Change gate function to view instead of copy

Only for vector input as copying a matrix may be more efficient due to
caching. A matrix is sliced per row, meaning the view will not be
aligned.

src/layers/recurrent.jl

@@ -1,5 +1,5 @@
 gate(h, n) = (1:h) .+ h*(n-1)
-gate(x::AbstractVector, h, n) = x[gate(h,n)]
+gate(x::AbstractVector, h, n) = @view x[gate(h,n)]
 gate(x::AbstractMatrix, h, n) = x[gate(h,n),:]
 
 # Stateful recurrence