Hinton had trained a five-layer neural network to recognize handwritten digits when given their bitmapped images. It was a form of computer vision, one that made handwriting machine-readable. But unlike previous works on the same topic, where the main objective is simply to recognize digits, Hinton’s network could also run in reverse. That is, given the concept of a digit, it can regenerate images corresponding to that very concept. We are seeing, quite literally, a machine imagining an image of the concept of “8”. The magic is encoded in the layers between inputs and outputs. These layers act as a kind of associative memory, mapping back-and-forth from image and concept, from concept to image, all in one neural network. “Is this how human imagination might work? But beyond the simplistic, brain-inspired machine vision technology here, the broader scientific question is whether this is how human imagination — visualization — works. If so, there’s a huge a-ha moment here. - medium.com