A team of electrical and computer engineers of the University of California, Los Angeles (UCLA) has created a physical artificial neural network—a device modeled on the working of a human brain.
The university said that the device can analyse large volumes of data and identify objects at the actual speed of light. It was created using a 3-D printer at the UCLA Samueli School of Engineering.
The so-called “diffractive deep neural network” device uses the light bouncing from the object itself to identify that object. According to some media reports, the device uses as little time as it would take for a computer to see the object.
The device does not need advanced computing programmes to process an image of the object and there’s no consumption of energy to run the device as it uses diffraction of light.
The new technologies based on this device can be used to speed up data-intensive tasks that involve sorting and identifying objects by using artificial intelligence. Technology based on the invention could be used in microscopic imaging and medicine.
According to Aydogan Ozcan, the study's principal investigator and the UCLA Chancellor's Professor of Electrical and Computer Engineering, the device 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.
The device was trained by using deep learning, in which machines learn through repetition and over time as patterns emerge.
3-D printing is being used extensively in various disciplines these days including healthcare. It is now being used by doctors to make simulated body parts. In June, reports said that scientists have developed a 3-D printed cornea using human cells.