Improve Research Reproducibility A Bio-protocol resource
Concise Method
tooltip

Training of the rRNN

BM Bicky A. Marquez
LL Laurent Larger
MJ Maxime Jacquot
YC Yanne K. Chembo
DB Daniel Brunner
request Request a Protocol
ask Ask a question
Favorite

For the training step we use 2000 values from the MG system and α = 0.830,32,33. The training target is equivalent to the input signal, shifted by a single time step. Via the teacher we estimate the optimal output weight vector Wopout

via its pseudo-inverse according to singular value decomposition. Equation (3) therefore minimizes the error between output tanh(Wout ⋅ xn +1) and teacher yn+1T. As training error measure we use the normalized mean squared error (NMSE) between output yn+1out and target signal yn+1T, normalized by the variance of teacher signal yn+1T:

where σ is the standard deviation.

Copyright and License information: The Author(s) ©2018
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.

Do you have any questions about this protocol?

Post your question to gather feedback from the community. We will also invite the authors of this article to respond.

0/150

tip Tips for asking effective questions

+ Description

Write a detailed description. Include all information that will help others answer your question including experimental processes, conditions, and relevant images.

post Post a Question
0 Q&A