前馈神经网络中的错误检查 [英] Error check in Feedforward Neural Network

问题描述

我的网络错误是否有可能减少，然后又增加?只是想检查我是否编码正确.

Is it possible that the error for my network decreases, then increase again? Just wanna check if i'm coding the right way.

推荐答案

是的，错误可能会暂时增加.这是因为您不是一直在测试一个输入和预期的输出(并且您不应该测试，因为那样网络将专用于该特定的输入-输出集).神经网络不会隐式知道"它正在朝着正确的方向前进.您基本上是遍历错误表面，以找到错误低于特定阈值的位置.因此绝对有可能在特定时期内增加错误，但是 overall ，随着反向传播根据错误调整权重，您的错误率应该会降低.

Yes, it is possible for the error to temporarily increase. This is because you aren't testing one input and expected output all the time (and you shouldn't, because then the network will be specialized for that particular input-output set). The neural network does not implicitly "know" that it is going in the right direction. You are basically traversing the error surface to find a location where the error is below a certain threshold. So it is definitely possible for the error to increase in a particular epoch, but overall, your error rate should be decreasing as the backpropagation adjusts the weights in accordance with the error.

例如，假设您正在尝试创建一个可以识别数字的神经网络.因此，您将净输入输入为"1"，并输入期望的输出.输出不匹配，因此您需要调整权重.因此，这意味着网络在识别"1"时将具有较低的误差.但是下一个输入可能是"4"，而"4"的误差可能更大，因此网络将再次进行自我调整.关键是找到一种权重的快乐媒介"，使它们能够识别输入并在一定的误差阈值内提供适当的输出.

For example, assume that you are trying to create a neural network that can recognize digits. So you feed the net inputs for a "1" and the expected output. The output doesn't match, and so you adjust the weights. So this means that the net will have a lower error for recognizing a "1". But the next input could be a "4", and the error for a "4" could be greater and so the net will again adjust itself. The point is to find a "happy medium" of sorts for the weights such that they recognize the input and provide the appropriate output within a certain error threshold.

但是，我不确定您所说的先减少，然后增加，直到最后一个纪元"是什么意思.您是仅针对特定时期进行训练，还是在网络达到特定错误阈值之前进行训练?

However, I am not sure what you mean by "decreases, and then increases until the last epoch". Are you only training for a certain number of epochs, or are you training until your network reaches a certain error-threshold?

这篇关于前馈神经网络中的错误检查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！