Neho seeks to develop the artificial neuron for AI of the future

Scientists have launched the Neho (Neuromorphic computing Enabled by Heavily doped semiconductor Optics) project aiming to develop an artificial neuron that might become the basis for realizing superfast light-based neural networks in future. The new neural networks will be used to obtain a source of computation with lower energy consumption, making new technologies based on artificial intelligence algorithms more efficient.

The 3 million euro three-year project funded by the European is coordinated by Italy, and specifically by the Italian Institute of Technology in Lecce with the participation of the National Research Council. Other European participants include the Ludwig-Maximilians University of Munich for Germany, the University of Ghent for Belgium, and the CNRS and Paris-Saclay University for France.

"This project allows us to enter a new era of information processing, that is faster, more energy-efficient and more flexible than ever before," says project coordinator Cristian Ciracì, leader of the Computational Nanoplasmonics unit at Iit Lecce.

This paves the way for a new generation of information technologies based on light particles (photons), which are much faster and less energy-consuming. The idea of the project is to use hybrid quasi-particles generated by the interaction of electrons with light: they are called plasmons and are composed of an electron and a photon.