How to use Neural Network Error as a Feedback Input

4 次查看（过去 30 天）
David Franco
David Franco 2018-2-9
评论： David Franco 2019-6-2
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

请先登录，再回答此问题。

采纳的回答

Waddah Waheeb
Waddah Waheeb 2019-6-1
The code to feed back network error as an input can be downloaded from the following link:
https://github.com/Waddah-Waheeb/RPNN-EF
Hope this helps!
  3 个评论
显示 1更早的评论
Waddah Waheeb
Waddah Waheeb 2019-6-2
编辑：Waddah Waheeb 2019-6-2
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.

请先登录，再进行评论。

更多回答（1 个）

Greg Heath
Greg Heath 2018-2-13
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

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by