A framework for decomposing transducers into sub-transducers on distinct subspaces to enable parallel and interpretable world models.
A Prime Decomposition of Probabilistic Automata
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
A definition of a probabilistic automaton is formulated in which its prime decomposition follows as a direct consequence of Krohn-Rhodes theorem. We first characterize the local structure of probabilistic automata. The prime decomposition is presented as a framework to study the global structure of probabilistic automata. We prove that the representation theory of a probabilistic automaton is determined by that of the finite groups in its holonomy decomposition.
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
From monoliths to modules: Decomposing transducers for efficient world modelling
A framework for decomposing transducers into sub-transducers on distinct subspaces to enable parallel and interpretable world models.