MATLAB Answers

0

How to use Neural Network Error as a Feedback Input

Asked by David Franco on 9 Feb 2018
Latest activity Commented on by David Franco on 2 Jun 2019
Using neural network error as a feedback input helps reduce the overall network error and increase forecasting accuracy ( Wahheb et al. 2016).
How can I supply my Neural Network with its own error?
References:
Waheeb W, Ghazali R, Herawan T (2016) Ridge Polynomial Neural Network with Error Feedback for Time Series Forecasting. PLoS ONE 11(12): e0167248. https://doi.org/10.1371/journal.pone.0167248

  0 Comments

Sign in to comment.

2 Answers

Answer by Waddah Waheeb on 1 Jun 2019
 Accepted Answer

The code to feed back network error as an input can be downloaded from the following link:
Hope this helps!

  3 Comments

This is done automatically during training !!!
So...
WHY DO YOU THINK YOU NEED TO DO THIS ???
Greg
During training, errors are used to update the weights. But in the given code, the past error is used as an input too. Based on the literature in time series forecasting, this type of modelling is used to model nonlinear moving-average processes (e.g., unpredictable events or past shocks) more directly. Please have a look at this link.
Thanks Waddah Waheeb! That's exactly what I needed.

Sign in to comment.


Answer by Greg Heath
on 13 Feb 2018

THAT IS WHAT HAPPENS AUTOMATICALLY WHEN YOU TRAIN THE NET ! SEE THE FIGURE
net = train(net,x,t)
figure
Hope this helps.
Thank you for formally accepting my answer
Greg

  0 Comments

Sign in to comment.