This is basically an AI hallucinating. It is told to look for certain objects in the image. Anything that looks like those objects is tweaked slightly to look MORE like those objects. This creates a feedback loop that causes all sorts of interesting patterns to emerge.
The brain of the internet, has recently demonstrated that its artificial neural networks have the power to dream by trained these networks to recognize objects, animals, faces and nature, by feeding them millions of images.
This is a slideshow of an image of the CITEC building in Bielefeld processed by Google's neural network Deep Dream. The output is zoomed and fed back to the network as a new input a hundred times.
Neurologist and author Oliver Sacks brings our attention to Charles Bonnett syndrome -- when visually impaired people experience lucid hallucinations. He describes the experiences of his patients in heartwarming detail and walks us through the biology of this under-reported phenomenon.
A journey trough all the layers of a artificial neural network.
This video is made using a visualization technique applied to a neural network trained to recognize a broad range of images. Each frame is recursively fed back to the network starting with a frame of random noise. Every 100 frames (4...