An optical neural chip for implementing complex-valued neural network

By H. Zhang, M. Gu, X. D. Jiang, J. Thompson, H. Cai, S. Paesani, R. Santagati, A. Laing, Y. Zhang, Man-Hong Yung and 8 more. Nature Communications, 2021

585 citations recorded by the source corpus.

Complex-valued neural networks have many advantages over their real-valued counterparts. Conventional digital electronic computing platforms are incapable of executing truly complex-valued representations and operations. In contrast, optical computing platforms that encode information in both phase and magnitude can execute complex arithmetic by optical interference, offering significantly enhanced computational speed and energy efficiency. However, to date, most demonstrations of optical neural networks still only utilize conventional real-valued frameworks that are designed for digital computers, forfeiting many of the advantages of optical computing such as efficient complex-valued operations. In this article, we highlight an optical neural chip (ONC) that implements truly complex-valued neural networks. We benchmark the performance of our complex-valued ONC in four settings: simple Boolean tasks, species classification of an Iris dataset, classifying nonlinear datasets (Circle and Spiral), and handwriting recognition. Strong learning capabilities (i.e., high accuracy, fast convergence and the capability to construct nonlinear decision boundaries) are achieved by our complex-valued ONC compared to its real-valued counterpart. Most demonstrations of optical neural networks for computing have been so far limited to real-valued frameworks. Here, the authors implement complex-valued operations in an optical neural chip that integrates input preparation, weight multiplication and output generation within a single device.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/ad583c91a7fca99eea8b1133af0e9af01e69ef68

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

Space-efficient optical computing with an integrated chip diffractive neural network (2022, unknown): “Typical silicon PIC architectures to realize chip-scale ONNs 7 – 15 use cascades of multiple Mach – Zehnder interferometers (MZIs) 7 – 13 and microring resonator-based wavelength division multiplexing technology 14,15 .”
Experimentally realized in situ backpropagation for deep learning in photonic neural networks (2022, methodology): “We implement both amplitude and phase detection (improving on past approaches [19]) using a self-configuring programmable Matrix unit layer [20, 23] on both the red and blue Generator and Analyzer subcircuits of Fig.”
Photonic matrix multiplication lights up photonic accelerator and beyond (2022, methodology): “12c, the input vectors were loaded on beams with different wavelengths and weighted by PCMs.”