The posting you link to is a misleading description of what these images actually represent. Here's the original: --- http://googleresearch.blogspot.com/2015/06/inceptionism-going-deeper-into-neural.html We ask the network: “Whatever you see there, I want more of it!” This creates a feedback loop: if a cloud looks a little bit like a bird, the network will make it look more like a bird. This in turn will make the network recognize the bird even more strongly on the next pass and so forth, until a highly detailed bird appears, seemingly out of nowhere. ---
no subject
Here's the original:
---
http://googleresearch.blogspot.com/2015/06/inceptionism-going-deeper-into-neural.html
We ask the network: “Whatever you see there, I want more of it!” This creates a feedback loop: if a cloud looks a little bit like a bird, the network will make it look more like a bird. This in turn will make the network recognize the bird even more strongly on the next pass and so forth, until a highly detailed bird appears, seemingly out of nowhere.
---