homehome Home chatchat Notifications


Artificial brain teaches itself how to count objects like animals do

An artificial brain has taught itself how to estimate the number of objects in an image without actually counting them, showcasing abilities displayed by many animals, as well as humans. Due to the fact that the model wasn’t preprogrammed with numerical abilities (it can’t count), it is believed that this skill emerged as a result […]

Mihai Andrei
January 20, 2012 @ 1:44 pm

share Share

An artificial brain has taught itself how to estimate the number of objects in an image without actually counting them, showcasing abilities displayed by many animals, as well as humans.

Due to the fact that the model wasn’t preprogrammed with numerical abilities (it can’t count), it is believed that this skill emerged as a result of a general learning process, instead of a number-specific mechanism.

“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.

The study has its most direct application in understanding and perhaps even treating dyscalculia – a condition in which people are unable (or find it extremely difficult) to do even the simplest of arithmetical tasks, and it could also help in robotics and the general programming of AI.

The skill in case is called ‘approximate number sense’, and it’s quite simple to estimate how good this sense is: all you have to do is take a look at two groups of dots on a page and estimate which one has more dots. Fish use this to hide in bigger groups, lions use it to hunt.

To investigate ANS in the neural network, researchers made it respond to images and generate new ones, based on rules it picks up from previous images. The software practically simulates retina-like layer of neurons that fire in response to the raw pixels which do some more sophisticated processing based on signals from the layer above.

They fed the AI 51,800 images, each containing up to 32 rectangles of different sizes and the program strengthened or weakened some connection between its neurons, so that the general pattern would be refined by what it just saw – basically, it would learn how to visualize what it just saw.

Infants demonstrate ANS without being taught, so the network was not programmed to understand the notion of ‘amount’; but when they analyzed how the neural network was working, they discovered a subset of neurons in the deepest layer that fired more often as the number of objects in the image decreased. This suggest the AI found a way to estimate the objects in each image, independent of the surface area of the objects.

share Share

How paleo-robots could help reveal the secret to life's transition to land

Fossils and computer models are great, but nothing feels as satisfying as reviving extinct animals as robots.

The Picotaur robot is nimble and weighs less than a grain of rice

Picotaur is less that 1 cm with impressive mobility from its innovative legs.

This Robot Dentist Just Performed Its First Procedure on a Human—Here’s What You Need to Know

The robot dentist can fix your cavities in 15 minutes. But would you trust it?

DeepMind's new AI robot can probably beat you in ping pong

It won't win any Olympic medals just yet, but the robot is probably the best ping-pong machine ever built.

This small robot is the 'jumpiest' ever created — it can jump over Big Ben

This type of robot could help us better explore the moon or Mars.

NASA sends "message in a bottle" onboard spacecraft headed for ocean world

The Clipper's metal plate is much like the Voyager golden records meant to introduce planet Earth and its Earthlings to alien civilizations.

Meet the smallest and fastest robot-insects ever developed

The mini-bug and water strider open up new realms in the field of small robots.

Meet Dragon Firefighter: A robot that uses water to fly

The robot spews water from its body, resembling how dragons are depicted spouting fire from their mouths in movies and books.

Scientists create healing microbots made of human skin cells

Scientists have developed free-swimming biological robots using human tracheal cells. These tiny machines can heal your body from the inside.

This amazing robot will clean your room for you — and will remember what you want

It's all fun and games until the robots start cleaning our rooms.