插入符号::序列:为mlpWeightDecay(RSNNS包)指定进一步的非调优参数
我在使用RSNNS包中的方法“mlpWeightDecay”的插入符号包指定学习速率时遇到问题。 “mlpWeightDecay”的调谐参数是大小和衰减 将尺寸常数保持在4并在c(0,0.0001,0.001,0.002)上调谐衰减的示例:插入符号::序列:为mlpWeightDecay(RSNNS包)指定进一步的非调优参数,r,machine-learning,neural-network,r-caret,R,Machine Learning,Neural Network,R Caret,我在使用RSNNS包中的方法“mlpWeightDecay”的插入符号包指定学习速率时遇到问题。 “mlpWeightDecay”的调谐参数是大小和衰减 将尺寸常数保持在4并在c(0,0.0001,0.001,0.002)上调谐衰减的示例: 数据(iris) TrainData看起来您可以在“…”中指定自己的learnFuncParams。插入符号检查您是否提供了自己的参数集,并且只覆盖learnFuncParams[3](这是衰减)。它将使用您提供的learnFuncParams[1,2,4]
数据(iris)
TrainData看起来您可以在“…”中指定自己的learnFuncParams。插入符号检查您是否提供了自己的参数集,并且只覆盖learnFuncParams[3](这是衰减)。它将使用您提供的learnFuncParams[1,2,4]
找到插入符号的一种非常方便的方法是键入getModelInfo(“mlpWeightDecay”),然后向上滚动到$mlpWeightDecay$fit部分。它显示了caret将如何调用真正的培训功能:
$mlpWeightDecay$fit
if (any(names(theDots) == "learnFuncParams")) {
prms <- theDots$learnFuncParams
prms[3] <- param$decay
warning("Over-riding weight decay value in the 'learnFuncParams' argument you passed in. Other values are retained")
}
$mlpWeightDecay$fit
如果(任何(名称(点)=“learnFuncParams”)){
prms我也在努力解决这个问题。汉娜,你有没有发现?
fit1 <- train(TrainData, TrainClasses,
method = "mlpWeightDecay",
preProcess = c("center", "scale"),
tuneGrid=expand.grid(.size = 4, .decay = c(0,0.0001, 0.001, 0.002)),
trControl = trainControl(method = "cv"),
learnFuncParams=c(0.4,0,0,0)
)
$mlpWeightDecay$fit
if (any(names(theDots) == "learnFuncParams")) {
prms <- theDots$learnFuncParams
prms[3] <- param$decay
warning("Over-riding weight decay value in the 'learnFuncParams' argument you passed in. Other values are retained")
}