A Fortran-Keras Deep Learning Bridge for Scientific Computing

Algorithm 2

Forward pass in the FKB network module. Each layer simply calls its own forward function. The technical operations occur within each layer.

	function output(self, input) result(last_layer_output)
...
! iterate through layers passing activation forward
do n = 1, size(layers)
call layers(n) % p % forward(layers(n-1) % p % o)
	end do
! get output from last layer
last_layer_output = layers(size(layers)) % p % o
end function output