Skip to main content

Table 1 Hyperparameters considered in the neural architecture search of deep neural networks (DNN)a

From: Would large dataset sample size unveil the potential of deep neural networks for improved genome-enabled prediction of complex traits? The case for body weight in broilers

Hyperparameter

Space

Number of units

1, 100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 2000, 3000, 4000, 5000

Hidden layers

1, 2, 3, 4

Dropout rateb

0.5, 0.6, 0.7, 0.8, 0.9, 1

L2c

0.0000, 0.0025, 0.0050, 0.0075, 0.0100, 0.0125, 0.0150, 0.0175, 0.0200, 0.0225, 0.0250, 0.0275, 0.3000, 0.0325, 0.0350, 0.0375, 0.0400, 0.0425, 0.0450, 0.0475, 0.0500, 0.0525, 0.0550, 0.0575, 0.0600, 0.0625, 0.0650, 0.0675, 0.0700, 0.0725, 0.0750, 0.0775, 0.0800, 0.0825, 0.0850, 0.0875, 0.0900, 0.0925, 0.0950, 0.0975, 0.1000

  1. aThe hyperparameters were randomly select and combined to find the optimal DNN architecture
  2. bThe dropout rate was applied in all layers, except for the output layer
  3. cL2 = ridge regularization
Back to article page

BMC Genomics

ISSN: 1471-2164

Contact us