输出神经元的错误值不正确吗? [英] is error value incorrect for output neurons?

问题描述

我使用完全连接的神经网络进行图像识别"mnist".

I use the fully connected neural network for image recognition "mnist".

我的网络有784个输入神经元，一个隐藏的神经元层包含1569个神经元，一个输出层包含10个神经元.

My network has 784 input neurons, one hidden layer of neurons consists of 1569 neurons, an output layer consists of 10 ones.

我有两个问题:

1. 我使用sigmoid和错误公式=输出*(1-输出)*(目标-输出).问题在于，如果输出神经元为1，且所需值为0，则该错误= 0，但这是错误的，不是吗?

1. I use sigmoid and formula for error error = output * (1 - output) * (target - output). The problem is that if the output neuron is 1, and the required value is 0, that error = 0, but it's wrong, is n't?

如果隐藏层中神经元的加权总和太大而导致结果为1，那么使用S形是正确的吗?什么值初始化权重?

Is it right to use sigmoid if weighted sum of neurons in the hidden layer becomes too large as the result is 1? What values ​​to initialize the weights?

推荐答案

确定还建议您随机初始化权重.通常，它建议您从((−1/√d)，(1√d))范围内选择神经网络的初始权重，其中d是给定神经元的输入数量.

Ok Its suggested you initialize your weights randomly. Typically its suggested you choose initial weights of a neural network from the range ((−1/√d),(1√d)), where d is the number of inputs to a given neuron.

并且错误始终是实际输出-电流输出".您提到的公式与隐藏层权重调整中BPN算法的步骤之一有关.我建议减少模型中隐藏节点的数量.一般建议使隐藏节点的数量少于输入的数量.

And error is always Actual output-Current Output. The formula you mentioned has to do with one of the steps of BPN algorithm in the hidden layer weight adjustment. I would suggest to reduce the number of hidden nodes in your model. Its a general advice to have the number of hidden nodes less then the number of inputs.

S型函数适合您的任务.

And sigmoid function is fine for your task.

这篇关于输出神经元的错误值不正确吗?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！