They create an artificial neuron that imitates real ones… but thinks at the speed of light

It’s not the first time. Artificial neurons have already been created that respond to our voice or are capable of reacting to chemical stimuli. But one that fulfilled all the functions… that already seemed almost impossible. At least until now.

A team of scientists from the Chinese University of Hong Kong has developed a laser-based artificial neuron that fully emulates the functions, dynamics and information processing of a biological neuron. Only with a small difference: their signal processing speed is 10 GBaud (one billion times faster than their biological counterparts). In this way, the new laser-graded neuron could lead to advances in fields such as artificial intelligence and other types of advanced computing.

The body contains several types of nerve cells, including graded neurons that encode information through continuous changes in membrane potential, allowing for subtle and precise signal processing. On the contrary, biological spike neurons transmit information using all-or-nothing action potentials, creating a more binary form of communication.

“Our laser-graded neuron overcomes the speed limitations of current photonic versions of spike neurons and has the potential for even faster functioning – explains study leader Chaoran Huang. By taking advantage of its neuron-like nonlinear dynamics and fast processing, we built a reservoir computing system that demonstrates exceptional performance on AI tasks such as pattern recognition and sequence prediction.

The results of this advance have been published in Optica and the study highlights that Thanks to this speed, they were able to process data from 100 million heartbeats or 34.7 million handwritten digital images in just one second..

“Our technology could accelerate AI decision-making in time-critical applications while maintaining high accuracy,” says Huang. We hope that integrating our technology into edge computing devices, which process data close to its source, will facilitate faster, smarter AI systems that better serve real-world applications with reduced power consumption in the future.”

Laser-based artificial neurons, which can respond to input signals in a way that mimics the behavior of biological neurons, are being explored as a way to significantly improve computing thanks to its processing speeds ultra-fast data transmission and low power consumption. However, most of those developed so far have been photon-pulsed neurons. These artificial neurons have a limited response speed, can suffer from information loss, and require additional laser sources and modulators.

“With powerful memory effects and excellent information processing capabilities, a single laser-graded neuron can behave like a small neural network,” adds Huang. Therefore, “Even a single laser-graded neuron without additional complex connections can perform machine learning tasks with high performance.”

In tests, the system showed great ability to recognize and predict long-term patterns and frequencies, in various AI applications with high processing speed. For example, it processed 100 million heartbeats per second and detected arrhythmic patterns with an average accuracy of 98.4%.

“We are working to improve the processing speed of our laser-graded neuron and, at the same time, develop a computing architecture that incorporates laser-graded neurons in cascade,” concludes Huang.