Informational and Causal Architecture of Continuous-time Renewal Processes
Author(s)Crutchfield, James P.; Marzen, Sarah E.
MetadataShow full item record
We introduce the minimal maximally predictive models (ϵ-machines) of processes generated by certain hidden semi-Markov models. Their causal states are either discrete, mixed, or continuous random variables and causal-state transitions are described by partial differential equations. As an application, we present a complete analysis of the ϵ-machines of continuous-time renewal processes. This leads to closed-form expressions for their entropy rate, statistical complexity, excess entropy, and differential information anatomy rates.
DepartmentMassachusetts Institute of Technology. Department of Physics
Journal of Statistical Physics
Marzen, Sarah, and James P. Crutchfield. “Informational and Causal Architecture of Continuous-Time Renewal Processes.” Journal of Statistical Physics 168.1 (2017): 109–127.
Author's final manuscript