Artificial Intelligence is “Strikingly Similar to Brain Cells”
Neuroscientists in London have learned that artificial intelligence (AI) navigates in a way that resembles the working of a human brain.
The electronic components of their “artificial agent” demonstrate an activity pattern remarkably similar to the firing of specialist neurons that have evolved to help animals find their way around the world. The results have been published by scientists at DeepMind, and the University of College London, in the journal Nature.
Despite the project having no immediate applications, they said, the results add important insights into both artificial and biological intelligence.
“It makes sense to look to neuroscience as a source of inspiration for new types of AI algorithms,” explained Demis Hassabis, DeepMind chief executive. “But we believe that this inspiration should be a two-way-street, with insights also flowing back from AI research to shed light on open questions in neuroscience. This work is a good example.”
The discovery of specialist neurons called grid cells in 2005, were at the heart of the project, which fire in a hexagonal pattern as animals explore their environment. These cells generate a system of coordinates in the brain, similar to hexagonal grid lines on a map, allowing for GPS-like positioning and navigation.
The aim of the project is to investigate the computational functions of grid cells – how they enable the brain to calculate the distance and direction to the desired destination – which has remained a mystery in neuroscience.
In a bid to seek answers, the researchers built a computer network that simulated the movements of rodents navigating through simple mazes, using an AI technique, called deep reinforcement learning. They found that patterns of activity were similar to biological grid cells “spontaneously emerged within the network, providing a striking convergence with the neural activity patterns observed in foraging mammals.”
“The emergence of grid-like units is an impressive example of deep learning doing what it does best: inventing an original, often unpredicted internal representation to help solve a task,” noted Francesco Savelli and James Knierim, neuroscientists at Johns Hopkins Univerisity, Maryland.
Caswell Barry, UCL neuroscientist, added, “This agent performed at a super-human level, exceeding the ability of a professional game player, and exhibited the type of flexible navigation normally associated with animals, taking novel routes and shortcuts when they became available.”
Taking into consideration the project’s success, Barry expects AI to be used to test other ideas for how the brain works, for example how it perceives sound or moves limbs. “In future, such networks may well provide a new way for scientists to conduct “experiments”, suggesting new theories and even replacing some of the work that is currently conducted in animals,” he concluded.