Boolean neural nets are observable
It is shown that arbitrary locally finite discrete neural networks are observable (have the shadowing property) in the sense that pseudo-orbits obtained by small perturbations of an orbit are approximated by actual orbits. The model includes discretizations of analog networks, arbitrary cellular automata, and a wide generalization of linear maps on a one dimensional grid. It follows that the true qualitative behavior of dynamical systems can be observed to infinite precision on computer simulations, despite unavoidable discretization and approximation errors. © 1994.
Theoretical Computer Science
Botelho, F., & Garzon, M. (1994). Boolean neural nets are observable. Theoretical Computer Science, 134 (1), 51-61. https://doi.org/10.1016/0304-3975(94)90277-1