daoran

From what I understand, the task of their toy experiment is to identify multiple objects in an image. This can be easily solved by simple computer vision algorithms.

The proper solution can be implemented as following. Firstly either using sliding window or selective search like algorithm to generate potential object targets, secondly using trained object models on these targets.

In my opinion, it seems that the researchers didn't know how to use cnn.

Beside Martin Kleppmann's wonderful book, I'd also recommend MIT 6.824 distributed system course, you can find lots of resources on the course website.