LEONI is partner in the ADOPD project developing ultrafast fiber-optical computational units based on Adaptive Optical Dendrites

Scientists working on the EU funded program explore the signal processing of neuronal networks. The results will be applied to the realization of optical computational units based on fiber-optical components.

Since October 1st 2020, LEONI is part of a multidisciplinary research group, which is working on new concepts for ultrafast fiber-optical units, a basis of next-generation neuromorphic computing with significantly reduced energy consumption compared to standard computers.

This project named ADOPD has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 899265.

 

As end-user demand increases for ever-faster computing performance for exponentially growing data volumes in applications ranging from smartphones and video games to autonomous vehicles, novel computing devices based on fiber-optic dendrite-inspired systems could prove to be a game-changing technology.

As a leading manufacturer of Optical Fiber Solutions, LEONI develops the required components and evaluates possible application areas within different markets of interest.

The objective of the project will be achieved in various work packages. The existing theories about adaptive signal processing in dendritic branches are expanded to understand the various processes and interactions. This makes it possible to define the requirements for a prototype based on optical technologies. Based on these findings, prototypes will be built characterised by ultra-fast, efficient signal processing. At the beginning, single mode fiber technology is used; in subsequent steps, the systems are expanded to include compact multimode technologies.

Because of its very extensive value chain, LEONI can perfectly support the requirements of the resulting special fiber designs: From fused silica to preform and the fiber drawing process itself, all the relevant factors can be adjusted and optimised at every production step.

Languages
Contact