SOURCE-LINKED INTELLIGENCE

Artificial intelligence enabled by automatic dynamic exploration of integrated photonic spiking neural networks

CORDIS · observation · Publication date unknown

Artificial intelligence enabled by automatic dynamic exploration of integrated photonic spiking neural networks In this project (ARIADNE) I will address several key challenges of today’s hardware-based neuromorphic computing by developing a novel AI system based on a highly complex, dynamical and nonlinear integrated photonic neural network that is easy to fabricate and consumes low power. The proposed implementation is enabled by an original machine learning approach which allows to considerably relax the requirements on fabrication reproducibility and on observability and tunability of the network parameters. The AI system is expected to learn to perform multiple complex and time-dependent computational tasks at high speed within a compact device, finding application in real-time control with enhanced cybersecurity (robotics, autonomous vehicles, internet of things, …) and physiologica

Read original source ↗ Open in workspace

recordType

award

status

SIGNED

region

EU

value

188590.08

unit

EUR