调整神经网络的大小参数
调整神经网络的大小参数
提问于 2017-12-08 09:16:38
我想用插入符号package.There拟合一个神经网络模型，它们都是重要的，不能被丢弃。我可以给size参数的最大值是4，超过这个值我会得到一个错误，说有太多的权重。
> ctrl<-trainControl(method = 'cv',number = 5)
> my.grid <- expand.grid(.decay = 0.1, .size =5)
> nn.fit <- train(train_predictors,train_responses[["r2c1"]],method = "nnet",algorithm = 'backprop', tuneGrid = my.grid,trace=F, linout = TRUE,trControl = ctrl)
Something is wrong; all the RMSE metric values are missing:
RMSE Rsquared MAE
Min. : NA Min. : NA Min. : NA
1st Qu.: NA 1st Qu.: NA 1st Qu.: NA
Median : NA Median : NA Median : NA
Mean :NaN Mean :NaN Mean :NaN
3rd Qu.: NA 3rd Qu.: NA 3rd Qu.: NA
Max. : NA Max. : NA Max. : NA
NA's :1 NA's :1 NA's :1
Error: Stopping
In addition: Warning messages:
1: model fit failed for Fold1: decay=0.1, size=5 Error in nnet.default(x, y, w, ...) : too many (1051) weights
2: model fit failed for Fold2: decay=0.1, size=5 Error in nnet.default(x, y, w, ...) : too many (1051) weights
3: model fit failed for Fold3: decay=0.1, size=5 Error in nnet.default(x, y, w, ...) : too many (1051) weights
4: model fit failed for Fold4: decay=0.1, size=5 Error in nnet.default(x, y, w, ...) : too many (1051) weights
5: model fit failed for Fold5: decay=0.1, size=5 Error in nnet.default(x, y, w, ...) : too many (1051) weights
6: In nominalTrainWorkflow(x = x, y = y, wts = weights, info = trainInfo, :
There were missing values in resampled performance measures.这个模型在4个神经元(size=4)的情况下表现得非常糟糕，如果我想拥有5个以上的神经元，我可以做些什么来使模型工作吗？(.What)
回答 2
Stack Overflow用户
回答已采纳
发布于 2018-02-13 12:58:28
在优化网格中，还可以为nnet方法指定其他参数。每种方法的可用参数都可以在线获得，但很难找到。下面是我为adam nn使用mxnet的示例：
mxnet_grid_A2 = expand.grid(layer1 = c(10, 12),
layer2 = c(4, 6),
layer3 = 2,
learningrate = c(0.001, 0.0001),
dropout = c(0, 0.2)
beta1 = .9,
beta2 = 0.999,
activation = 'relu')Stack Overflow用户
发布于 2018-06-26 04:16:47
您始终可以使用插入符号train方法中的...可选参数将附加参数传递给底层训练方法(在本例中为nnet)。nnet包的CRAN文档描述了MaxNwts参数，该参数允许控制最大数量的隐藏单元。
页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/47706327
复制相关文章
相似问题