Chevron Left
Back to Convolutional Neural Networks

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

4.9
stars
42,029 ratings

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

AV

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

OA

Sep 3, 2020

Great course. Easy to understand and with very synthetized information on the most relevant topics, even though some videos repeat information due to wrong edition, everything is still understandable.

Filter by:

4501 - 4525 of 5,570 Reviews for Convolutional Neural Networks

By Saravanakumaar J

•

Dec 9, 2017

Course is good. Much thanks for Angrew Ng, to explaining CNN in simpler way. However, the practical assignments are not properly configured to load. In Week2 & Week4 the practical assignments did not load properly. Hence it took longer time for me.

Also, couple functions' expected output and my implementation output did not match however, I got the full score. This again misleads us.

By Michael B

•

Aug 4, 2018

The lectures are what you would expect from Andrew Ng. Excellent.

Some of the assignments make unreasonable jumps in expectations regarding understanding of TensorFlow and Keras operations. An overview of exactly what is being used would be helpful as some of it is very nonintuitive.

Additionally, some of the assignments have known grading issues. Be sure to check the discussions.

By Muhammad Y

•

Oct 9, 2018

Overall the course is solid and covers many important topics ranging in complexity from simple to advanced and state of the art (NST). However, Videos are sometimes not properly edited. There is repetition of dialogue. Also, I think practice questions can be made a bit more challenging. I also noticed that in this course there aren't any explanations for right or wrong answers.

By Daniel Z

•

Aug 14, 2018

Excellent lecture content.

Some of the programming assignments are quite poor. Sometimes there are minor mistakes in function descriptions, and other times the whole assignment architecture/plan is not well thought out. If the staff doesn't have resources to improve this, then allow the community to create branches and submit merge requests :)

Overall, I'm happy with this course.

By Peter S

•

Aug 8, 2020

The Course is more than great, learning about using ConvNets in different problems and applications was very interesting and useful. The only drawback is that the code in assignments is built on TensorFlow 1.x which is outdated and even some links to TensorFlow or Keras documentations are note working, I'm sure this code will get upgraded soon. Thanks Andrew and all the staff.

By Devansh B

•

May 12, 2019

Andrew NG explains CNN fundamentals really well in this course. I liked the use-case based teaching. Also, the assignments were at par with the lectures. I faced a couple of issues in Face recognition assignment of Week 4. The team should look into that. Looking at Discussion forums helped me in moving past those issues. A big shout out to people actively participating there.

By gaurav s

•

Apr 24, 2020

Learned a lot. Theoretically, course is must-to-do, most of the code is done so please do not expect that you'll be a king in Tensorflow and CNN. However, you will be able to implement things in real-time and yes coding you can learn anytime at your own pace. Also, the projects that were implemented in the exercises are not something that can be done alone (at least for me).

By Joshua H

•

Jun 29, 2020

Initial introduction of convolutional neural networks was very thorough, with week one even addressing back propagation along convolutional neural networks via the programming exercise. Later weeks showed interesting ways in which the theory of convolutional neural networks has been applied, although some independent research has to be to supplement learning in the course.

By Luisa F A S

•

Aug 23, 2022

Downsides are some edition errors in videos (like not taking out parts where Andrew repeats same phrases) and erros on quizzes' gradings (marking as wrong a correctly answered question and giving something like "answered out of alloted time" when everything was submitted within the time limit). But other than that, this is a great introductory course to computer vision.

By Jack B

•

Dec 4, 2017

Good course with very relevant and practical content. Since it was the first time this course was offered, a few bugs in the assignments notebooks. While you don't need to be a guru in vector algebra to complete this course, I would appreciate a little more focus on the rationale for using 'Axis = True', for example or 'Keep Dims = ???. thanks for a great course.

By Peggy F C

•

Aug 17, 2018

This course really tied all of the previous ones together, giving the student a more holistic understanding of deep learning and neural networks. However, the instructions for these assignments were the least clear of all the assignments so far and often, trying to decipher what the steps were asking for deterred from the otherwise incredibly helpful experience.

