Normalisation of matrices using mapminmax function

12 views (last 30 days)
i tried to normalise the input and target matrices for load forecasting using the below code.
p and t aretaken as original input and target matrices .
[pn,ps] = mapminmax(p);
[tn,ts] = mapminmax(t);
After using this code, which matrix should i use as input and target while uploading data using NNFit tool in matlab?
pn and tn should be used as input and target matrices for nnfir tool?if so where do we use ps and ts and what s its purpose during neural network training procedure.?

Answers (1)

Srivardhan Gadila
Srivardhan Gadila on 31 Oct 2020
As mentioned in the documentation of mapminmax under the Normalize Inputs and Targets Using mapminmax section,
"The normalized inputs and targets pn and tn that are returned will all fall in the interval [–1,1] should be used for the network. The structures ps and ts contain the settings, in this case the minimum and maximum values of the original inputs and targets. After the network has been trained, the ps settings should be used to transform any future inputs that are applied to the network and the ts settings is used to convert the outputs back into the same units that were used for the original targets. They effectively become a part of the network, just like the network weights and biases."

Tags

Community Treasure Hunt

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

Start Hunting!