在对输入数据进行归一化后，如何对神经网络预测进行归一化(去标准化) [英] How to denormalise (de-standardise) neural net predictions after normalising input data

问题描述

在归一化神经网络的输入数据后，如何返回原始数据比例.用标准偏差法进行归一化. 但是问题已经讨论过了，它属于为每个神经网络输入返回相同的值.我遵循了建议和规范化的数据.是否有非常明显的方法来获取非规范化数据的充分(彼此不同)的预测?

How does one return original data scale after normalising input data for the neural net. Normalising was made with the standard deviation method. But the problem has already discussed, it belongs to returning same values for each neural net input. I've followed the advice and normalised data. Are there very obvious ways how to get adequate (which are different from each other) predictions for non-normalised data?

但是被标准化的输入显示出相对可接受的输出结果(预测).但这似乎导致过度拟合.那么，如何避免过拟合呢?

But being normalised inputs demonstrate relatively acceptable output results (predictions). But it seems to result in overfitting. So, how to avoid overfitting?

推荐答案

如果您还使用以下方法对目标进行了标准化:

If you have also standardized your targets using:

     y - mean(y)
y' = -----------
      stdev(y)

然后您只需解决y的上述问题:

Then you just have to solve the above for y:

y = y' * stdev(y) + mean(y)

并用神经网络的预测替换y.

And replace y with what your neural networks predicts.

对于分类，您不应该将目标标准化.对于回归，您应该.

For classification, you shouldn't standardize the targets. For regression, you should.

您对当前形式中的过度装配部分尚不清楚.

Your question is not clear about the overfitting part in its current form.

这篇关于在对输入数据进行归一化后，如何对神经网络预测进行归一化(去标准化)的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！