Causal blankets: Theory and algorithmic framework

We introduce a novel framework to identify perception-action loops (PALOs) directly from data based on the principles of computational mechanics. Our approach is based on the notion of causal blanket, which captures sensory and active variables as dynamical sufficient statistics -- i.e. as the "differences that make a difference." Moreover, our theory provides a broadly applicable procedure to construct PALOs that requires neither a steady-state nor Markovian dynamics. Using our theory, we show that every bipartite stochastic process has a causal blanket, but the extent to which this leads to an effective PALO formulation varies depending on the integrated information of the bipartition.

[1]  Nihat Ay,et al.  The Umwelt of an embodied agent—a measure-theoretic definition , 2015, Theory in Biosciences.

[2]  Anil K. Seth,et al.  Reconciling emergences: An information-theoretic approach to identify causal emergence in multivariate data. , 2020, PLoS computational biology.

[3]  Young,et al.  Inferring statistical complexity. , 1989, Physical review letters.

[4]  Fernando E. Rosas,et al.  Beyond integrated information: A taxonomy of information dynamics phenomena , 2019, 1909.02297.

[5]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[6]  Chrystopher L. Nehaniv,et al.  Representations of Space and Time in the Maximization of Information Flow in the Perception-Action Loop , 2007, Neural Computation.

[7]  Chrystopher L. Nehaniv,et al.  Organization of the information flow in the perception-action loop of evolved agents , 2004, Proceedings. 2004 NASA/DoD Conference on Evolvable Hardware, 2004..

[8]  Pedro A. M. Mediano,et al.  Measuring Integrated Information: Comparison of Candidate Measures in Theory and Simulation , 2018, Entropy.

[9]  Steven L. Bressler,et al.  Wiener–Granger Causality: A well established methodology , 2011, NeuroImage.

[10]  P. Grassberger.  Toward a quantitative theory of self-generated complexity , 1986 .

[11]  Daniel Polani,et al.  Information Theory of Decisions and Actions , 2011 .

[12]  Adeel Razi,et al.  Parcels and particles: Markov blankets in the brain , 2020, Network Neuroscience.

[13]  Ryota Kanai,et al.  A technical critique of the free energy principle as presented in "Life as we know it" and related works , 2020 .

[14]  Daniel Polani,et al.  Action and perception for spatiotemporal patterns , 2017, ECAL.

[15]  Karl J. Friston,et al.  Markov blankets, information geometry and stochastic thermodynamics , 2019, Philosophical Transactions of the Royal Society A.

[16]  Shun-ichi Amari,et al.  Unified framework for information integration based on information geometry , 2015, Proceedings of the National Academy of Sciences.

[17]  James P. Crutchfield,et al.  Computational Mechanics: Pattern and Prediction, Structure and Simplicity , 1999, ArXiv.

[18]  Karl J. Friston,et al.  The Markov blankets of life: autonomy, active inference and the free energy principle , 2018, Journal of The Royal Society Interface.

[19]  Shun-ichi Amari,et al.  Methods of information geometry , 2000 .

[20]  Illtyd Trethowan.  Causality , 1938 .

[21]  N. Ay,et al.  Information and closure in systems theory , 2006 .

[22]  Eckehard Olbrich,et al.  Autonomy: An information theoretic perspective , 2008, Biosyst..

[23]  C. Shalizi,et al.  Causal architecture, complexity and self-organization in time series and cellular automata , 2001 .

[24]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[25]  Ay Nihat,et al.  Information Geometry on Complexity and Stochastic Interaction , 2001 .

[26]  Karl J. Friston,et al.  Some Interesting Observations on the Free Energy Principle , 2020, Entropy.