We need to use the following code to compile the model:

model %>% compile(optimizer = "rmsprop",
          loss = "binary_crossentropy",
          metrics = c("acc"))

From the preceding code, we can observe the following:

• We have used the rmsprop optimizer to compile the model.
• For loss, we have used binary_crossentropy since the response has two values, that is, positive or negative. Metrics will make use of accuracy.

Now, let's start fitting the model.