A photonic complex perceptron for ultrafast data processing
Mattia Mancinelli, Davide Bazzanella, Paolo Bettotti, Lorenzo Pavesi

TL;DR
This paper introduces a fully passive, silicon photonic perceptron that uses phase training and multiplexing to perform ultrafast binary pattern recognition and XOR operations at 16 Gbps, advancing optical neural network technology.
Contribution
It presents a novel complex-valued photonic perceptron with phase-only training, combining time and space multiplexing in a scalable silicon photonics chip.
Findings
Performs binary pattern recognition at 16 Gbps
Achieves low bit error rates of 10^{-6}
Uses phase-only training to avoid amplitude attenuation
Abstract
In photonic neural network a key building block is the perceptron. Here, we describe and demonstrate a complex-valued photonic perceptron that combines time and space multiplexing in a fully passive silicon photonics integrated circuit. An input time dependent bit sequence is broadcasted into a few delay lines where the relative phases are trained by particle swarm algorithms toward the given task. Since only the phases of the propagating optical modes are trained, signal attenuation in the perceptron due to amplitude modulation is avoided. The perceptron performs binary pattern recognition and few bit delayed XOR operations up to 16 Gbps (limited by the used electronics) with Bit Error Rates as low as . The perceptron is fully integrated, silicon based, scalable, and can be used as a building block in large neural networks.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