By Johan W

•

Nov 15, 2017

A lot of nice information and specific examples of recent state of the art networks for various applications. Some of the programming assignments were great, using both Keras and Tensorflow! A few of the assignments were a bit unrelated, i.e. required implementing mostly a couple of trivial functions not particularly related to machine learning or deep learning.

By Roni M

•

Apr 22, 2020

The material was interesting and very clear (like previous courses in this specialisation)

However I believe using Keras and TF here without sufficient background created some frustration till I was able to gradually understand the concepts there. The lectures (and theoretical background) were very clear, but the programming assignments were a little too simple.

By Nityesh A

•

Feb 6, 2018

Excellent content!

The programming exercises are expertly designed. They have very meticulously designed them order to help students, who are a little less familiar with programming, complete functions that do complicated tasks.

The videos could use some editing because *a lot* of the stuff that's in them is repetitive because of Mr. Ng correcting his statements.

By Bhavesh K

•

Jun 28, 2020

This is great course for convolution neural networks . i really learnt a lot but the only thing which resist me to give five stars is i wanted to learn a more accurate face recognition system and to also be able to build an object detection model for my own projects through transfer learning i mean this should have been taught in the programming assignments.

By Andres J

•

Jun 24, 2018

Content was very good. You will get a good understanding about convolutional networks. Also good place to learn some basics of tensorflow and a little more about Keras. Some minuses: Home assignments where easy and you could do them without thinking much. Main frustration was due to having to reopen jupiter because it died very often. Hope they will fix this

By Mohammed A E

•

Jul 21, 2021

The Course is exceptional in every detail in it. Andrew as usual explained the concepts in an intuitive way that sticks to the brain. The one thing that can be better is the part where R-CNN, Fast R-CNN, and Faster R-CNN were explained they did not get much attention and I feel like I have not grasped the idea behind them as the other parts of the course.

By Luis A A

•

Oct 22, 2020

Excellent program with very valuable information regarding convolutional networks and intuitive exercises. I encourage the staff to update the tasks with the latest Tensorflow versions. Having the codes with Tensorflow 1. At least I would appreciate a clear information of how to migrate the codes from Tensorflow 1 to 2 (or whatever the latest version is).

By Edwin G

•

Jan 15, 2018

There are some issues with the scoring of the programming assignments (I lost hours on the iou function and eventually realised I had to submit an incorrect formulation to pass, and the same thing happened on the triplet_loss function.) Other than these issues, which seem minor (and are) but cost me so much time and effort I would have given 5 out of 5.

By Stephen S

•

Dec 16, 2017

The course as such is excellent, but quality of material is not on that level. In the videos Andrew is sometimes repeating himself (final cut of video is missing). Programming assignment for Face Recognition has two bugs, weights can only be loaded with a hack from forum thread and expected output of triplet_loss is not matching grader expected results.

By Robert P

•

Apr 16, 2018

The content is generally great and well worth it. I wish they would fix some of the errors, especially in ungraded exercises. You end up wasting a lot of time because of them. Perhaps the most frustrating aspect is navigating to the Jupyter notebooks. I wish the links to the notebooks were on the same pages as the Submission and Discussion links.

By K Y

•

Apr 15, 2021

It is a nice course but one bad thing in this course is the programming exercise, sometime it is not very clear or there are some places that function has changed but the function mentioned is the old version and another suggestion is i hope there are more vids on the syntax on tensorflow, one vid in course 2 is not enough to handle the assignment.

By Ahmad A

•

Jan 13, 2018

I liked the course and the topics were discussed and learned. I gain much more algorithms and tools for various ML topics.

However, I am still missing the tools to start a problem from scratch - i.e. gathering data, arranging the data, building the proper data/structure for the algorithm. In the course, all the time, we get a well cooked datasets...

By Matt G

•

Jun 28, 2022

This was a great course: challenging and insightful. I liked the way in which TensorFlow was connected to published networks/papers. I did, however, feel that there was a significant change in effort required--compared to the earlier courses in the specialization. The increased effort was mostly due to the additional reading from the literature.