Corpus ID: 7077093

Pattern Discovery and Computational Mechanics

@article{Shalizi2000PatternDA,
  title={Pattern Discovery and Computational Mechanics},
  author={C. Shalizi and J. Crutchfield},
  journal={ArXiv},
  year={2000},
  volume={cs.LG/0001027}
}
  • C. Shalizi, J. Crutchfield
  • Published 2000
  • Computer Science
  • ArXiv
  • Computational mechanics is a method for discovering, describing and quantifying patterns, using tools from statistical physics. It contructs optimal, minimal models of stochastic processes and their underlying causal structures. These models tell us about the intrinsic computation embedded within a process -- how it stores and transforms information. Here we summarize the mathematics of computational mechanics, especially recent optimality and uniqueness results. We also expound the principles… CONTINUE READING
    10 Citations
    The Insights of Algorithmic Entropy
    • 16
    • PDF
    Emergence Made Ontological? Computational versus Combinatorial Approaches
    • P. Huneman
    • Computer Science
    • Philosophy of Science
    • 2008
    • 19
    • PDF
    ACORNS - towards computational modeling of communication and recognition skills
    • 39
    Metadata of the chapter that will be visualized online
    The Last Scientific Revolution
    • 7
    • PDF
    Artificial Neural Diagnostics and Prognostics: Self-Soothing in Cognitive Systems
    • 22
    • PDF

    References

    SHOWING 1-10 OF 35 REFERENCES
    Computational Mechanics: Pattern and Prediction, Structure and Simplicity
    • 412
    • PDF
    Inferring statistical complexity.
    • 825
    The calculi of emergence: computation, dynamics and induction
    • 687
    • PDF
    Finite statistical complexity for sofic systems.
    • N. Perry, P. M. Binder
    • Medicine, Mathematics
    • Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics
    • 1999
    • 23
    Induction: Processes of Inference, Learning, and Discovery
    • 2,132
    Statistical language learning
    • 1,083
    • PDF
    Error and the Growth of Experimental Knowledge
    • 399
    A theory of the learnable
    • 3,382
    • PDF
    Unsupervised Learning Procedures for Neural Networks
    • 109
    • PDF