Chevron Left
Вернуться к Convolutional Neural Networks

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

4.9
звезд
Оценки: 28,628
Рецензии: 3,463

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:

251–275 из 3,421 отзывов о курсе Convolutional Neural Networks

автор: Xavier S P

Dec 20, 2017

The idea of inserting convolutions into the net and in the back propagation is really cool yet so simple to implement after watching those lectures. It makes sense why image simplification via convolution in layers can greatly help performance in a deep learning net.

автор: 梁礼强

Apr 02, 2019

this course is pretty good,but the some of these techniques introduced in class are slightly out-of-date,such as yolo v2 and this version of neural style transfer. It's OK as an introduction, but it may be better to mention the latest or general version algorithms.

автор: Nilanka W

Jan 14, 2018

This course taught how the latest computer vision systems works. The content is really great and the lectures and mentors have put a lot of effort in creating the assignments and notebooks, which are high quality. recommend to anyone who are interested in the field

автор: Rúben G

Oct 20, 2019

Through this course I understood how modern Computer Vision tasks are addressed with CNN. Also I learn that a CNN can be combined with a FCN. I further understand better the notion of the neural network and the advantage/disadvantage of having more or less layers.

автор: Michael F

Nov 01, 2018

The best in this series of courses so far. The maths was hard, and the programming assignments were accordingly at a higher level. But the applications of ConvNets are so fascinating, and their implications so profound, that I enjoyed every moment of this course.

автор: Pavan K V

Jan 19, 2018

the best course out of all 4 in deep learning.The best thing i liked most in this course is the applications such as

1) Image classification/Image recognition

2) Object detection-Automatic Car Driving

3) Face Verification and Face Recognition

4) Neural Style Transfer

автор: Zhao Y

Nov 25, 2017

This course gives me a deep understanding of CNN and also introduces me some latest information about face recognition. It makes me have an access to learn AI in an efficient way. Words seem to fail me when I want to show my gratitude to the teachers and mentors.

автор: khalid w

Nov 10, 2019

This course has helped me very much in understanding the nomenclature of convolution networks. Previously I struggled reading different research papers related to convolution networks as I was unable to understand the different dimensional changes in each layer.

автор: Oleksiy S

Dec 20, 2018

Exellent course for first experience with convolutional networks. A few mistakes that seem frustrating at the time you are completing course really help to gain better overall understanding. Thanks a lot for good work all the involved people, stuff and mentors.

автор: Sayar B

Aug 16, 2018

Perhaps the toughest course so far, Convolutional Neural Networks introduces us to computer vision. Professor Andrew explains complex, state-of-the-art cases where computer vision is being used today. Great programming assignments, great lectures, great course.

автор: Shifeng X

Mar 25, 2018

awesome course! the assignment is actually not just a piece of homework, it indeed a kind of guidance, give you detail step by step examples of how to code the learned algorithm. Thanks to the lecturer, didn't find any course more 'user-friendly' than this one.

автор: ABEL G G

Nov 07, 2017

Wow.. what Can I say? This was the toughest of the three previous but super happy to be in this journey.

I learned a lot and I am motivated more than anytime to immerse myself in this field. There is so much to learn. Thanks to all the people behind this course!

автор: Karthikeyan R

Dec 29, 2019

Again, excellent course from Andrew Ng! Made complex algorithms and concepts very clear! Got to know how CNN, Facial recognition and Object detection works. Reference to the literature paper will come handy in the future if one thought of diving deep into CNN.

автор: Julian S

Nov 20, 2017

Excellent course. Concepts very clearly described. Only improvement would be more Tensorflow and possibly Keras training. Yes, you can go elsewhere for this, but Andrew Ng is so good at explaining, I'd expect he'd do a better job!

Many thanks Mr Ng and team!!

автор: Yao F

May 20, 2019

The course is pretty good with advanced techniques on computer vision. The only regret is one problem about the last coding homework. I failed to load the pre-trained model and can only finish the home work without checking the accuracy of designed examples.

автор: Pankaj D

Dec 26, 2017

Amazing course plan and delivery! Classic CNN architectures, ResNet, YOLO, face-recognition, neural-transfers - all in a very succinct package! Some very minor issues with auto-grading of assignments, but nothing that the discussion forums won't get you thru.

автор: Jayaram R

Jan 28, 2019

Andrew's explanations, and the exercises are absolutely fantastic. There seems to be a lot of tricky math in Convolution Neural Networks and Andrew's explanations and illustrations help students understand the essential concepts behind each type of Conv net.

автор: Paul S

Nov 29, 2018

Excellent course. Very good and well structured explanations by Andrew Ng: one concept per video, sometimes a second video to explain why the concept works or to give some intuition. Course covers many of the classis deep learning papers. Highly recommended.

автор: Joshua P J

Aug 07, 2018

Weeks 1 & 2 were very good. Week 4 was excellent with extremely clear presentation. I didn't like week 3; it felt like the topics were presented in random order, and the homework felt trivial (I finished it easily but I still have no idea what was going on).

автор: Kaan A

Jul 30, 2019

This course was the greatest one among the first 4 courses of the Deep Learning Specialization. Real world examples were perfect. Moreover, the paper suggestions helped me a lot to learn through my process of this course. Thank you Andrew and Coursera Team.

автор: Michael G

Nov 16, 2018

Great examples and walkthroughs. I didn't think I would be able to code all the various CNN architectures, but this course made that process challenging, but doable. Now it is time to start working on side projects to sharpen the skills I have learned here.

автор: Artem P

Apr 22, 2018

Probably the best course in the specialization (well, along with Sequence models). 50 layer VGG model built in Keras gives awesome enterprise-level results on a relatively small data sets..! But I recommend taking all these courses, they are all very good.

автор: 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.

автор: 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

автор: 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.