WHY ARE GOOGLE’S NEURAL NETWORKS MAKING THESE BRAIN-MELTING IMAGES?


Cool little surprise gift of the internet age.

The acid trip you’re looking at is the result of a feedback loop occurring in an artificial neural network, which is a series of algorithm “layers” acting like neurons do in the brain. These networks can learn — each neuron connection can adjust its own “weighting”and prioritization — and with practice become much better. Google does this with their image-recognizing neural networks by feeding them millions of photos and adjusting the layers until the output is correct. The ultimate goal is to have a program that could see any kind of picture with a dog in it, for example, no matter the lighting, orientation, color, etc., and tell us there’s a dog in the photo.
For these trippy images however, Google engineers decided to look into what each neural network layer was doing as it looked for certain image aspects, starting with basic components like edges and lines, and ending with “dog”.
...
Google calls this technique of diving deep into the abstractions of images at certain layers of image recognition “Inceptionism”.

Cool little surprise gift of the internet age.