Scalable Photonic Neurons are optical devices that emulate the behavior of biological neurons using light rather than electrical signals. They form the basis of photonic neural networks, which promise ultrafast and energy-efficient computation. Researchers design scalable architectures that allow integration of large numbers of these neurons onto photonic chips. NEC Laboratories America contributes to this research through experiments in optical signal processing and neuromorphic computing. Scalable photonic neurons represent a convergence of photonics and artificial intelligence.
Eric Blow of NEC Labs will address how machine-learning methods applied to distributed acoustic-sensing data can monitor facility perimeters and detect intrusion via walk, dig, or drive events over buried optical fibre—for example achieving ~90% classification accuracy.