In this paper we contrast linear parametric estimation with non-parametric non-linear neural estimation of the reversion speed a, in the context of the Vasicek model, which is routinely being used for deriving the term structure of the short rate. The sampling parameters of the short-rate, even its realization, were varied widely. Neural regression was employed in an attempt to identify a possibly non-linear relationship, and from that to extract a measure of instantaneous reversion speed (a local equivalent of reversion speed). Neural network models outperformed consistently the linear estimator in ternis of explained variability by more than 10%, indicating a degree of non-linearity in the underlying relationship.