News for hackers. Stuff that matters.
Re:Deep Dreams with Caffe by rsp1984 on Thursday July 02, 2015 @08:35AM (#9818396)
I always wonder why sometimes the system finds faces and other elements in essentially untextured / homogeneous parts of images. Wouldn't there be some sort of "data term" in the energy functional that would suppress these results and/or move them to other parts of the image?

Perhaps this is working entirely differently and I'm thinking too much in the classical computer vision realm. Would love some explanation though.

Re:Deep Dreams with Caffe by wodenokoto on Thursday July 02, 2015 @12:02PM (#9819762)
I imagine the chance of an input that would result in zero confidence in all output nodes is damn near zero.

There will basically always be an output nose with the highest confidence, no matter how low.