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
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.
автор: Shivdas P•
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.
автор: Gurubux G•
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
автор: Gilad R•
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.
автор: Bernard O•
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.
автор: Stephen V K•
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.
автор: Himanshu B•
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.
автор: Luis A O A•
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.
автор: Sai K•
I'm very glad that I chose Deeplearning.ai to learn AI. Andrew not only helped us learn the state-of-the-art techniques but also encouraged us to experiment and explore the concepts. I definitely am looking forward to complete the full specialization. Thank you Coursera !!!
автор: Fanyi D•
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.
автор: Kurt K•
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.
автор: mcvean s•
This course was an amazing experience! Learning with one of the greatest minds in the field, and the simplicity of this course to cover the topics in depth is exceptional. Everyone interested to dive into the field of CNNs and Computer Vision will benefit from this course.
автор: Bharath C•
This course is really informative on various concepts of CNNs and I believe it is a must for any beginner starting in Deep learning to start with this course to understand the overall applications as well as the procedure and programming involved in each of those concepts.
автор: Arkajyoti M•
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.
автор: Alex B•
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
автор: Arun P R•
Its is the finest and greatest course I have ever seen on Convolutional Neural Network. It feeds a lot of intuition on the field of Computer vision and CNN impact on it. It goes through many state of art algorithms and revolutionary implementations of Deep neural network.
автор: Soumyodeep D•
Great Course!! Just completed it. Really a good course for beginners who want a jump start in CNNs. Without the theory given in this course, it will be really difficult for someone to implement Convolutional Neural Nets in practice using Tensorlfow or any other library.
автор: Ruthuparna K•
I am thoroughly satisfied with this course, as it gives a very in-depth knowledge into CNN and their applications, while also giving an introduction into TensorFlow and Keras. Andrew Ng is amazing as always. I loved the interesting things we got to do in the assignments.
автор: aditya g•
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..!!
автор: Serzhan A•
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.
автор: Nguyễn V A•
This course is excellent! I would recommend this course if you love CNN and want to know more about it. Personally, I would like to thanks Andrew Ng and all the equipes for providing such an amazing content. Besides, thanks for giving me the chance to learn this course!
автор: Danilo B•
This course is perfect at introducing a newcomer to CNNs and at the same time covering many applications of this type of neural network. I like how even though the papers mentioned are sometimes 5 years old Professor Ng and the team is able to create such a good course.
автор: Eung P•
An excellent course on CNN! After watching Professor Andrew's video lectures and trying related programming work, I was able to gain a reasonable amount of confidence on the various concepts, which otherwise could have been overwhelmingly difficult and complicated.
автор: Elio M•
Great course once again! It would benefit by having the programming exercises for weeks 2-4 somewhat less trivial, in order to trigger more thinking on the different solutions and how/why they work. It remains still another great piece of work by Andrew Ng. Thank you!
автор: Steve C•
great course with detailed description of the convolutional network concept with many practical examples. Neural Style Transfer was probably one of my favorite programming exercise for machine learning taken in Coursera. Thanks to the staffs for creating this course!
автор: Mihai P•
This course exceeded my expectations. It is very robust and covers a lot of state of the art topics that are really used nowadays. I'm really excited about the knowledge i've gained from this course because it offered a great value that cannot be measured. Thank you!