试用软件

How can set a target value of a error of 0.001 between my target values, output values of trained neural network?

6 次查看（过去 30 天）

显示更早的评论

PRAVEEN REDDY KANTHALA 2017-5-30

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/342598-how-can-set-a-target-value-of-a-error-of-0-001-between-my-target-values-output-values-of-trained-ne

评论： PRAVEEN REDDY KANTHALA 2017-5-31

采纳的回答： Greg Heath

How can I set a target value of a error of 0.001 between my target values, output values of trained neural network?

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。

请先登录，再回答此问题。

采纳的回答

Greg Heath 2017-5-31

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/342598-how-can-set-a-target-value-of-a-error-of-0-001-between-my-target-values-output-values-of-trained-ne#answer_268989

编辑：Greg Heath 2017-5-31

msegoal = 0.001*mean(var(target',1))

This results in a Rsquare of 99.9%

Hope this helps.

Greg

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

PRAVEEN REDDY KANTHALA 2017-5-31

What is difference between performance and mse? If both are same,then why I am getting different values for performance when I have a target of 0.001. however the above code sent by you is not creating a error of 0.001. I have tested using a sample data for which I already have outputs.i have found the difference between nn outputs and these outputs but difference is too large up to .6. Am I missing something? Please help.

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 and Statistics Deep Learning Toolbox

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 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