encoder_small: Network small
In scAlign: An alignment and integration method for single cell genomics

Defines network architecture for scAlign.

1
2
3

encoder_small(inputs, input_size = NULL, complexity = 3,
  emb_size = 32, l2_weight = 1e-04, dropout = TRUE,
  dropout_rate = 0.3, is_training = TRUE, batch_norm = TRUE)

`inputs`	Mini-batch placeholder
`input_size`	Number of features per cell
`complexity`	Determines the depth and width of an automatically created network
`emb_size`	Number of hidden nodes in final (embedding) hidden layer
`l2_weight`	Weight on l2_regularizer
`dropout_rate`	Probability for dropout.
`is_training`	Determines if dropout and batch norm should be include in pass through network
`batch_norm`	Determines if batch normalization layers should be included