Save for later

Convolutional Neural Networks

Deep Learning,

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.

Get Details and Enroll Now

OpenCourser is an affiliate partner of Coursera and may earn a commission when you buy through our links.

Get a Reminder

Send to:
Rating 4.6 based on 3,411 ratings
Length 5 weeks
Effort At the rate of 5 hours a week, it typically takes 5 weeks to complete this course
Starts Jun 19 (50 weeks ago)
Cost $49
From via Coursera
Instructors Andrew Ng, Head Teaching Assistant - Kian Katanforoosh, Teaching Assistant - Younes Bensouda Mourri, Kian Katanforoosh, Younes Bensouda Mourri
Download Videos On all desktop and mobile devices
Language English
Subjects Programming Data Science
Tags Computer Science Data Science Algorithms Machine Learning

Get a Reminder

Send to:

Similar Courses

What people are saying

computer vision

This was a very decent exploration of how Convolutional Neural Networks are used to solve various computer vision problems.

I recommend it to everyone seriously interested in Computer Vision advanced tasks.

It was my first exposure to computer vision/CNNs, and I can say that the introduction here is absolutely the best.

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 Enjoyed the course but the programming assignments weren't well designed I think.

Since I have a computer vision background I was expecting much more challenges at this points when doing the pratical assignments.

Course provides good overview over state-of-the-art techniques in computer vision.

Gave me a really close feel of deep learning for computer vision.

Good course to get knowledge in Computer Vision 非常好。讲得很细! some of the quizzes were a little buggy very cool!

This course covers the basics of convolutional neural networks , resnets, inception nets, yolo, style transfer, face recognition.The programming assignments mostly for yolo and face recognition is done with transfer learning , i think its only fair as they are computationally expensive to train.I am confident about all the materials covered in this course Andrew Ng as always breaks down the problem to the basics so you can understand them.Its a great course if you want to know and implement the well known computer vision problems with the well known algorithms.

Overall the Course is good but the only examples given in assignments or lectures pertain to Computer Vision and Image recognition/manipulation.

A must course to get start in Convolutional Neural Network and Computer Vision.

Hey,There are lot of things are happening in computer vision field and this course helped me in understanding the concept like convolution and their use in computer vision field.

Practical advice like using existing open-source implementation or existing network architecture are really helpful.Overall this course equipped me to understand the CNN and it's practical application in computer vision field.ThanksVipul Shaily Excellent Course Enjoy the examples.

CNN is a technically-difficult-to-understand, still-evolving field of Neural Networks, and it has thus far found remarkable uses in the field of computer vision.

Read more

face recognition

Absolutely fantastic course,I just loved it.....Only problem was to me in the face recognition topic.Training a siamese network need sharing base model with multiple inputs,which is important for training model with unconventional loss functions like triplet loss.And this isn't covered in the course.If that is included in it would be awesome Nice Course.

Learned skills for building driverless car and face recognition!

Andrew Ng covers relevant and current topics on DeepLearning community, autonomous driving, face recognition and convolutional neural networks.

Other than the Face Recognition Assignment (grader problems) the Course was a very good experience.

Great Course but I found some bugs with the assigments of face recognition.

A great course, unfortunately I had to fight with the grader for week 4 face recognition :).

W4 face recognition assignment is very buggy, also the whole website seems to be really slow in general.

Many times I had a correct solution, spent a lot of time trying to fix it only to discover via the discussion forum that an incorrect solution passes the grader ;/ Would give it 5 stars were it not for a) the grader problem in the face recognition exercise and b) some of the obscure tensorflow in the NST exercise.But all in all prof Ng is brilliant and the way the course is set up is very intelligent and challenging.

I would like to learn more about Face Recognition and other Image Detection applications.

Face recognition is a bit oversimplified, there is more to it that a simple accuracy metric.

Frustrated since in week 4 face recognition notebook, you need to put the "wrong" code there which did not match the given output to "cheat" the grader to get points.

Great course, but some discrepancy between face recognition/verification notebook and the grader make this impossible to get full grade (I had to check in the forum and enter an answer giving a result not corresponding to the expected output).

2) face recognition assignment wasted lots of time due to incorrect data and expected result!

这门课真的特别好,特别是对于入门者来说。 Please fix the grader in Week 4 - Face recognition - Triplet loss exercise Andrew Ng : Just the best professor ...

Read more

neural style transfer

A nice course on convolutional neural networks, face recognition and neural style transfer.

Great diving into the cutting edge computer vision algorithms (such as YOLO), the state of the art CNN architectures(ResNet, VGG, Inception Network, Siamese Network), with a variety of applications of this architectures and algorithms, such as self-driving system, neural style transfer generator and face recognition and verification!

