New AI device can identify objects at the speed of light
The artificial
neural network have applications in medicine, robotics and security
Scientists have created
a 3D printed artificial neural network — a device modelled on how the human
brain works — which can analyse large volumes of data and identify objects at
the speed of light.
Several devices in everyday life use computerised
cameras to identify objects, such as internet search engines that can quickly
match photos to other similar images, says researchers at the University of
California, Los Angeles.
However, those systems rely on a piece of equipment
to image the object, first by ‘seeing’ it with a camera or optical sensor, then
processing what it sees into data, and finally using computing programmes to
figure out what it is.
Identifying object in no time
The new device, called a ‘diffractive deep neural
network’, uses the light bouncing from the object itself to identify that
object in as little time as it would take for a computer to simply ‘see’ the
object.
The device, described in the journal Science,
does not need advanced computing programmes to process an image of the object
and decide what the object is after its optical sensors pick it up. No energy
is consumed to run the device because it only uses diffraction of light,
researchers says.
Speed up data-intensive tasks
New technologies based on the device could be used to
speed up dataintensive tasks that involve sorting and identifying objects. For
example, a driverless car using the technology could react instantaneously —
even faster than it does using current technology — to a stop sign.
With a device based on the system, the car would
‘read’ the sign as soon as the light from the sign hits it, as opposed to
having to ‘wait’ for the car’s camera to image the object and then use its
computers to figure out what the object is.
Technology based on the invention could also be used
in microscopic imaging and medicine, for example, to sort through millions of
cells for signs of disease, researchers say.
— PTI
No comments:
Post a Comment