Chevron Left
Back to Convolutional Neural Networks

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

4.9
stars
42,318 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

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.

AG

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.

Filter by:

976 - 1000 of 5,613 Reviews for Convolutional Neural Networks

By Nishit K

Nov 20, 2019

I am deep learning practitioner and use CNNs very much for my work, but material here was very interesting and refreshing! Of course Andrew is awesome.

By Jiali H

Jun 18, 2019

the assignments have some bugs that sometime I could not find the "submit" button. Also, the links of "Hints" sometimes didn't direct to the right one.

By Chen S

Mar 18, 2018

Useful algorithms. The overviewing teaching style is quite useful in the sense that some of the ways of construction CNNs for specific use is provided.

By Sreejith S

Dec 3, 2017

Great Course Anderw and team. Planning to try out a face recognition use case in office before the next course on sequence models start :)

Thanks again

By Tuan D V

Jul 20, 2021

This course is definitely tougher than the first three courses. Challenging but worth it.Content is great, but videos could be trimmed to cut retakes.

By Saravanan S

Dec 28, 2020

Very Good Course. Best place for those who are new to deep learning and want to explore CNN and to get insights on both theory and practical knowledge

By Warren P

Jun 13, 2020

Great labs and course content. Overlaying image content with a style was thoroughly enjoyable. Like all of the courses, it is well-constructed. Bravo!

By AMIT P

Jun 9, 2020

I did few projects based on object detection and face recognition, but after completing this course only I get a better understanding of these topics.

By tahir i

May 12, 2020

its is one of the best course on coursera to learn neural network i have learn a lot i hope this will help me in my professional carrier and other too

By Michael D

Mar 12, 2018

what can I say, this is another fantastic course. Andrew Ng does such a fantastic job of simplifying yet not trivializing some pretty complex topics.

By Gitesh K

Mar 7, 2018

The in the specialization. Although if there could also be a tutorial on how to input or create your own dataset of images, it would be of great help.

By Per T H

Mar 3, 2018

Excellent course, thought in a very pedagogical way by Andrew Ng. You can really save a lot of time with a good Professor on these difficult subjects.

By 熊子量

Mar 11, 2020

Courses content is as inviting as the first three courses. It's a good way to provide the essaies' link for those who want to dig deeper in research.

By Fahad T

Nov 26, 2019

Good course to get started with Convolutional neural networks. Learned a lot of network architecture. My personal favorite part was Object detection.

By Haider k

Nov 9, 2019

Great course with lots of state of the art practical projects. Professor Andrew Ng can explain complicated topics with simple/intuitive explanations.

By Subhadeep D

May 14, 2019

An excellent course which made me familiar with the state-of -art techniques in Computer Vision. Highly recommend it for Computer Vision enthusiasts.

By Leonardo A S M

Jan 6, 2018

Great class, lots of practical tips & skills learned. Just wish the programming assignments were a bit more challenging (as in starting from scratch)

By helen d

Nov 13, 2024

Andrew is a great instructor! The course syllabus and the labs did really help me get much deeper understanding of the algorithms. Thank you! Andrew

By Christopher A

Oct 19, 2023

I enjoyed the course. Taking it at my pace and gaining understanding or how various neural network architectures work and the intuition behind them.

By snigdha m

Mar 12, 2021

It was nice learning various aspects of CONV networks. Also, the programming assignments was helpful for nice learning in terms of practical concept

By Kamyar A

Feb 21, 2021

This specialization, especially this course helped me build my network for my bachelor's thesis from scratch! Thanks Andrew! Thanks Deeplearning.ai!

By Santanu G

Jun 9, 2020

Excellent course to gain clear conception on all basic things related to convolutional Neural Network and to use the same in practical applications.

By Khanh N

Feb 7, 2020

Computer Vision has always been of great interest to me and this course lit up my way of approaching closely to become a ML engineer as of my dream.

By madhumita.behera@gmail.com

Dec 12, 2019

I had a wonderful time working on this course. Even though i had worked a lot on CNNs this course was still useful in understanding the fundamental.

By Vivek G

Dec 3, 2019

this was harder than previous ones, but it was required. The Neural Style Transfer in the last week was not explained well but it was okay. Thankyou