* Fellows, I just got the certificate. As you know, I really love to review the whole specialization so I decide to take the class myself. Since I haven’t watched all lectures yet, this is my usual “Quick Impression”.
* I am a slow learner (getting stubborn? ) , so I was more like the 100th guy who finish the class in our Coursera deeplearning.ai forum. Go check it out. There are many experienced DLers there: https://www.facebook.com/groups/DeepLearningAISpecialization/
* Many of you had noted that it is a very good class for computer vision. My assessment so far this is a very good *first* class if you want to get into DL-based computer vision. But then there are many great material you can still only learn from cs231n. So I would suggest you to go through it as well after you finish Course 4.
* So far as I see, it has perhaps one of the best explanations on basics of Convnet, as well as what YOLO is. Perhaps the pity is the short length of the course disallow going in-depth on topic such as RCNN, segmentation, GAN-based synthesis. All of these, cs231n has much better coverage.
* At this point, the course is still a bit unstable. There are assignment which requires an implementation which doesn’t match the notebook. But the staff is working on it now.
That’s what I have. Hope this is helpful. I am going to write up a full review for Course 3 and 4 soon too.