Chevron Left
Back to Convolutional Neural Networks

Learner Reviews & Feedback for Convolutional Neural Networks by DeepLearning.AI

40,450 ratings
5,359 reviews

About the Course

In the fourth course of the Deep Learning Specialization, you will understand how computer vision has evolved and become familiar with its exciting applications such as autonomous driving, face recognition, reading radiology images, and more. By the end, you will be able to build a convolutional neural network, including recent variations such as residual networks; apply convolutional networks to visual detection and recognition tasks; and use neural style transfer to generate art and apply these algorithms to a variety of image, video, and other 2D or 3D data. 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


Jan 12, 2019

Great course for kickoff into the world of CNN's. Gives a nice overview of existing architectures and certain applications of CNN's as well as giving some solid background in how they work internally.


Jul 11, 2020

I really enjoyed this course, it would be awesome to see al least one training example using GPU (maybe in Google Colab since not everyone owns one) so we could train the deepest networks from scratch

Filter by:

5276 - 5300 of 5,334 Reviews for Convolutional Neural Networks

By Daryl V D

Jun 19, 2018

TOO MANY BUGS IN THE EXERCISES.It was a dis-incentive. Really.And I love me some! It has been great. The videos and content structure are fantastic.

By Arsh P

Dec 15, 2018

Though the videos were very good but the assignments require too much from us and also there are few mistakes in week 3 and 4 notebooks which take a lot of time.

By Yongseon L

Jun 15, 2019

By mike v

Jun 8, 2019

The content is excellent, but there were technical problems with the final homework assignment that were not addressed by staff in a timely manner.

By Sébastien C

Aug 18, 2020

Content was interestind and provided good theoretical overview. Exercices where you just have to fill in some line of codes are not usefull.

By Joshua S

Nov 29, 2019

Some of the code was incorrect and the guidance was often confusing. Visibly worse than the other courses in the specialization,

By Kristoffer M

Nov 30, 2019

Don't feel like I understand these models much better than before. Still don't see the logic of the identity layers

By Prasenjit D

Dec 6, 2017

Lots of problem with the grader. Wasted a lot of time grappling with grader issues. Very disappointed.

By Sandeep K C

Dec 28, 2018

The quality of some of the graders e.g. IOU is poor. One cannot make out what exactly is it checking

By I M

Oct 17, 2019

Disappointed by the quality of notebooks, which often disconnect and lose all the code you wrote.

By Shuhe W

Jun 8, 2019

The course assignment parts have many errors, I have to fix it myself. That's silly.

By Bernard F

Dec 13, 2017

Good content, but quite a bit of technical work is needed to present this better.

By Ryan B

Jan 2, 2020

for goodness sake "your didn't pass the test" isn't feedback for notebook grades

By Coral M R

Jun 7, 2019

Dificultades en la hoja de tareas de Face Recognition que deberían solucionar

By Jason K

Dec 13, 2017

The content was good, as usual, but week 4's quiz was pretty buggy.

By Mike B

May 7, 2018

Good course but lots of technical issues with the assignments.

By Kishan

Feb 13, 2018

The notebooks were too simple. And the grader was not working.

By Stéphane P

Mar 30, 2019

Videos are good, but exercises are really confusing

By chao z

Feb 22, 2018

content good, but assignment is in poor quality

By hossein

Jul 19, 2020

The structure of the assignments is not good

By Ankur S

Dec 30, 2019

Programming exercises have bugs

By borja v

Aug 22, 2019

unclear content...I'm sorry

By Alex A K

Sep 28, 2019

Numerous technical issues

By Christopher H

Feb 24, 2022

C​ustomer service informed me that once a user completes a course, they're not permitted to access the assignments for reference again. This is a huge drawback to this platform, as that's where the real lessons are and essentially prevents a paying customer from being able to reference their own work. This is esspecially dissapointing given that I would have followed the instructions to download the Jupyter notebooks while in the class had I know about this bizzarre policy.

By Mostafa A

Dec 16, 2017

Assignement: Face recognition for happy house was not happy at all

it took me 4 attempts to pass.

triplet_loss function you need to submit incorrect answer to pass. to get correct answer you need to have axis=-1. Bu to pass you have to take it out.

I hope you guys fix to stop more people to waste there time.

Not happy at all.