Neuromorphic photonic networks using silicon photonic weight banks

TLDR

Photonic systems for high‑performance information processing have attracted renewed interest, and neuromorphic silicon photonics promises to integrate processing functions that vastly exceed electronic capabilities, potentially accessing new regimes of ultrafast information processing for radio, control, and scientific computing. The authors report first observations of a recurrent silicon photonic neural network, in which connections are configured by microring weight banks. They simulate a 24‑node silicon photonic neural network programmed via a neural compiler to solve a differential system emulation task, and propose a power‑consumption analysis for modulator‑class neurons compatible with silicon photonic platforms. They demonstrate a mathematical isomorphism between the silicon photonic circuit and a continuous neural network model via dynamical bifurcation analysis, and predict a 294‑fold acceleration over conventional benchmarks.

Abstract

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.