ON THE GENERATIVE NATURE OF PREDICTION

DOI10.1142/S0219525909002143zbMath1172.60009MaRDI QIDQ3636537

Wolfgang Löhr, Nihat Ay

Publication date: 30 June 2009

Published in: Advances in Complex Systems (Search for Journal in Brave)

zbMATH Keywords

prediction; computational mechanics; hidden Markov models; \(\varepsilon\)-machines

Mathematics Subject Classification ID

60J22: Computational methods in Markov chains

62M20: Inference from stochastic processes and prediction

93E14: Data smoothing in stochastic control theory

60G25: Prediction theory (aspects of stochastic processes)

60J99: Markov processes

Related Items

Beyond Bell's theorem: correlation scenarios, Information symmetries in irreversible processes, Properties of the statistical complexity functional and partially deterministic HMMs, Predictive models and generative complexity, Strong and weak optimizations in classical and quantum models of stochastic processes, The Computational Structure of Spike Trains

Cites Work

• Toward a quantitative theory of self-generated complexity
• The calculi of emergence: Computation, dynamics and induction
• Reductions of hidden information sources
• Predictability, Complexity, and Learning
• Asymptotic Mean Stationarity of Sources With Finite Evolution Dimension
• On Stochastic Processes Derived From Markov Chains
• Computational mechanics: pattern and prediction, structure and simplicity.