Posted on Google research blog, researchers posted how neural networks trained to classify images interpret and re-interpret image abstractions, as some examples below.
not bad idea from a friend who immediately identified it (especially bottom examples) with this image search:
 |
| Left: Original photo by Zachi Evenor. Right: processed by Günther Noack, Software Engineer |
 |
| Left: Original painting by Georges Seurat. Right: processed images by Matthew McNaughton, Software Engineer |
 |
| The original image influences what kind of objects form in the processed image. |
 |
| Neural net “dreams”— generated purely from random noise, using a network trained on places by MIT Computer Science and AI Laboratory. See our Inceptionism gallery for hi-res versions of the images above and more (Images marked “Places205-GoogLeNet” were made using this network). |