Chevron Left
Retour à Convolutional Neural Networks

Avis et commentaires pour d'étudiants pour Convolutional Neural Networks par deeplearning.ai

4.9
étoiles
28,556 évaluations
3,451 avis

À propos du cours

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....

Meilleurs avis

AG

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.

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.

Filtrer par :

226 - 250 sur 3,409 Avis pour Convolutional Neural Networks

par Yernur N

Jul 18, 2019

It is an essential course for those who wants to boost their general knowledge in the area of CNNs. It will give you a great foundation to build on your career and further learning. I struggled a bit with Keras, but I am planning on taking another course to learn this field further.

par Matheesha A

Jun 21, 2019

This is an excellent course to learn the concepts of Convolutional Neural Nets. The hands on experience by the weekly assignments were very helpful to understand the concepts. I strongly recommend this course for the students who are interested in learning CNNs. Thanks Prof. Andrew.

par Xiaolong L

Feb 05, 2020

Excellent course! The programing exercises are both realistic and let you build (toy version) of state of art CV system. Many reference to heavy weight papers in the domain in the course, which student who really want to get into DL and CV can read and further expand their horizon.

par MADAN M

Feb 22, 2018

I got thrilled by the lectures and its assignments. One thing that I would request is a lecture on how to use pre-computed models, in all the assignments we are using pre-computed models. Andrew explains why we should use them but in practice its seems little difficult to use them.

par Shaelander C

Dec 10, 2019

Very informative course . Professor Andrew Ng has done a great job of explaining most of the concepts of CNN. And Assignments are really good to apply what we learn in the lectures. Professor Andrew is the best professor I ever came across the style of his teaching is unmatchable.

par Animesh S

May 21, 2019

Great course, concisely conveys both techniques and advice for practical implementation of Neural Networks in Image recognition. Great for a person who is already familiar with the idea of Deep Learning and want to take it forward, and ties in perfectly with the specialisation.

par Ali S

Aug 10, 2018

This course is a perfect way to teach these high-level concepts. They made it easy, step by step, and practical. You can learn not only convolutional neural networks in both conceptual and practical way, but also a lot of tips and tricks about tensorflow, Keras and even python.

par Shivdas P

Jan 01, 2020

The course is well structured, especially the exercise where one has to code the complete CNN example. It gives good insights on how to use the frameworks such as TensorFlow and Keras. Feel comfortable in understanding the concepts around CNN and it's implementation using TF.

par Gurubux G

Aug 20, 2019

One of the toughest and most exciting Course I have completed on the internet. Thanks a ton Andrew! I wish I can work with Deeplearning Team someday, so that I can learn every week, every day and probably explore the deepest of the Learning ocean potential that the team holds

par Gilad R

Aug 13, 2019

I really liked the dive into academic literature combined with the wide view of CNNs across various applications. The programming exercises were very revealing and informative, although a little more guidance on TensorFlow technicalities would have helped accelerate learning.

par Bernard O

Oct 31, 2018

This is quite a challenging course. Critical lessons on convolutions are the biggest value to me on this segment of the course. Takes a lot of the mystery out of CNN, but need to work hard at it. A very rewarding experience but does come with a few tear-my-hair-out incidents.

par Stephen V K

May 17, 2019

The course does an very good job of explaining the concepts behind different types of neural networks, but the homework assignments pretty much only test these concepts. Students should not expect to gain any significant experience coding neural networks in keras/tensorflow.

par Himanshu B

Jul 17, 2018

This is must course for the ones who really want to move into deep learning and the most important part of Deep learning and machine learning. So much informative and the best part is practical implementation where learning is so much great and informative with instructions.

par Luis A O A

Mar 20, 2018

I had only a little knowledge of CNN and struggled to grasp some concepts but after watching the lectures only once I can confidently explain the structure of a CNN and even compute the dimension of the layers on the fly thanks to the quiz questions. Totally would recommend.

par Fanyi D

Nov 18, 2019

Prof. Andraw Ng is very good at presenting the core ideas to audience in simple and intuitive words and this course is especially useful for engineers with different background to step into or refresh some principles of the CNN. I personally strongly recommend this course.

par Kurt K

Nov 27, 2017

A clear explanation of a difficult subject with an emphasis on being able to create and to understand your own neural networks.- Plus in this module how to use algorithms which significantly reduce your computational needs and with an introduction to processing visual data.

par Arkajyoti M

Jun 10, 2019

Thank you so much for this wonderful course.

I have only one suggestion there's a lot of bugs in the notebooks, especially the last one Week 4 Happy House Face recognition. Please fix that as a lot of weights are missing and completing that exercise involves a lot of hacks.

par Alex B

Oct 12, 2018

The most challenging course in the series so far, it was also the one that helped me best understand how these networks function. I have already recommended this course to colleagues, and think it is the perfect course for an intro to computer vision, tensor flow and Keras

par Aditya A G

Mar 17, 2018

Very nicely prepared and presented. Assignments gives good insights into concepts learned while for yolo,neural styles, face recognition problems eagerly looking for building CNN architectures from scratch & training them in future courses. Thanks a lot Andrew & Team..!!

par Serzhan A

Nov 20, 2017

The best course in the series so far. Andrew Ng makes the complicated seem easy and does so by dividing the topics into small digestible pieces. You will binge-learn his courses because of how addicting and gratifying the experience of learning is made by the instructor.

par Leonardo R C

Jun 01, 2019

This is a very interesting and fun course to take. You put into practice all the knowledge from previous coruses from the specialization and apply them in applications that are changing the world right now. As usual, professor Andrew explains every concept perfectly.

par Harold L M M

Nov 19, 2018

The best course by far in this specialization. This course covers all the important topics in Convolutional Neural Networks, face verification and face recognition.

You have to work very hard to complete it. Thus, it's a great challenge!

Thank you Professor Andrew Ng!

par Yoan S

Oct 05, 2018

These courses are VERY well put together and concentrate excellent concept in little time compared to taking the available Stanford CNN classes online which are verytime consuming for the same result. Andrew is motivating and makes difficult concepts very accessible.

par 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.

par 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.