i have problem in ANN
显示 更早的评论
i tried to model an ANN model to predict the behavior of concrete due to sulfate attack but the model cannot predict in out of inputs range.
for instance, i trained the network to predict the concrete behavior at different ages like 10, 100, 500, 1000, and 2000 days. the model can predict the propertie at any time between 10 and 2000 days, but it has a large error at predicting the properties at 20000 days.
采纳的回答
Greg Heath
2013-1-30
编辑：Greg Heath
2013-1-30
0 个投票
This is not exceptional.
NNets are good interpolators but very poor extrapolators.
The basic assumption is that training data has, approximately, the same statistical characteristics as the general population.
Hope this helps.
Thank you for formally accepting my answer.
Greg
2 个评论
Ali
2013-1-30
Greg Heath
2013-2-4
There is no sure way.
You might be able to recognize a particular functional behavior via plots.
However, don't bet the mortgage on guaranteed success.
Greg
更多回答（0 个）
类别
在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
