The causal states of computational mechanics define the minimal sufficient (prescient) memory for a given stationary stochastic process. They induce the ε-machine which is a hidden Markov model (HMM) generating the process. The ε-machine is, however, not the minimal generative HMM and minimal internal state entropy of a generative HMMis a tighter upper bound for excess entropy than provided by statistical complexity. We propose a notion of prediction that does not require sufficiency. The corresponding models can be substantially smaller than the ε-machine and are closely related to generative HMMs. © 2009 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.
CITATION STYLE
Löhr, W., & Ay, N. (2009). Non-sufficient memories that are sufficient for prediction. In Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering (Vol. 4 LNICST, pp. 265–276). https://doi.org/10.1007/978-3-642-02466-5_25
Mendeley helps you to discover research relevant for your work.