Abstract
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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Crutchfield, J.P., Young, K.: Inferring statistical complexity. Phys. Rev. Let. 63, 105–108 (1989)
Shalizi, C.R., Crutchfield, J.P.: Computational mechanics: Pattern and prediction, structure and simplicity. Journal of Statistical Physics 104, 817–879 (2001)
Löhr, W., Ay, N.: On the generative nature of prediction. Accepted for publication in Advances in Complex Systems (preprint, 2008), http://www.mis.mpg.de/publications/preprints/2008/prepr2008-8.html
Still, S., Crutchfield, J.P.: Optimal causal inference. Informal publication (2007), http://arxiv.org/abs/0708.1580
Grassberger, P.: Toward a quantitative theory of self-generated complexity. Int. J. Theor. Phys. 25, 907–938 (1986)
Bialek, W., Nemenman, I., Tishby, N.: Predictability, complexity, and learning. Neural Computation 13, 2409–2463 (2001)
Heller, A.: On stochastic processes derived from Markov chains. Annals of Mathematical Statistics 36, 1286–1291 (1965)
Crutchfield, J.P.: The calculi of emergence: Computation, dynamics and induction. Physica D 75, 11–54 (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Löhr, W., Ay, N. (2009). Non-sufficient Memories That Are Sufficient for Prediction. In: Zhou, J. (eds) Complex Sciences. Complex 2009. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 4. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02466-5_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-02466-5_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02465-8
Online ISBN: 978-3-642-02466-5
eBook Packages: Computer ScienceComputer Science (R0)