试用软件

hardlim returns 0.5 and 1 !!

5 次查看（过去 30 天）

显示更早的评论

Morteza 2019-3-27

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/452716-hardlim-returns-0-5-and-1

回答： Garrett Beard 2021-12-3

采纳的回答： Garrett Beard

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
显示 3更早的评论隐藏 3更早的评论

Hugo Fournier 2020-2-24

Same problem here. Have you found a solution?

Morteza 2020-2-25

Unfortunately No. We can replace 0.5 by 0.

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

Garrett Beard 2021-12-3

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/452716-hardlim-returns-0-5-and-1#answer_846445

'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.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

更多回答（0 个）

请先登录，再回答此问题。

类别

AI, Data Science, and Statistics Deep Learning Toolbox Function Approximation, Clustering, and Control Function Approximation and Clustering Define Shallow Neural Network Architectures

在 Help Center 和 File Exchange 中查找有关 Define Shallow Neural Network Architectures 的更多信息

标签

Community Treasure Hunt

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

Translated by

试用软件