Inferring the Dynamic, Quantifying Physical Complexity
Through its formalization of inductive inference, computational learning theory provides a foundation for the inverse problem of chaotic data analysis: inferring the deterministic equations of motion underlying observed random behavior in physical systems. Integrating the geometric and statistical techniques of dynamical systems with learning theory provides a framework for consistently, although not absolutely, distinguishing between deterministic chaos and extrinsic fluctuations at a given level of computational resources. Two approaches to the inverse problem, estimating symbolic equations of motion and reconstructing minimal automata from chaotic data series, are reviewed from this point of view. With an inferred model dynamic the dynamical entropies and dimensions can be estimated. More interestingly, its structural properties give a measure of the intrinsic computational complexity of the underlying process.
KeywordsInverse Problem Inference Method Inductive Inference Dynamical System Theory Deterministic Chaos
Unable to display preview. Download preview PDF.
- 1.J. P. Crutchfield, N. H. Packard, J. D. Fanner, and R. S. Shaw. Chaos. Sci. Am., 255: 46, 1986.Google Scholar
- 4.J. P. Crutchfield and K. Young. Computation at the onset of chaos. In W. Zurek, editor, Entropy, Complexity, and Physics of Information. Addison-Wesley, 1989. to appear.Google Scholar
- 5.J. P. Crutchfield and K. Young. Thermodynamics of minimal reconstructed machines. in preparation, 1989.Google Scholar
- 11.J. P. Crutchfield. Noisy Chaos. PhD thesis, University of California, Santa Cruz, 1983. published by University Microfilms Intl, Minnesota.Google Scholar
- 14.A. W. Biermann and J. A. Feldman. On the synthesis of finite-state machines from samples of their behavior. IEEE Trans. Comp., C-21: 592, 1972.Google Scholar
- 15.N. H. Packard. Measurements of Chaos in the Presence of Noise. PhD thesis, University of California, Santa Cruz, 1982.Google Scholar
- 17.J. P. Crutchfield. Time is the ultrametric of causality. in preparation, 1989.Google Scholar
- 18.J. P. Crutchfield. Compressing chaos. in preparation, 1989.Google Scholar
- 22.R. Shaw. The Dripping Faucet as a Model Chaotic System. Aerial Press, Santa Cruz, California, 1984.Google Scholar