neg_create_model: create deep learning using positive unlabeled learning

In lkmklsmn/empty_nn: Remove empty droplets in scRNA-seq data

create deep learning using positive unlabeled learning

Usage

neg_create_model(input)

Arguments

input

Examples

##---- Should be DIRECTLY executable !! ----
##-- ==>  Define data, use random,
##--	or do  help(data=index)  for the standard data sets.

## The function is currently defined as
function (input) 
{
    model <- keras_model_sequential()
    model %>% layer_dense(units = 256, activation = "relu", input_shape = input) %>% 
        layer_dropout(rate = 0.4) %>% layer_dense(units = 128, 
        activation = "relu") %>% layer_dropout(rate = 0.3) %>% 
        layer_dense(units = 2, activation = "softmax")
    model %>% compile(loss = "binary_crossentropy", optimizer = optimizer_rmsprop(), 
        metrics = c("accuracy"))
    model
  }

lkmklsmn/empty_nn documentation built on Jan. 30, 2024, 1:31 a.m.