ZNO is a causal neural operator for discrete-time dynamics that parameterizes stable low-rank rational filters in the z-plane and shows advantages on systems with poles near the unit circle.
The ZNO dynamic branch (3.2)–(3.3) is a low-rank factorization of a MIMO rational transfer matrix with r≪w state channels, and the full residual layer adds a dense pointwise skip
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ZNO: Stable Rational Neural Operators in the Z-Domain for Discrete-Time Dynamics
ZNO is a causal neural operator for discrete-time dynamics that parameterizes stable low-rank rational filters in the z-plane and shows advantages on systems with poles near the unit circle.