A Computer with Just 2 'Neurons' Can Learn to Ride a Bike

It doesn't take a whole lot of brain to ride a bicycle. In fact, it takes just two neurons — or, to be precise, two nodes on a digital neural network.

Matthew Cook, a researcher at the Institute for Neuroinformatics in Zurich, showed this in a self-published report from 2004, written when he was a professor at the California Institute of Technology. Cook studies thinking — how it works, how it's structured and how it evolves in response to the outside world. Building simple "neural networks" designed to solve specific problems can help researchers model the process of thinking in the brain or move toward smarter artificial intelligence.

To be clear: These neural networks don't involve stringing together any actual neurons. Instead, they're clusters of simulated nodes, or model neurons, on a computer that can interact with one another by strengthening and weakening their connections. These networks have proved remarkably talented at tackling, understanding and solving complex problems even without any information programmed into them in advance. [History of A.I.: Artificial Intelligence (Infographic)]

When Cook built a stripped-down two-node network, he found that, compared with human beings or a sophisticated, dedicated algorithm, it was more talented at piloting a bicycle in a little physics simulator — despite getting no direct information in advance about how to pull it off.

Everyone — algorithm, human or neural network — who tried to pilot the bicycle got the same information and means of control. They could watch the bike's speed, its direction, its position in space, the angle of its handlebars and how far it leaned to one side or another. And they could push and pull on the handlebars and apply a torque to the back wheel that simulated pedaling. Continue Reading.