AI device identifies objects at the speed of light
08 August 2018
Using 3D printing, a team of UCLA electrical and computer engineers have created a physical artificial neural that can analyse large volumes of data and identify objects at light-speed.
Numerous devices in everyday life today use computerised cameras to identify objects: consider, for example, automated teller machines that can ‘read’ handwritten cheques, or internet search engines that can quickly match photos to other similar images in their databases. Such systems, however, 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 programs to figure out what it is.
The UCLA-developed device gets a head start. Called a ‘diffractive deep neural network’, it 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 UCLA device does not need advanced computing programs to process an object’s image, before identifying the item in question; plus, no energy is consumed to run the device because it only uses diffraction of light.
New technologies based on the device could be used to expedite data intensive tasks that involve the sorting and identification of objects. For example, a driverless car that uses the technology could react instantaneously – even faster than it does through current technology – to a stop sign.
With a device based on the UCLA system, the car would ‘read’ the sign as soon as the light from the sign hits it, as opposed to experiencing a delay, namely for the car's camera to image the object and then use its programming to decide 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.
The study was published online in Science on the 26th of July.
"This work opens up fundamentally new opportunities to use an artificial intelligence-based passive device to instantaneously analyse data, images and classify objects," said Aydogan Ozcan, the study's principal investigator and the UCLA Chancellor's Professor of Electrical and Computer Engineering.
"This optical artificial neural network device is intuitively modelled on how the brain processes information. It could be scaled up to enable new camera designs and unique optical components that work passively in medical technologies, robotics, security – or any application where image and video data are essential."
More information on the device
The process of creating the artificial neural network began with a computer-simulated design. Then, the researchers used a 3D printer to create very thin, 8 centimetre-square polymer wafers. Each wafer has uneven surfaces, which help diffract light coming from the object in different directions.
The layers look opaque to the eye but submillimetre-wavelength terahertz frequencies of light used in the experiments can travel through them. And each layer is composed of tens of thousands of artificial neurons – in this case, tiny pixels that the light travels through.
Together, a series of pixelated layers functions as an ‘optical network’ that shapes how incoming light from the object travels through them. The network identifies an object because the light coming from the object is mostly diffracted toward a single pixel that is assigned to that type of object.
The researchers then trained the network using a computer to identify the objects in front of it by learning the pattern of diffracted light that each object produces as the light from that object passes through the device. The ‘training’ used a branch of artificial intelligence called deep learning, in which machines ‘learn’ through repetition and over time as patterns emerge.
"This is intuitively like a very complex maze of glass and mirrors," Ozcan said. "The light enters a diffractive network and bounces around the maze until it exits. The system determines what the object is by where most of the light ends up exiting."
Because its components can be created by a 3D printer, the artificial neural network can be made with larger and additional layers, resulting in a device with hundreds of millions of artificial neurons. Those bigger devices could identify many more objects at the same time or perform more complex data analysis. And the components can be made inexpensively: the device created by the UCLA team could be reproduced for less than $50.
While the study used light in the terahertz frequencies, Ozcan said it would also be possible to create neural networks that use visible, infrared or other frequencies of light. A network could also be made using lithography or other printing techniques, he explained.
Contact Details and Archive...