By Theodore Lainas

 

An important achievement in the field of information processing using photonic technology and neural networks is presented by a scientific group of the Department of Informatics of the Aristotle University of Thessaloniki.

 

Researchers have created the world's fastest artificial intelligence processor, which is made up of photonic neurons and runs on light instead of electricity.

 

The processor is based on an original photonic neuron architecture, which allows the implementation of algebraic operations at very high speeds, while at the same time utilizing original neural network training techniques to optimally adapt the algorithms to the special characteristics of light.

 

This combination led to the experimental demonstration of a photonic processor operating at speeds up to 50GHz (25 times faster than the speed of modern GPU processors) with the simultaneous possibility of 10 times lower energy consumption.

 

Aristotle’s University Department of Informatics research highlights the significant speed and energy efficiency advantages provided by the use of light in the implementation of multiplication and addition operations, and allows processors to operate at speeds many times faster than today's corresponding NVIDIA GPU and TPU computing units of Google.

 

The specific scientific field is today a rapidly developing technological branch, which began to be intensively researched about five years ago, with the Informatics Department of the Aristotle University being among the three pioneers, together with two of the leading American universities, the Massachusetts Institute of Technology (MIT) and Princeton University.

 

Their research in the field of photonic neural networks for artificial intelligence applications has attracted significant funding from a number of European Horizon and national research programs, as well as from the American start-up company Celestial AI, which is based in Silicon Valley, California.