conference-paper

All-optical recurrent neural network with sigmoid activation function

Research footprint

At a glance

Citations
7
References
15
Comments
0
Paper overview

Abstract

We demonstrate experimentally, the first all-optical recurrent-neuron with a sigmoid activation function and four WDM-inputs with 100psec pulses. The proposed neuron geared up a neural-network for financial prediction-tasks exhibiting an accuracy of 42.57% on FI-2010.

Record transparency

Publication details

DOI
10.1364/ofc.2020.w3a.5
OpenAlex
W3010570736
Document type
conference-paper
Language
EN
Last metadata update
Community

Comments

Log in to join the discussion.

  1. No comments yet. Start the discussion.