1
$\begingroup$

I tried below code where I used method as 'mxnet':

classifier = train(form = Survived ~ ., data = training_set_scaled, method = 'mxnet')

From this code I got output:

Neural Network 

713 samples
  8 predictor
  2 classes: '0', '1' 

No pre-processing
Resampling: Bootstrapped (25 reps) 
Summary of sample sizes: 713, 713, 713, 713, 713, 713, ... 
Resampling results across tuning parameters:

  layer1  dropout  Accuracy   Kappa       
  1       0.00     0.6220221   0.234515267
  1       0.35     0.6220221   0.234515267
  1       0.70     0.6220221   0.234515267
  3       0.00     0.3931104  -0.002267395
  3       0.35     0.3931104  -0.002267395
  3       0.70     0.3931104  -0.002267395
  5       0.00     0.3798166  -0.119003962
  5       0.35     0.3798166  -0.119003962
  5       0.70     0.3798166  -0.119003962

Tuning parameter 'layer2' was held constant at a value of 0
Tuning

Tuning parameter 'momentum' was held constant at a value of 0.9

Tuning parameter 'activation' was held constant at a value of relu
Accuracy was used to select the optimal model using the largest value.
The final values used for the model were layer1 = 1, layer2 = 0, layer3 =
 0, learning.rate = 2e-06, momentum = 0.9, dropout = 0 and activation = relu.

But the problem with this code is, its not giving high accuracy.

Is there any solution to this to find out the optimal hyperparameter of neural network in R ?

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.