ASIND algorithm alternately identifies self-dynamics, interactive functions, and networks sparsely without prior knowledge, claiming state-of-the-art identification and 100-step prediction on network dynamics.
Nature Machine Intelligence , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
S4 models exhibit stable time-continuity unlike sensitive S6 models, with task continuity predicting performance and enabling temporal subsampling for better efficiency.
citing papers explorer
-
ASIND: Alternating Sparse Identification for Predicting Network Dynamics Without Knowledge
ASIND algorithm alternately identifies self-dynamics, interactive functions, and networks sparsely without prior knowledge, claiming state-of-the-art identification and 100-step prediction on network dynamics.
-
Continuity Laws for Sequential Models
S4 models exhibit stable time-continuity unlike sensitive S6 models, with task continuity predicting performance and enabling temporal subsampling for better efficiency.