CNN is very powerful and it's the core of object detection, face recognition and neural style transfer.

Plus, you learn how to implement Neural Style Transfer (DeepDream) here!

-- Another example, on the programming assignment, on Neural Style transfer, it is POORLY explained how the framework works when it comes to setting a_G and a_C.

The intuition behin object detection/face recognition and neural style transfer are well explained, but some more details for understaing how these models work is missing in my opinion.

Having the grading system a bit more flexible would save everybody's time.I didn't understand all the operations we did in tensorflow in the neural style transfer programming assignment.

It provides all the basic theoretical and practical knowledge to get you started right away with CNNs and its applications in computer vision, including state-of-the-arts algorithms for image recognition, face detection and neural style transfer.

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.

the best course out of all 4 in deep learning.The best thing i liked most in this course is the applications such as1) Image classification/Image recognition2) Object detection-Automatic Car Driving3) Face Verification and Face Recognition4) Neural Style Transfer pretty cool!

Great, loved it This is a great course which make me know how to do computing vision and neural style transfer (which is something I thought amazing before).

One of the best courses on ConvNet; it is rigorous and yet fun because of the broad range of projects - from Object Detection to Face Recognition / Face Verification and Neural Style Transfer.

I really enjoyed learning about CNNs, YOLO, and Neural Style Transfer.

I especially liked the Neural Style Transfer homework.

Read more

object detection

Awesome wonderful and useful, It helps me a lot when I try to familiar with face recogization, object detection and so on.

Grate learning experience Great course which gives me a basic understanding on the technologies behind object detection, face recognition.

this course should get you started with object detection (where in the picture is/are this object/s?).

Fascinating how straight-forward it is to build a CNN to do object detection and face recognition/validation.

Planning to try out a face recognition use case in office before the next course on sequence models start :)Thanks again Good introductory course for ConvNet and its trending applications such as object detection and facial recognition.

The next weeks gives you what are under the hood in object detection systems, other CNN architectures, style use...

The course assigments give hands on experience in object detection and face recognition.

Thank you so much for including object detection in this course.

Covers a wide array of immediately appealing subjects: from object detection to face recognition to neural style transfer, intuitively motivate relevant models like YOLO and ResNet.

Even experienced professionals can have all their concepts cleared not only in CNNs, but also in YOLO and it's applications in object detection.

Other topics were also learned that included me applying these concepts into real-world applications like the neural style transfer as well as the object detection and face recognition.

The week 1 and 2 were perfect, then week3,4 had some issues with the lectures- Andrew sir was repeating some parts and the problems/corrections in the slides.Also the week3 object detection was tough n the hints were not enough, with the errors in the assignment submission costing me a day explained very wellvery interesting with andrewthe main problem with this course is bug fixing on assignments.. i lost alot of hours just because of this Very elaborate concepts explained in a very simple and understanding manner.

Got to know how CNN, Facial recognition and Object detection works.

My personal favorite part was Object detection.

Read more

looking forward

The most exciting of the four courses so far, now looking forward to course 5. amazing projects and andrew is as fantastic as ever Really nice well explained course.

Looking forward o sequence models!

Looking forward to recurrent NN course.

Looking forward to try my own models now.

Excellent material and presentations!The assignments are more challenging this time, so don't expect passing them too easily.Looking forward to the next course in the series!

Looking forward to completion of the specialization.

very frustrated Very interesting to learn but won't be useful for my role.Looking forward to sequence models!

Looking forward to see the fifth course sequence models!

And of cause, I'm looking forward for the fifth course.

Looking forward for the next course in this specialization.

I was really looking forward to learn about ConvNets.

Looking forward to sequence models :) While as always Professor Ng was brilliant and informative, the final homework assignment (face recognition) was a disaster.

I am looking forward to the next course with RNNs and LSTMs!

Looking forward for the next class in the series.

Read more

deep learning specialization

I really can't recommend this course highly enough (and the same goes for the entire Deep Learning Specialization).

This has been the most exiting course within the Deep Learning specialization by deep

The best course (at least of the four courses that I have already taken) in the Deep Learning Specialization.

This has been the best course in the deep learning specialization so far.

Muchas Gracias... !The course is very good, particularly I am very grateful to COURSERA, for giving me the opportunity to do the five courses of the Deep Learning Specialization with financial aid and allowing me to have access to this type of training and certification.

Still don't see the logic of the identity layers One of the most important courses in the Deep Learning Specialization in my opinion.

