Networks of electronic neurons and synapses could revolutionize AI.
(Photo: Moment/Getty Images)
Munich, Paris Alice Mizrahi bases her work on artificial intelligence (AI) on the core of human intelligence: “Our inspiration is the way the brain works with nerve cells and synapses,” says Mizrahi, who was developed by a joint laboratory of the French research organization CNRS and the Thales Group in a suburb of Paris.
“A lot of people look at artificial intelligence in terms of algorithms that rely on classic computer chips,” she says. “We are working on neuromorphic chips that are modeled on a network of nerve cells.”
The hope is that by the end of the decade, a technology will be in use whose computing power consumes much less energy than previous AI processes. European companies like Thales are at the forefront of development – the next generation of AI semiconductors could come from Europe and break the market power of the US group Nvidia.
Artificial intelligence: turning away from the classic chip architecture
Read on now
Get access to this and every other article in the
Web and in our app free of charge for 4 weeks.
Further
Read on now
Get access to this and every other article in the
web and in our app.
Further