R - 神经网络 - 传统的反向传播似乎很奇怪
Posted
技术标签:
【中文标题】R - 神经网络 - 传统的反向传播似乎很奇怪【英文标题】:R - neuralnet - Traditional backprop seems strange 【发布时间】:2016-08-19 03:57:18 【问题描述】:我正在尝试neuralnet
包中的不同算法,但是当我尝试传统的backprop
算法时,结果非常奇怪/令人失望。几乎所有的计算结果都是~.33???我假设我必须错误地使用算法,就好像我使用默认的 rprop+
运行它一样,它确实区分了样本。当然,正常的反向传播并没有那么糟糕,特别是如果它能够如此快速地收敛到提供的阈值。
library(neuralnet)
data(infert)
set.seed(123)
fit <- neuralnet::neuralnet(formula = case~age+parity+induced+spontaneous,
data = infert, hidden = 3,
learningrate = 0.01,
algorithm = "backprop",
err.fct = "ce",
linear.output = FALSE,
lifesign = 'full',
lifesign.step = 100)
preds <- neuralnet::compute(fit, infert[,c("age","parity","induced","spontaneous")])$net.result
summary(preds)
V1
Min. :0.3347060
1st Qu.:0.3347158
Median :0.3347161
Mean :0.3347158
3rd Qu.:0.3347162
Max. :0.3347286
这里的某些设置应该不同吗?
示例默认神经网络
set.seed(123)
fit <- neuralnet::neuralnet(formula = case~age+parity+induced+spontaneous,
data = infert, hidden = 3,
err.fct = "ce",
linear.output = FALSE,
lifesign = 'full',
lifesign.step = 100)
preds <- neuralnet::compute(fit, infert[,c("age","parity","induced","spontaneous")])$net.result
summary(preds)
V1
Min. :0.1360947
1st Qu.:0.1516387
Median :0.1984035
Mean :0.3346734
3rd Qu.:0.4838288
Max. :1.0000000
【问题讨论】:
【参考方案1】:建议您在输入神经网络之前对数据进行标准化。如果你这样做,那么你很高兴:
library(neuralnet)
data(infert)
set.seed(123)
infert[,c('age','parity','induced','spontaneous')] <- scale(infert[,c('age','parity','induced','spontaneous')])
fit <- neuralnet::neuralnet(formula = case~age+parity+induced+spontaneous,
data = infert, hidden = 3,
learningrate = 0.01,
algorithm = "backprop",
err.fct = "ce",
linear.output = FALSE,
lifesign = 'full',
lifesign.step = 100)
preds <- neuralnet::compute(fit, infert[,c("age","parity","induced","spontaneous")])$net.result
summary(preds)
V1
Min. :0.02138785
1st Qu.:0.21002456
Median :0.21463423
Mean :0.33471568
3rd Qu.:0.47239818
Max. :0.97874839
实际上有一些关于 SO 处理这个问题的问题。 Why do we have to normalize the input for an artificial neural network? 似乎有一些最详细的信息。
【讨论】:
有趣,我应该知道缩放。谢谢你。您知道为什么rprop+
算法能够在默认情况下处理此问题而无需缩放?
我不知道 - 我想它在代码中的某个地方是默认完成的,但我不知道为什么会有所不同。
很公平,感谢您回答我的问题。我会四处寻找,也许稍后再问这个问题。以上是关于R - 神经网络 - 传统的反向传播似乎很奇怪的主要内容,如果未能解决你的问题,请参考以下文章