AN ARTIFICIAL brain has taught itself to estimate the number of objects in an image without actually counting them, emulating abilities displayed by some animals including lions and fish, as well as humans.
Because the model was not preprogrammed with numerical capabilities, the feat suggests that this skill emerges due to general learning processes rather than number-specific mechanisms. "It answers the question of how numerosity emerges without teaching anything about numbers in the first place," says Marco Zorzi at the University of Padua in Italy, who led the work.
To investigate ANS, Zorzi and colleague Ivilin Stoianov used a computerised neural network that responds to images and generates new "fantasy" ones based on rules that it deduces from the original images. The software models a retina-like layer of neurons that fire in response to the raw pixels, plus two deeper layers that do more sophisticated processing based on signals from layers above.
The pair fed the network 51,800 images, each containing up to 32 rectangles of varying sizes. In response to each image, the program strengthened or weakened connections between neurons so that its image generation model was refined by the pattern it had just "seen". Zorzi likens it to "learning how to visualise what it has just experienced".
Infants demonstrate ANS without being taught, so the network was not preprogrammed with the concept of "amount". But when Zorzi and Stoianov looked at the network's behaviour, they discovered a subset of neurons in the deepest layer that fired more often as the number of objects in the image decreased. This suggested that the network had learned to estimate the number of objects in each image as part of its rules for generating images. This behaviour was independent of the total surface area of the objects, emphasising that the neurons were detecting number.