Comparison of Models for Training Optical Matrix Multipliers in Neuromorphic PICs

2021-11-23 · Ali Cem, Siqi Yan, Uiara Celine de Moura, Yunhong Ding, Darko Zibar, Francesco Da Ros

We experimentally compare simple physics-based vs. data-driven neural-network-based models for offline training of programmable photonic chips using Mach-Zehnder interferometer meshes. The neural-network model outperforms physics-based models for a chip with thermal crosstalk, yielding increased testing accuracy.

📄 PDF Abstract BibTeX arXiv:2111.14787

Code (0)

등록된 구현이 없습니다.

Data-driven Modeling of Mach-Zehnder Interferometer-based Optical Matrix Multipliers

2022-10-17 · Ali Cem, Siqi Yan, Yunhong Ding, Darko Zibar 외

Photonic integrated circuits are facilitating the development of optical neural networks, which have the potential to be both faster and more energy efficient than their electronic counterparts since optical signals are …

Data-efficient Modeling of Optical Matrix Multipliers Using Transfer Learning

2022-11-29 · Ali Cem, Ognjen Jovanovic, Siqi Yan, Yunhong Ding 외

We demonstrate transfer learning-assisted neural network models for optical matrix multipliers with scarce measurement data. Our approach uses <10\% of experimental data needed for best performance and outperforms analyt…

Transfer Learning

Event-based Optical Flow on Neuromorphic Processor: ANN vs. SNN Comparison based on Activation Sparsification

2024-07-29 · Yingfu Xu, Guangzhi Tang, Amirreza Yousefzadeh, Guido de Croon 외

Spiking neural networks (SNNs) for event-based optical flow are claimed to be computationally more efficient than their artificial neural networks (ANNs) counterparts, but a fair comparison is missing in the literature. …

Event-based Optical Flow Optical Flow Estimation

Addressing Data Scarcity in Optical Matrix Multiplier Modeling Using Transfer Learning

2023-08-10 · Ali Cem, Ognjen Jovanovic, Siqi Yan, Yunhong Ding 외

We present and experimentally evaluate using transfer learning to address experimental data scarcity when training neural network (NN) models for Mach-Zehnder interferometer mesh-based optical matrix multipliers. Our app…

Transfer Learning

Toward all-optical unsupervised Hebbian learning in deep photonic neuromorphic networks

2026-01-29 · Xi Li, Disha Biswas, Peng Zhou, Wesley H. Brigner 외 arxiv

We propose a deep photonic neuromorphic network (PNN) architecture based on phase-change material (PCM) synapses and local optical feedback for online, unsupervised Hebbian learning. The proposed architecture combines op…