A team of researchers from Tsinghua University in China has developed a self-driving bicycle outfitted with artificial intelligence, which navigates using a neuromorphic chip.
The researchers envision the Tianjic processor as helping machines respond to vocal commands, recognize their surroundings, evade obstacles, and maintain balance.
The bicycle uses the chip to efficiently run software previously trained for specific tasks vital for battery-powered vehicles.
Researchers hope ultimately to combine the training process with in-the-moment execution, so the bicycle can learn as it goes.
The Chinese scientists view the Tianjic chip as a milestone toward "artificial general intelligence."
The hope is that such chips eventually will allow machines to learn more complex tasks more efficiently, and be more adaptable in executing them.
“That is where we see the big promise,” said Mike Davies, who oversees Intel's efforts to build neuromorphic chips.
From The New York Times
View Full Article - May Require Paid Subscription
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA