The story appears on

Page A11

May 13, 2018

GET this page in PDF

Free for subscribers

View shopping cart

Related News

Home » Sunday » Technology

Self-navigating AI learns shortcuts

A computer program modelled on the human brain learnt to navigate a virtual maze and take shortcuts, outperforming a flesh-and-blood expert, its developers said Wednesday.

While artificial intelligence programs have recently made great strides in imitating human brain processing — everything from recognizing objects to playing complicated board games — spatial navigation has remained a challenge.

It requires the recalculation of one’s position, after each step taken, in relation to the starting point and destination — even when traveling a never-before-taken route.

Navigation is considered a complex behavioral task, and in animals it is partly controlled by a sort of onboard GPS driven by “grid cells” in the brain’s hippocampus region.

These cells have been observed firing in a regular pattern as mammals explore a new environment.

In a new study published in the journal Nature, AI researchers said they had developed a “deep neural network,” or computer “brain,” which they trained to navigate toward a goal in a virtual maze.

When shortcuts were introduced, by opening a previously blocked opening for example, the AI automatically took the shorter route.

Furthermore, the computer “brain” generated navigational grids strikingly similar to those observed in the brains of foraging mammals, said the team.

The program “performed at a super-human level, exceeding the ability of a professional game player,” three of the study authors said in a press statement.

It “exhibited the type of flexible navigation normally associated with animals, taking novel routes and shortcuts when they became available.”

Most of the researchers are attached to DeepMind, the British AI company that also created AlphaGo, the self-trained computer that beat human champions at the Chinese board game “Go” said to require intuition rather than brute processing power to prevail.

The team said their work was “an important step in understanding the fundamental computational purpose of grid cells in the brain.”

The discoverers of grid cells were awarded the Nobel Prize for Medicine in 2014.

(AFP)




 

Copyright © 1999- Shanghai Daily. All rights reserved.Preferably viewed with Internet Explorer 8 or newer browsers.

沪公网安备 31010602000204号

Email this to your friend