3D Printed Artificial Neural Network to be Used in Medicine, Robotics and Security


Artificial neural network doesn’t need advanced computing programs to process an image of the object rather uses bouncing light from the object to identify it

Electrical and computer engineers at UCLA Samueli School of Engineering have created an artificial neural network using a 3D printer which works on the principle of the human brain. These artificial networks can analyse the large volume of data and identify objects at the actual speed of light.

Technology to speed up data-intensive tasks

The UCLA developed device gets a head start. It is called a diffractive deep neural network, which 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 does not need advanced computing programs to process an image of the object and decide what the object is after its optical sensors pick it up. Additionally, no energy is consumed to run the device because it only uses diffraction of light.

So new technologies based on this device can be used to speed up data-intensive tasks that involve sorting and identifying objects. For example, a driverless car using the technology could react faster than it does use 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.

Hence, it can 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.

Process to create an artificial neural network

The process of creating the artificial neural network began with a computer-simulated design. Then, the researchers used a 3D printer to create 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 submillimeter-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 that are actually the tiny pixels through which the light travels.

Together, a series of pixelated layers function 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 towards 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. 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.

Since 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.