hardlim returns 0.5 and 1 !!

1 次查看(过去 30 天)
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?
  5 个评论
Hugo Fournier
Hugo Fournier 2020-2-24
Same problem here. Have you found a solution?
Morteza
Morteza 2020-2-25
Unfortunately No. We can replace 0.5 by 0.

请先登录,再进行评论。

采纳的回答

Garrett Beard
Garrett Beard 2021-12-3
'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.

更多回答(0 个)

Community Treasure Hunt

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

Start Hunting!

Translated by