Feedforward Neural Network - Model Optimization #3
Using keras (python deep learning library), I am trying to find the best neural network model structure.
Searched combinations:
n_hidden_layers = 3 or 4
neurons_in_layer = 64 or 128
dropout = 0 or 0.5
activation_function = relu or selu
Fixed values:
model_optimizer = Adam
learning_rate = 0.001
max_epochs = 300
batch_size = 96
model_loss = sparse_categorical_crossentropy
kernel_regularizer_per_layer = L1
early_stopping = val_loss ; patience = 20
model configurations: 4608
searched time: 7h14m17s
BEST Result
Epoch 249/300:
loss: 0.5427 - accuracy: 0.9566
val_loss: 0.5808 - val_accuracy: 0.9405
Using 784 samples for training and 336 for validation
Comments
Post a Comment