This is course 4 of the Deep Learning Specialization.

This course was the greatest one among the first 4 courses of the Deep Learning Specialization.

This is one of the interesting part of the deep learning specialization.Good work !!

Another great course in the in the Deep Learning specialization.

amazing Another great course in the Deep Learning specialization.

This is the best course in Deep learning specialization.

Even though the programming assignments were pretty tough in this course (for me the toughest of all the courses in the deep learning specialization), I managed to complete this course in (my) record time.

Among all the Deep Learning Specialization courses, this one is the best.

Read more

about convolutional neural networks

Best course about Convolutional Neural Networks, strongly recommended.

One of the most complete courses about Convolutional Neural Networks I´ve ever listen to.

A lot of valuable information and knowledge about convolutional neural networks.

Great stuff and lot of things are covered comprehensively to learn about Convolutional Neural Networks Highly complicated topic very well presented, a lot of applicable content.

Well designed and structured course to learn about convolutional neural networks.

kudos to the team behind... Great Course for learning about Convolutional Neural Networks.

I've learned a lot about Convolutional Neural Networks from this course!

You get to know a lot in detail about convolutional neural networks , how they work and how to apply it in computer vision problems .

Learnt a tons about convolutional neural networks and computer vision algorithms.

Very informative about convolutional neural networks but had lengthy assignments Faced Some challenge with the Course Assignments that was too time consuming but overall the course was pretty good Excellent Course Grading assignments troubles are annoying especially after such a good teaching it is really frustrating.

This is the best comprehensive course about Convolutional Neural Networks.

[1] Decently organized assignments [2] Andrew deals with important topics about convolutional neural networks.

This course helped me to learn in detail about convolutional neural networks.

Read more

highly recommend this course

Another excellent course by professor Andrew Ng and Coursera, the level of explanations and material are excellent, the detail in those Jupyter Notebooks is fantastic, I highly recommend this course to anyone interested in Deep Learning.

I highly recommend this course, especially for those who are new to the field.

I would highly recommend this course to anyone looking to dive deeper into deep learning and computer vision!

I would highly recommend this course as learning from basic stratch to deepen your understanding about the subject topic, Although i found it very hard to solve the assignments because i was not on the track of tensorflow.I would also recommend to take cs20 class by stanford which teaches tensorflow very well or you can refer the youtube videos for tensorflow also.

I you want to have a good course on Object Detection, Neural Style transfer, I would highly recommend this course.

Highly recommend this course to everyone!

Highly recommend this course!

I highly recommend this course to anyone who wants to be an adept Deep Learning Practitioner.

I highly recommend this course to any aspiring machine learning student.

Read more

tensor flow

The hands-on assignments are generally of the right level, although a longer introduction to Tensor Flow would be useful.

But the homework, most of time, I am searching the forum try to understand the tensor flow, also the errors from the grading system still exists from time to time.

Also the involvement of Keras I found annoying, yes it eases the implementation of ConvNets, but while learning I would have preferred to use tensor flow instead, or even implement a simple NumPy ConvNet on my own.

I suggest anyone interested in deep learning vision to start with this course and then move on to implement a CNN in tensor flow form scratch using one of many tutorials online.Thank to the team for this great course!Best regards, Some kinks in the video cutting of Andrew when he makes mistakes, but otherwise very good course.

Much better than Tensor Flow courses that just want you to know how to use the tool.

I think, the hints can be very helpful for even new tensor flow users.

Though, I think the last week is not that much important for the industry purpose but definitely it is good for those who are interested in non-industrial use of tensor flow and neural networks.

That said, reading some supplementary tensor flow materials would probably be helpful as I'm still a little hazy on it.

the only drawback in my opinion is that one who's not trained in using tensor flow can have hard times in figuring out what's happening and what should be done.

The programming assignment is more challenging to me mainly because I am not that familiar with tensor flow, and higher number of dimension in this field requires more focus and concentration.

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 Amazing course!

Brand new concept of Neural Style Transfer and Face Recognition with One-Shot Learning This course give me a better intuition about what cnn is and how it's work.In this course's programming exercise you will learn Keras framework.HaPPy LearnING :) The content is really useful but the assignment could be more challenge and maybe add a tutorial of Keras and Tensor flow.

star less because the language Keras and Tensor Flow where I felt difficulty.

Frustrating and annoying pitfalls in the assignements: most of the time you lose time on trivial syntactical issues on python / tensor flow, rather than concentrating on the model itself.Beside that the Kernel stabiliyt is gettin worse and worse in these courses as the weight of the models increase: the kernel breaks too frequently and you don't have any other way to restart it from the beginning, losing all the modification.

