Yes it is possible. The easiest way to do this is to specify two inputs:
in_1 = Input(...)
in_2 = Input(...)
hidden = Dense(...)(in_1)
in_2_and_hidden = merge([in_2, hidden], mode='concat')
output = Dense(...)(in_2_and_hidden)
The documentation better explains that mergein detail. The general idea of ββseveral inputs and functional models can be read here .
source
share