A connection is drawn between rational functions, the realization theory of dynamical systems, and feedforward neural networks. This allows us to parametrize single hidden layer scalar neural networks with (almost) arbitrary analytic activation functions in terms of strictly proper rational functions. Hence, we can solve the uniqueness of parametrization problem for such networks.

IR is typically a sigmoidal function such as (1.2) but other choices than (1.2) are possible and of interest.

IR is typically a sigmoidal function such as (1.2) but other choices than (1.2) are possible and of interest.

IR is typically a sigmoidal function such as (1.2) but other choices than (1.2) are possible and of interest.