The results are intriguing—even a relatively simple neural network can be used to over-interpret an image, just like as children…

The results are intriguing—even a relatively simple neural network can be used to over-interpret an image, just like as children we enjoyed watching clouds and interpreting the random shapes. This network was trained mostly on images of animals, so naturally it tends to interpret shapes as animals. But because the data is stored at such a high abstraction, the results are an interesting remix of these learned features.

http://googleresearch.blogspot.be/2015/06/inceptionism-going-deeper-into-neural.html