Neuromorphic photonic networks using silicon photonic weight banks

By Alexander N. Tait, T. F. de Lima, E. Zhou, A. Wu, Mitchell A. Nahmias, Bhavin J. Shastri, Paul R. Prucnal. Scientific Reports, 2016

788 citations recorded by the source corpus.

Photonic systems for high-performance information processing have attracted renewed interest. Neuromorphic silicon photonics has the potential to integrate processing functions that vastly exceed the capabilities of electronics. We report first observations of a recurrent silicon photonic neural network, in which connections are configured by microring weight banks. A mathematical isomorphism between the silicon photonic circuit and a continuous neural network model is demonstrated through dynamical bifurcation analysis. Exploiting this isomorphism, a simulated 24-node silicon photonic neural network is programmed using “neural compiler” to solve a differential system emulation task. A 294-fold acceleration against a conventional benchmark is predicted. We also propose and derive power consumption analysis for modulator-class neurons that, as opposed to laser-class neurons, are compatible with silicon photonic platforms. At increased scale, Neuromorphic silicon photonics could access new regimes of ultrafast information processing for radio, control, and scientific computing.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/e7e5d0e8f13dd8f74f6ffb16f5a32ca490fa2f5e

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

Photonics for artificial intelligence and neuromorphic computing (2020, methodology): “ver, that matching particular transfer function shapes is not necessary: neural training and programming techniques can be adapted to transfer functions naturally exhibited by analog photonic devices [18,30,62]. All-optical neurons do not ever represent the neuron signal as an electrical current but”
Deep Neural Network Inverse Design of Integrated Photonic Power Splitters (2019, methodology): “It has received some attention in optical community and there has been several recent work on reverse modeling for design of nano-structured optical components using DNN [19-25], as well as hardware implementation of an artificial neural network [26-30].”
Experimental investigation of performance differences between coherent Ising machines and a quantum annealer (2018, background): “zation to the underlying physical dynamics. Examples include digital CMOS annealers [6, 7], as well as analog devices such as nano-magnet arrays [8], electronic oscillators [9, 10] and laser networks [11]. Quantum adiabatic computation [12] and quantum annealing [13, 14, 15, 16] are also prominent e”
Review of Silicon Photonics Technology and Platform Development (2021, background): “actively explored, with SiP-based QKD networks [134], [135], artificial neural network and optical computing [136], [137] already being demonstrated.”
Large-Scale Optical Neural Networks based on Photoelectric Multiplication (2018, methodology): “This encoding, reminiscent of the Coherent Ising Machine [28, 29, 30], contrasts with other approaches used for neural networks, which encode inputs in separate spatial channels [23, 24, 22].”
Inference in artificial intelligence with deep optics and photonics (2020, methodology): “Micro-ring weight banks were also used by Tait et al. 34 to implement a recurrent silicon photonic neural network.”