Chevron Left
Вернуться к Convolutional Neural Networks

Отзывы учащихся о курсе Convolutional Neural Networks от партнера deeplearning.ai

4.9
звезд
Оценки: 28,640
Рецензии: 3,465

О курсе

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....

Лучшие рецензии

RS

Dec 12, 2019

Great Course Overall\n\nOne thing is that some videos are not edited properly so Andrew repeats the same thing, again and again, other than that great and simple explanation of such complicated tasks.

RK

Sep 02, 2019

This is very intensive and wonderful course on CNN. No other course in the MOOC world can be compared to this course's capability of simplifying complex concepts and visualizing them to get intuition.

Фильтр по:

201–225 из 3,421 отзывов о курсе Convolutional Neural Networks

автор: Vidar I

Feb 13, 2018

This course really gets you started working with CNN. The only downside are the "bugs" in the assignments. My advise is to read the discussion forums before you do the assignment to know if there is a bug that you should know of before submitting.

Beside this minor bug, the course content is 5 star.

автор: Damian C

Mar 26, 2018

Really enjoyed learning more about the current state of the art of image recognition models. Although the structure needed can be at times overwhelming, the concepts are clear and implementation via open source packages make it feasible. Many thanks for making this available, keep the good work!

автор: Maciej F

May 08, 2019

Somehow, a bit harder than rest of the courses for me. I had problems with tracking dimensionality and tensorflow notebooks were hard and difficult to debug. I think it would be nice if tensorflow has its own as a course or 2 weeks maybe. But anyway the concepts explanations is great as always!

автор: Juan M E B

Apr 19, 2018

Excelent course. ConvNets are an eye-opening subject and the course explains the main concepts and applications in a simple way, indicating the source papers to understand better. I'd only ask for a couple of videos explaining in more detail backpropagation and the upload of the missing slides.

автор: Andrei N

Sep 21, 2019

The content, examples, assignments, and quizzes are thoroughly developed. All the courses of the specialization share the same notation and lead a student from basic concepts to complex ones helping to develop an intuition on each step. The best course on topic of Deep Learning one could find.

автор: benedikt h

Mar 10, 2018

great ! It is complex though, don't get fooled by the doable exercises - to really understand you can take several loops.

Imagine someone breaks up recent complex research paper into python notebooks for you and you get this delivered like a delicious food - this is how I feel about this class.

автор: Jun W

Dec 16, 2017

This is an excellent course. Although I've got 100%, there are still some details and intuitions need to be figured out. Maybe I will go over it again. And of cause, I'm looking forward for the fifth course. I wish the fifth is not the last course. We still need to know reinforcement learning.

автор: Dr. R M

Nov 07, 2017

Very informative lectures with simple explanations of what the algorithms are doing. The programming assignments are extremely detailed and well explained. This makes it very efficient and fun to learn the concepts of Conv Nets, Res Nets, the YOLO algorithm and so on in a short period of time.

автор: Nour A

Jan 07, 2019

The course explains topics I used to consider as "complicated" in a very clear and simple way. The videos and quizzes about theoretical concepts accompanied with programming assignments and extra reading material give solid understanding of the topic, its current trends, and future direction.

автор: Igor C C

Nov 05, 2018

I think that should have an optional video with the mathematics behind the convolution/cross relation, showing element-wise operations on a small volume with more than one channel. I know most people will find it boring, but i think it will make easier to fully comprehend the 1x1 convolution.

автор: Wei F

Dec 17, 2017

Really enjoyed learning this course. I'm a PhD Student in CS but neither in computer vision or NLP. I feel like these courses are sort of jump-starter, if you would like to learn more about DL and to be expert, there's a long way to go. However, this is really a good starter!! Thanks Andrew!

автор: Adarsh K

Feb 04, 2020

The best place to start Computer Vision! You'll get to implement state of the art Techniques in CV, most with practical Application. The quizzes are very well designed and test your concepts. You'll learn to use open source implementations and build on top of that as well. Wonderful Course!

автор: Dipo D

Jan 11, 2020

Like the other courses in the DeepLearing.ai certification, this course was also very crystal clear in teaching the concepts. Now, I can confidently read additional materials on Computer Vision. The assignments were also well thought out, kudos to all the TAs. Thanks for the awesome course.

автор: Rahuldeb D

Sep 04, 2018

Another exceptional course offered by Coursera. There are lot of new concepts to learn in this course.

Prof. Andrew Ng has explained each and every concepts in very lucid manner. I want to give a big thanks to Andrew Ng and all other teaching associates for offering such a beautiful course.

автор: Brandon W

Nov 24, 2017

Students had some technical issues throughout this course, with the autograder not correctly grading the assignments despite having all expected outputs correct. In time, I hope these issues can be fixed. However, given the level of instruction and quality of the course, still deserves a 5.

автор: Ajay S

Aug 30, 2019

really a great course for the image learning . i love this course well . and thanks for providing me the financial aid for the course . this will really help me to complete my research work on time .

Thnaks. for the profession Andrew Ng . for the designing and teaching a wounderful course.

автор: Sean C

Feb 20, 2018

Andrew Ng's explanation of Inception Networks greatly helped to demystify more complex-looking architecture diagrams in Google's Inception Net. This course helped a lot in being to be able to understand the base building blocks, as well as their arrangement & purposes within the network.

автор: Vincenzo M

Nov 26, 2017

Another super course from Andrew Ng and his team. As the other courses of the specialization, it presents the core concepts clearly. The exercise are foundamental to retain the concepts. As a suggestions, I would substitute the style transfer with an example more useful for real problems.

автор: MOHD F

Jul 23, 2019

Convolutional Neural Networks by Andrew Ng is a Great course to start into the of CNN's Terminology for DeepLearning. This course provides me with a solid background in how the Convolutional Neural Networks works internally. Great lectures ........... Great everything thankyou Coursera

автор: Miroslav M

Apr 24, 2019

I've gained very important knowledge for Image verification and recognition algorithms using ConvNet models. These models are used nowadays powering robots and self-driving cars. Thank you very much deeplearning.ai for this opportunity to get closer to finishing my new carrier journey.

автор: Janzaib M

May 06, 2018

Very very well designed homework. Gave me a really close feel of deep learning for computer vision. The great thing is, in this course you play with very very state of the ConvNet architechture. Thank you so much Professor Andrew NG and your team. A very big contribution you have done.

автор: Huang C H

Nov 24, 2017

Convolutional Neural Network are exciting to learn, but its concept can be quite abstract. However the materials are delivered progressively, and in a concise manner. The programming exercises are challenging. I hope there was more in-depth introduction to Tensorflow and Keras, though.

автор: Feng W

Mar 15, 2019

I have some problem doing week four programming assignment "Happy House Face Verification/Recognition". The pre-trained model "FRmodel" wouldn't be loaded (waiting for over half hour). I still managed to submit the assignment and passed the test without running out the correct result.

автор: badreddine m

Dec 24, 2017

it is my second courses in coursera after Machine learning by Andrew Ng and Stanford university, I'm very satisfied by the courses quality and encourage you to go further, I'm a follower of coursera courses and one day I will contribute to share more knowledge using coursera platform.

автор: Sami

Feb 15, 2018

i think that's the most important course for me, of course all of them, where very very useful, but being an undergraduate Robotics engineer, the most essential thing is to learn image processing and how to make your robot think and learn and detect object and learn from environment.