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
62,825 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

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.

JS

Apr 4, 2021

Fantastic course and although it guides you through the course (and may feel less challenging to some) it provides all the building blocks for you to latter apply them to your own interesting project.

Filter by:

6801 - 6825 of 7,216 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By thiên t

Jan 1, 2021

I can't use tensorflow v1 on my computer and Google Colab

By Karthi C

Jun 26, 2018

Became hard core technical but that's what it mean to be.

By ภาณุเทพ ท

Jun 26, 2018

So far so good, but why no batch norm in last assignment.

By Luis M A P

Apr 4, 2018

As the 1st course, really easy to follow and interesting!

By Evaristo C

Sep 17, 2017

Something that you won't see in many other MOOCs, worthy!

By Rafael M

Aug 31, 2017

Very good.

Would be better it it touches tools like keras.

By 方嘉浩

Jun 7, 2022

improve my understand about Deep Neural Networks to work

By hatem a a

Sep 13, 2021

Very goog course,but the code section need more explain

By Nilange o s

Jul 3, 2020

Good course , 'll get to know more about hyperparameters

By Le K H P

Dec 20, 2017

A bit short on the Tensorflow tutorial, otherwise great.

By Tauhiduzzaman K H

Jul 5, 2020

Installation of tensor flow might have make it complete

By Siwei Y

Nov 20, 2017

极高水准的教学,然课程略短。 编程作业依然过于保姆化 ,简直就是直接喂到嘴边。这样反而起不到加深印象的效果 。

By Quoc V T

Nov 11, 2017

Great course for Hyperparameter tuning and Optimization

By Mark M

Sep 15, 2017

Enjoyed the content and the introduction to Tensorflow.

By yuichi k

Jul 1, 2020

内容は素晴らしいが、日本語訳がついている動画が少なく苦労した。英語が苦手でDLを何も知らない人は少し大変かも

By Lior R

Dec 28, 2019

The course was great but I think it needs more quizzes

By Aleksandar O

May 13, 2018

Useful but rather dry iteration of the specialization.

By Tianxiang Z

Nov 21, 2017

Great as usual except the typos in the assignment page

By yashwanth v

Jun 3, 2020

more introduction to tensorflow would be appreciated.

By Clement K

May 7, 2020

Very disapointed the course does not use tensorflow 2

By Thomas P

Mar 31, 2020

Some more basics on tensorflow would have been great!

By Alexander S

Mar 25, 2020

Very good overall, exercises could be a bit more free

By Ritesh R A

Dec 17, 2019

tensorflow sesssion should have been more descriptive

By Mihaly K

Nov 6, 2019

Assignments sometimes too easy, minimal input needed.

By Brent D

Feb 25, 2019

Tensorflow project was rushed and hard to understand.