Skip to main content

Table 1 The list of the tuned hyperparameters

From: Fast and accurate microRNA search using CNN

HyperparameterProb/pair/mixed matrixOne-hot matrix
Number of convolution layers2, 4, 61
Kernel size for convolution2, 3, 5[8, 16], [4, 8, 12, 16], [2, 4, 6, 8, 10, 12, 14, 16]
  [2, 4, 6, 8, 10, 12, 14, 16]
  [2, 4, 6, 8, 10, 12, 14, 16]
Number of kernels (1st convolution layer)16, 32, 6464, 128, 256, 512
Number of kernels (2nd convolution layer)32, 64, 128not applicable
Pooling methodMax pooling, average pooling 
Number of units (1st fully connected layer)64, 128,256128, 256, 512
Number of units (2nd fully connected layer)32, 64, 128not applicable
Learning algorithmAdam, SGD 
Dropout rate0.7, 0.5