Chevron Left
Convolutional Neural Networks に戻る による Convolutional Neural Networks の受講者のレビューおよびフィードバック



This course will teach you how to build convolutional neural networks and apply it to image data. Thanks to deep learning, computer vision is working far better than just two years ago, and this is enabling numerous exciting applications ranging from safe autonomous driving, to accurate face recognition, to automatic reading of radiology images. You will: - Understand how to build a convolutional neural network, including recent variations such as residual networks. - Know how to apply convolutional networks to visual detection and recognition tasks. - Know to use neural style transfer to generate art. - Be able to apply these algorithms to a variety of image, video, and other 2D or 3D data. This is the fourth course of the Deep Learning Specialization....



Jul 12, 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


Jan 13, 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.


Convolutional Neural Networks: 376 - 400 / 4,690 レビュー

by Guillaume G

Nov 15, 2017

I really like how Andrew Ng is able to explain actually pretty complex concepts in a comprehensible way, built on the knowledge of the previous weeks content.

Also great is the integration of recent techniques: inception modules/networks, residual networks.

by Amit A

Dec 27, 2019

Excellent course. Professor Andrew Ng ensured easiness in following the courses, highlighted important aspects and the assignments were very well structured. I am glad to have taken up this course and I hope to start using my learning in the coming months

by Chetan P B

May 08, 2020

Amazing!! The assignments very well cover the concepts taught in video lectures and each part of the convolutional network is explained in detail. The First 2 weeks are quite full of concepts. I enjoyed the last 2 weeks covering the applications of CNNs.

by Daniel J D

Jan 04, 2019

Andrew Ng's courses and Geoffrey Hinton's are about as good as courses get--rigorous, practical, and yet fairly thorough in the underlying theory. Convolution Neural Networks is certainly no exception to that as he goes into res nets and inception nets.

by Yu G

Nov 03, 2017

It's really a great course that I've waited for so long! Thanks a lot for providing the well-organized and easy -understanding materials for those new starters of deep learning like me! Hope to see the last part of sequence models in the nearly future!

by Aniket T

Jul 26, 2020

The course was great you'll get intuition and deep understanding of how convolutional network work.... The material was missing segmentation part and assignment can be moved to tf 2.0... Overall it was great course and the assignments were also great.


Jul 03, 2020

The instructor was great, also the assignments were really a helpful one. I would really appreciate the instructor making CNN such an easy and interesting topic. Even the content of the syllabus was also great and hence I enjoyed the course even more.

by Eric N

Jan 21, 2018

The Neural Style Transfer assignment could benefit from some better descriptions and coding direction, but overall I loved all the assignments and learned a lot. I would like to learn more about Face Recognition and other Image Detection applications.

by Sonny R

Jul 30, 2019

This provide me with a much deeper understanding of CNN and the basic building blocks for building CNN and facial recognition. I really enjoyed the programing exercising and learning how to do leverage additional frameworks like TensorFlow and Keras.

by Jack S

Jul 21, 2019

Great course! I learned so many stuff. Andrew's lectures are very intuitive and helpful. Those Jupyter notebooks are definitely worth time exploring. One last thing is that I wish some limits of the current CNN model can be mentioned for big picture.


May 03, 2019

Another great course in the Deep Learning specialization. It's been a wonderful experience diving into computer vision and discovering some exciting new applications and concepts.

Many thanks to the course team and a special thank you to Dr. Andrew Ng

by Luisa F V C

Aug 05, 2020

In my opinion, this course is the most important and complete of the specialization course. Really, Andrew explains all the concepts necessary to create your own CNN or improving exist CNN. I loved this course. I know will be very useful in my Ph.D.

by Ratchainant T

May 15, 2018

I really learn a lot from this course. However, It would be great if the course introduce how to annotate images and read annotated images to data set in order to get start computer vision project from scratch for audiences who has zero experiences

by Ocin L

Apr 08, 2018

Great course which gives me a basic understanding on the technologies behind object detection, face recognition. Also, the programming assignments are very useful and give me hands on experience on how to build a basic system using the technologies.

by Alexander K

Jan 29, 2020

Sometimes I had to close browser 1-2 times to make Kernel working during the submission of programming assignments. Interrupting or restarting the kernel was not helping. I'm sure it is not related to the course content, but just a technical issue,

by Karan S

Sep 05, 2019

The understanding of Deep Networks for Computer Vision gave me boost to go ahead and use them. I got some awareness about Keras, but I am a bit confused that should I stick with Tensorflow or with Keras. I Loved to work with Tensorflow in Course 2.

by Bogdan G

Mar 12, 2019

Excellent course on CNN which gets you familiar with many popular models from 2012-2016 including all the basic CNN models LeNet, AlexNet, VGG, Inception, ResNet, object localization/detection and YOLO, Face recognition with DeepFace, etc. Thanks!

by Rahul K

Aug 22, 2018

The best course among whole specialisation. One gets to learn a lot about image processing as well as a whole set of reading materials with every programming assignment. Go through the reading materials if you want in depth knowledge of some topic.

by John P

Nov 12, 2017

As always, Andrew Ng manages to make the relatively complex seem simple. The programming assignments are excellent for demonstrating some diverse applications of deep learning and the optional backprop for conv layers was particularly illuminating.

by Bradley W

Dec 20, 2017

Great course that gives insight in CNNs. The coding in frameworks is sometimes confusing and there were some bugs in the face recognition lab, but these are minor compared to the value of the course. Many ideas presented are state of the art.

by Shyam P

May 09, 2020

This is the best course I have ever had on Coursera. The assignments and the lectures are amazing. After completing this course, I got the confidence that I am not far away from becoming a data scientist now. Thankyou Andrew Ng sir and the team

by Stephen M

Jul 20, 2018

This was a really exciting course, presented in a way that was clear and is easy to understand. It is great that it uses such widely used frameworks such as TensorFlow and Keras — which will make the learning quite applicable to the real world.

by Moaraj H

Oct 23, 2018

It was good, but a few broken parts in the assignment almost made me quit. Once fixed it was the normal extremely useful, introduction into very cutting edge stuff. Thanks for putting in the work for this guys, it really is an amazing resource

by Diego A P B

Mar 06, 2018

CNNs are one of the most valuable types of Neural Networks that are being used nowadays, and this course is a great introduction to both the logic and math behind the algorithms. For sure one of the many stepping stones to master this subject!

by GurArpan S D

Dec 07, 2017

I would not consider this course as on par with the prior courses on this specialization. It seemed rushed and there wasn't as much complex thinking we had to do on the assignments. Hopefully, you make it better over time! 5 stars nonetheless!