Customization of performance function for Neural Network Time-Series Prediction and Modeling in which the target is normalized by external time series values

1 ビュー (過去 30 日間)
Marco Pizzoli
Marco Pizzoli 2021 年 11 月 24 日
コメント済み: Marco Pizzoli 2021 年 11 月 25 日
Dear all,
We are struggling to figure out if it is possible to normalize the target for the performance function involving an external time series.
For instance, given the target t and the estimated output y we can easily obtain the loss function by using Matlab function:
perf = mse(net,t,y);
Now, we ask is it possible to define a new target such that (and therfore ), where x is a function of time that is not used for network training?
% for instance
x = rand(length(t));
y_new = y./x;
t_new = t./x;
my_perf = mse(net, t_new, y_new);
Unfortunately, when training the network we don't manage to provide to mse fucntion and .
Thank you in advance,
Marco and Francesco

回答 (1 件)

yanqi liu
yanqi liu 2021 年 11 月 25 日
sir,may be it is not suitable,if the inputlayers has rescale,such as transfer to [0, 1],may be the result can compute
  1 件のコメント
Marco Pizzoli
Marco Pizzoli 2021 年 11 月 25 日
Thank you for the reply.
However I don't get what you mean.


Community Treasure Hunt

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

Start Hunting!

Translated by