Data-efficient Modeling of Optical Matrix Multipliers Using Transfer Learning

Ali Cem; Darko Zibar; Francesco Da Ros; Ognjen Jovanovic; Siqi Yan; Yunhong Ding

arxiv: 2211.16038 · v1 · pith:MEEPQ2IS · submitted 2022-11-29 · cs.LG · cs.ET· cs.NE

Data-efficient Modeling of Optical Matrix Multipliers Using Transfer Learning

Ali Cem , Ognjen Jovanovic , Siqi Yan , Yunhong Ding , Darko Zibar , Francesco Da Ros This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:MEEPQ2IS record.json open to challenge →

classification cs.LG cs.ETcs.NE

keywords datamatrixmodelsmultipliersopticaltransferanalyticalapproach

0 comments

read the original abstract

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 analytical models for a Mach-Zehnder interferometer mesh.

This paper has not been read by Pith yet.

Data-efficient Modeling of Optical Matrix Multipliers Using Transfer Learning

discussion (0)