Dropout Layer Before Fully connected Layer

Hi guys

I am asking if it is possible to make dropout layer before FC layer

Example below:-

layers = [

imageInputLayer([64 64 3],"Name","imageinput","Normalization","none")

convolution2dLayer([5 5],4,"Name","conv_1","Padding","same")

reluLayer("Name","relu_1")

maxPooling2dLayer([2 2],"Name","maxpool_1","Padding","same","Stride",[2 2])

convolution2dLayer([3 3],8,"Name","conv_2","Padding","same")

reluLayer("Name","relu_2")

maxPooling2dLayer([2 2],"Name","maxpool_2","Padding","same","Stride",[2 2])

convolution2dLayer([3 3],32,"Name","conv_3","Padding","same")

reluLayer("Name","relu_3")

averagePooling2dLayer([2 2],"Name","avgpool2d_1","Padding","same","Stride",[2 2])

convolution2dLayer([3 3],64,"Name","conv_4","Padding","same")

reluLayer("Name","relu_4")

averagePooling2dLayer([2 2],"Name","avgpool2d_2","Padding","same","Stride",[2 2])

dropoutLayer(0.51,'Name','drop1')

fullyConnectedLayer(2,"Name","fc")

softmaxLayer("Name","softmax")

classificationLayer("Name","classoutput")];

Best,

Answer 1

[Shashank Gupta]

Hi Abdussalam,

Yes, you can use Dropout layer before the fully connected layer, Dropout is just a regularization technique for preventing overfitting in the network, it can be applied anywhere regardless of FC or Conv but again it is generally recommended to use it after FC layer because they are the ones with the greater number of parameter and thus they are likely to excessively co-adapting themselves causing Overfitting.

However, it’s a stochastic regularization technique, you can really place it everywhere. Usually placed on the layer with a greater number of parameters, but no denies you from applying anywhere.

[Abdussalam Elhanashi]

Hi Shashank Gupta

Thank For your reply

Is it possibe to use Dropout with value 0.6?

Best,