为什么神经网络倾向于输出“均值"? [英] Why neural network tends to output 'mean value'?

问题描述

我正在使用keras为回归任务构建一个简单的神经网络. 但是输出总是趋向于基本事实y数据的均值". 看到第一个数字，蓝色是基本事实，红色是预测值(非常接近基本事实的恒定均值).

I am using keras to build a simple neural network for a regression task. But the output is always tends to the 'mean value' of ground truth y data. See the first figure, blue is ground truth, red is predicted value (very close to the constant mean of ground truth).

即使我将学习时间设置为100，该模型也会很早就停止学习.

Also the model stops learning very early even though I set a learning epoch=100.

在神经网络将在何种条件下停止早期学习以及为什么回归输出趋向于成为基本事实的均值"时，任何人都有想法?

Anyone have ideas under what kinds of conditions the neural network will stop learning early and why the regression output tends to 'the mean' of ground truth?

谢谢！

推荐答案

可能是因为数据不可预测....?您是否确定该数据集具有某种N阶可预测性?

Possibly because the data are unpredictable....? Do you know for certain that the data set has N order predictability of some kind?

只是盯着您的数据集，它缺乏周期性，缺乏同调性，没有任何斜率，偏斜，趋势或模式……我真的不能说出您的网络是否有问题.在没有任何模式的情况下，均值永远是最好的预测……而且神经网络完全有可能(尽管不确定)正在发挥作用.

Just eyeballing your data set, it lacks periodicity, lacks homoscedasticity, it lacks any slope or skew or trend or pattern... I can't really tell if there is anything wrong with your 'net. In the absence of any pattern, the mean is always the best prediction... and it is entirely possible (although not certain) that the neural net is doing its job.

我建议您找到一个更简单的数据集，然后看看是否可以解决该问题.

I suggest you find an easier data set, and see if you can tackle that first.

这篇关于为什么神经网络倾向于输出“均值"?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！