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

1 次查看（过去 30 天）
Marco Pizzoli
Marco Pizzoli 2021-11-24
评论： Marco Pizzoli 2021-11-25
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

请先登录，再回答此问题。

回答（1 个）

yanqi liu
yanqi liu 2021-11-25
sir，may be it is not suitable，if the inputlayers has rescale，such as transfer to [0, 1]，may be the result can compute

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

产品

Community Treasure Hunt

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

Start Hunting!

Translated by