2009 | OriginalPaper | Chapter
Non-sufficient Memories That Are Sufficient for Prediction
Authors : Wolfgang Löhr, Nihat Ay
Published in: Complex Sciences
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
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 HMM is 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.