hardlim returns 0.5 and 1 !!

1 view (last 30 days)
Morteza on 27 Mar 2019
Answered: Garrett Beard on 3 Dec 2021
I have a binarry classification problem with 0-1 classes. I used 3layered neural network with "hardlim" as the activation function of output layer and "tansig" for hidden and input layer. I am wonderfull why my predicted output contains 0.5 and 1 instead of 0-1 !!
Does MATLAB automatically normalizes data when we use it's standard function for NN? Or I should manually normalize data?
Morteza on 25 Feb 2020
Unfortunately No. We can replace 0.5 by 0.

Sign in to comment.

Accepted Answer

Garrett Beard
Garrett Beard on 3 Dec 2021
'net variable'.output.processFcns = {}
By default, the neural network class applies mapminmax to the output vector. Remove the normalization and you will get [0, 1] for outputs.

More Answers (0)

Community Treasure Hunt

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

Start Hunting!