Self-Normalizing Neural Network, Enabling One Shot Transfer Learning for Modeling EDFA Wavelength Dependent Gain

Agastya Raj; Zehao Wang; Frank Slyne; Tingjun Chen; Dan Kilper; Marco Ruffini

Self-Normalizing Neural Network, Enabling One Shot Transfer Learning for Modeling EDFA Wavelength Dependent Gain

Networking and Internet Architecture 2023-10-24 v2 Machine Learning

Authors: Agastya Raj , Zehao Wang , Frank Slyne , Tingjun Chen , Dan Kilper , Marco Ruffini

Abstract

We present a novel ML framework for modeling the wavelength-dependent gain of multiple EDFAs, based on semi-supervised, self-normalizing neural networks, enabling one-shot transfer learning. Our experiments on 22 EDFAs in Open Ireland and COSMOS testbeds show high-accuracy transfer-learning even when operated across different amplifier types.

Keywords

extreme learning machine deep learning

Cite

@article{arxiv.2308.02233,
  title  = {Self-Normalizing Neural Network, Enabling One Shot Transfer Learning for Modeling EDFA Wavelength Dependent Gain},
  author = {Agastya Raj and Zehao Wang and Frank Slyne and Tingjun Chen and Dan Kilper and Marco Ruffini},
  journal= {arXiv preprint arXiv:2308.02233},
  year   = {2023}
}

Comments

This paper is a preprint of a paper submitted to ECOC 2023 and is subject to Institution of Engineering and Technology Copyright. If accepted, the copy of record will be available at IET Digital Library

Self-Normalizing Neural Network, Enabling One Shot Transfer Learning for Modeling EDFA Wavelength Dependent Gain

Abstract

Keywords

Cite

Comments

Related papers