Read more

cutting edge

You're not just learning about cutting edge computer vision techniques, carefully and thoroughly explained, you're gleaning the distilled wisdom of a true master of deep learning.

Very simple and understandable submission of very hard to read and realize machine learning papers, perfect explanationof the cutting edge machine learning algorithms, architectures and approaches used in this field.

Dr. Ng really exposes us to this cutting edge research, by explaining research papers, starting from its 'inception' to work that was published just two years ago.

Making cutting edge research accessible to learners.

Excellent cutting edge materials.

too many bugs Excellent for learning the fundamental ideas behind CNN's and also cutting edge applications.

Most of the techniques taught are cutting edge and replications of recent papers.

This course is really instructive and teaches cutting edge algorithms in the field.

Great real-life and cutting edge applications of CNNs!

Once fixed it was the normal extremely useful, introduction into very cutting edge stuff.

Highly recommended to learn about the cutting edge scale and depth.

Read more

step by step

I only wish there was an opportunity to go step by step from looking at images, creating the dataset from the images, creating labels, applying a model, and then testing.

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.

Step by step explanation of every component in CNN, the logic, the steps and also hands down clearly designed course for anyone who wishes to understand CNN from group up.

I am glad to have taken up this course and I hope to start using my learning in the coming months Very good course to give step by step introduction about CNN Very good material.

Positives:1) Well designed course that takes you through the concepts of CNNs step by step and introduces cutting edge state-of-art applications based on it.2) As always well prepared lectures effectively deliver the course material.Negatives:1) Course lectures should have covered overviews of actual models used in assignments (YOLO for object detection, Inception network for face recognition..) and the actual cost functions that were used to train them.

Overall a very comprehensive course that guides you into the the computational framework of convolutional neural networks step by step.

An excellent course, and step by step.

They made it easy, step by step, and practical.

Read more

happy house

Despite the confusing bug and server running problem in the last assignment of happy house ,the course is still great .

However, the programming assignments, in particular the Happy House, was done in a rush due to errors in the models and code provided.

Assignement: Face recognition for happy house was not happy at allit took me 4 attempts to pass.

good but it's hard :D 很好的教程,喜欢的朋友可以试试 Would have given it 5 stars but the notebooks were problematic, especially week 4 Happy House.

It was a great help for me Another very good course, only marred by the problems with running the final 'Happy House' face recognition notebook of week 4: the values did not seem to load into the model.

There some problem with the happy house assignment in week 4, specifically in function 'verify', kindly omit that mistake, otherwise, everything is great, loved it very good excellent course, absolutely brilliant Excellent course...!

Thank you professor who helped me in understanding lectures and my peers who helped me in discussion forums:) 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.

Videos are good, but exercises are really confusing please fix the following problemweek 4 Programming AssignmentsFace Recognition for the Happy House - v3 Unable to load FaceNet Can't load weights - deleting them is not solving the problem Great course to start deep learning study.

I wish the assignments were a bit more challenging I have some problem doing week four programming assignment "Happy House Face Verification/Recognition".

On the final happy house assignment, I think I spent more time trying to load and reload the notebook (when I get the "method not allowed" warning) than actually finishing the assignment.

Read more


An overview of related careers and their average salaries in the US. Bars indicate income percentile.

AWS Developer - (OPT EAD can apply) $63k

Build / DevOps Engineers $67k

Design/Build Manager $87k

Assistant Professor of Neural and Behavioral Sciences $118k

Assistant Professor of Neural and Behavioral Sciences $118k

Client Build Team $123k

Network Build Engineer $128k

Principal Design/Build $142k

Software Build Specialist $143k

Build & Release $151k

Embedded Build Engineer $176k

Build Engineer Lead 2 $219k

Write a review

Your opinion matters. Tell us what you think.

Rating 4.6 based on 3,411 ratings
Length 5 weeks
Effort At the rate of 5 hours a week, it typically takes 5 weeks to complete this course
Starts Jun 19 (50 weeks ago)
Cost $49
From via Coursera
Instructors Andrew Ng, Head Teaching Assistant - Kian Katanforoosh, Teaching Assistant - Younes Bensouda Mourri, Kian Katanforoosh, Younes Bensouda Mourri
Download Videos On all desktop and mobile devices
Language English
Subjects Programming Data Science
Tags Computer Science Data Science Algorithms Machine Learning

Similar Courses

Sorted by relevance

Like this course?

Here's what to do next:

  • Save this course for later
  • Get more details from the course provider
  • Enroll in this course
Enroll Now