Google AI program DeepMind learns human navigation skills

Avatar By Le Williams | 3 years ago

The latest program from Google’s artificial intelligence group, DeepMind, has overwhelmed experts at a maze game, subsequent to learning human geography skills.

Scientists observed AI training processes resulted in independent moving actions through landscapes, spontaneously developing electrical activity similar to that seen in the specialized brain cells of a human’s navigational skills. Notably, these ‘grid cells’ were only identified in animals in 2005 in work that earned researchers a Nobel prize.

The latest breakthrough reveals the potential for human brain-like activity to emerge in AI systems. The innovation opens opportunities for computer engineers to build models that support neuroscientists success in understanding the human brain.

After discovering the AI-made grid cells, the DeepMind researchers made a superior version of the program. DeepMind triumphed over experienced players at a game that involved racing through rooms to find a prize after being dropped into the virtual environment at a random location. Equipped with the artificial grid cells, the AI was faster and found shortcuts that would occasionally crop up when doors in the environment suddenly opened.

“It is doing the kinds of things that animals do and that is to take direct routes wherever possible and shortcuts when they are available,” said Dharshan Kumaran, a senior researcher at DeepMind. “With the grid cells, its performance is markedly enhanced to the point that it surpasses an expert human player.”

The feat marks a milestone in the field of artificial intelligence. Until now the technology used has proved itself to be superhuman at object recognition and games such as chess, Go, and poker, but not at the very different cognitive challenge of efficient navigation.