Inside an Artificial Brain is made using a visualisation technique applied to a neural network trained to recognise 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 seconds) the next layer is targeted until the lowest layer is reached.
The resulting video shows how the machine abstracts vision. It starts off with simple shapes and lines, and then gradually increases the level of abstraction until faces and animals can be identified.