# Modeling Silicon-Photonic Neural Networks under Uncertainties

arXiv: https://arxiv.org/abs/2012.10594 · HTML: https://mlsanity.com/paper/2012.10594/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2020.

## Built on by (most cited first, 7 of 7)

- [A compact butterfly-style silicon photonic-electronic neural chip for hardware-efficient deep learning](https://mlsanity.com/paper/2111.06705/) (2021)
- [SONIC: A Sparse Neural Network Inference Accelerator with Silicon Photonics for Energy-Efficient Deep Learning](https://mlsanity.com/paper/2109.04459/) (2021)
- [Characterizing Coherent Integrated Photonic Neural Networks under Imperfections](https://mlsanity.com/paper/2207.10835/) (2022)
- [Pruning Coherent Integrated Photonic Neural Networks Using the Lottery Ticket Hypothesis](https://mlsanity.com/paper/2112.07485/) (2021)
- [Analysis of Optical Loss and Crosstalk Noise in MZI-based Coherent Photonic Neural Networks](https://mlsanity.com/paper/2308.03249/) (2023)
- [Thermal Crosstalk Modelling and Compensation Methods for Programmable Photonic Integrated Circuits](https://mlsanity.com/paper/2404.10589/) (2024)
- [LuxIA: A Lightweight Unitary matriX-based Framework Built on an Iterative Algorithm for Photonic Neural Network Training](https://mlsanity.com/paper/2512.22264/) (2025)

## Abstract (arXiv)

Silicon-photonic neural networks (SPNNs) offer substantial improvements in computing speed and energy efficiency compared to their digital electronic counterparts. However, the energy efficiency and accuracy of SPNNs are highly impacted by uncertainties that arise from fabrication-process and thermal variations. In this paper, we present the first comprehensive and hierarchical study on the impact of random uncertainties on the classification accuracy of a Mach-Zehnder Interferometer (MZI)-based SPNN. We show that such impact can vary based on both the location and characteristics (e.g., tuned phase angles) of a non-ideal silicon-photonic device. Simulation results show that in an SPNN with two hidden layers and 1374 tunable-thermal-phase shifters, random uncertainties even in mature fabrication processes can lead to a catastrophic 70% accuracy loss.