Literature DB >> 33929404

Adaptive sigmoid-like and PReLU activation functions for all-optical perceptron.

Jasna Crnjanski, Marko Krstić, Angelina Totović, Nikos Pleros, Dejan Gvozdić.   

Abstract

We present an approach for the generation of an adaptive sigmoid-like and PReLU nonlinear activation function of an all-optical perceptron, exploiting the bistability of an injection-locked Fabry-Perot semiconductor laser. The profile of the activation function can be tailored by adjusting the injection-locked side-mode order, frequency detuning of the input optical signal, Henry factor, or bias current. The universal fitting function for both families of the activation functions is presented.

Year:  2021        PMID: 33929404     DOI: 10.1364/OL.422930

Source DB:  PubMed          Journal:  Opt Lett        ISSN: 0146-9592            Impact factor:   3.776


  1 in total

1.  Programmable photonic neural networks combining WDM with coherent linear optics.

Authors:  Angelina Totovic; George Giamougiannis; Apostolos Tsakyridis; David Lazovsky; Nikos Pleros
Journal:  Sci Rep       Date:  2022-04-04       Impact factor: 4.379

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.