Aug 26, 2020

I liked the course. I just think there should be more assignments. Perhaps after each week because the content is dense and complex.

By Vighnesh N G

•

Apr 21, 2020

Too much spoon feeding in the programming exercises, could have asked us to make a model with atleast x accuracy then left us alone.

By Mahesh S P

•

Apr 17, 2020

This was the toughest course since lot of mathematical, especially statistics back ground is required. However, I could complete it.

By S S

•

Aug 18, 2022

The course includes lots of information and need focus and concentration.

The Tensorflow part is not enough to solve the assignment.

By Sri K

•

Apr 10, 2020

Its require basic python programming for implementation of neural networks , different models techniques to get perspective of it .

By Ahmed N

•

Mar 24, 2018

One of my best courses i have ever participated in, i gained a lot of knowledge and knew the underlying mathematics of every model.

By Mathieu J

•

Feb 24, 2018

Second step of the specialization,

a bit less rewarding than the fist course as more fine tuning and less overview of deep learning

By Mohammed M

•

Oct 18, 2017

Programming assignments could have been more challenging. Otherwise, the course instructor is pretty awesome!! Thank you Andrew Ng.

By Swann C

•

Oct 6, 2017

Good material and definitely essential in order to gain a lot of time aiming at the right direction navigating all these parameters

By Amine D

•

Nov 22, 2019

Very good course. I would have liked a little longer introduction to the tensorflow architecture and less help on the assignements

By Curt D

•

Sep 5, 2018

A good introduction to gradient descent algorithms and hyperparameter tuning with a little TensorFlow thrown in for good measure!

By Jorge C

•

Sep 22, 2017

Good course, Hyperparameter tuning, Regularization and Optimization are well explained, and the Tensor Flow lab is very useful too

By Marcela I

•

Jan 18, 2021

Es un buen curso, basado principalmente en aspectos prácticos. Me pareció menos interesante que otros de la misma especialización

By Xin J X

•

Sep 19, 2017

Tips are very useful! Have some typos/errors in assignments, more coding work can help understanding. Thanks for sharing, Andrew!

By JUI-CHIEH, W

•

Aug 26, 2017

Many practical tricks such as tuning hyper parameters and the use of major optimization techniques such as batchnorm and dropout.