Saved in:
Bibliographic Details
Main Authors: Liu, Yi-Feng, Ren, Rui-Yao, Hou, Dai-Bao, Weng, Hai-Zhong, Wang, Bo-Wen, Huang, Ke-Jie, Lin, Xing, Liu, Feng, Li, Chen-Hui, Jin, Chao-Yuan
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2308.14015
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917602103656448
author Liu, Yi-Feng
Ren, Rui-Yao
Hou, Dai-Bao
Weng, Hai-Zhong
Wang, Bo-Wen
Huang, Ke-Jie
Lin, Xing
Liu, Feng
Li, Chen-Hui
Jin, Chao-Yuan
author_facet Liu, Yi-Feng
Ren, Rui-Yao
Hou, Dai-Bao
Weng, Hai-Zhong
Wang, Bo-Wen
Huang, Ke-Jie
Lin, Xing
Liu, Feng
Li, Chen-Hui
Jin, Chao-Yuan
contents Due to their intrinsic capabilities on parallel signal processing, optical neural networks (ONNs) have attracted extensive interests recently as a potential alternative to electronic artificial neural networks (ANNs) with reduced power consumption and low latency. Preliminary confirmation of the parallelism in optical computing has been widely done by applying the technology of wavelength division multiplexing (WDM) in the linear transformation part of neural networks. However, inter-channel crosstalk has obstructed WDM technologies to be deployed in nonlinear activation in ONNs. Here, we propose a universal WDM structure called multiplexed neuron sets (MNS) which apply WDM technologies to optical neurons and enable ONNs to be further compressed. A corresponding back-propagation (BP) training algorithm is proposed to alleviate or even cancel the influence of inter-channel crosstalk on MNS-based WDM-ONNs. For simplicity, semiconductor optical amplifiers (SOAs) are employed as an example of MNS to construct a WDM-ONN trained with the new algorithm. The result shows that the combination of MNS and the corresponding BP training algorithm significantly downsize the system and improve the energy efficiency to tens of times while giving similar performance to traditional ONNs.
format Preprint
id arxiv_https___arxiv_org_abs_2308_14015
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Slimmed optical neural networks with multiplexed neuron sets and a corresponding backpropagation training algorithm
Liu, Yi-Feng
Ren, Rui-Yao
Hou, Dai-Bao
Weng, Hai-Zhong
Wang, Bo-Wen
Huang, Ke-Jie
Lin, Xing
Liu, Feng
Li, Chen-Hui
Jin, Chao-Yuan
Signal Processing
Hardware Architecture
Due to their intrinsic capabilities on parallel signal processing, optical neural networks (ONNs) have attracted extensive interests recently as a potential alternative to electronic artificial neural networks (ANNs) with reduced power consumption and low latency. Preliminary confirmation of the parallelism in optical computing has been widely done by applying the technology of wavelength division multiplexing (WDM) in the linear transformation part of neural networks. However, inter-channel crosstalk has obstructed WDM technologies to be deployed in nonlinear activation in ONNs. Here, we propose a universal WDM structure called multiplexed neuron sets (MNS) which apply WDM technologies to optical neurons and enable ONNs to be further compressed. A corresponding back-propagation (BP) training algorithm is proposed to alleviate or even cancel the influence of inter-channel crosstalk on MNS-based WDM-ONNs. For simplicity, semiconductor optical amplifiers (SOAs) are employed as an example of MNS to construct a WDM-ONN trained with the new algorithm. The result shows that the combination of MNS and the corresponding BP training algorithm significantly downsize the system and improve the energy efficiency to tens of times while giving similar performance to traditional ONNs.
title Slimmed optical neural networks with multiplexed neuron sets and a corresponding backpropagation training algorithm
topic Signal Processing
Hardware Architecture
url https://arxiv.org/abs/2308.14015