A unified framework for information integration based on information geometry

Abstract

We propose a unified theoretical framework for quantifying spatio-temporal interactions in a stochastic dynamical system based on information geometry. In the proposed framework, the degree of interactions is quantified by the divergence between the actual probability distribution of the system and a constrained probability distribution where the interactions of interest are disconnected. This framework provides novel geometric interpretations of various information theoretic measures of interactions, such as mutual information, transfer entropy, and stochastic interaction in terms of how interactions are disconnected. The framework therefore provides an intuitive understanding of the relationships between the various quantities. By extending the concept of transfer entropy, we propose a novel measure of integrated information which measures causal interactions between parts of a system. Integrated information quantifies the extent to which the whole is more than the sum of the parts and can be potentially used as a biological measure of the levels of consciousness.

References in corpus (2)

• Multivariate Granger Causality and Generalized Variance
• Improved Measures of Integrated Information

Cited by in corpus (22)

• Stochastic thermodynamic interpretation of information geometry
• PyPhi: A toolbox for integrated information theory
• Integrated information as a common signature of dynamical and information-processing complexity
• Efficient Algorithms for Searching the Minimum Information Partition in Integrated Information Theory
• Towards an extended taxonomy of information dynamics via Integrated Information Decomposition
• Geometric thermodynamics for the Fokker-Planck equation: Stochastic thermodynamic links between information geometry and optimal transport
• Fast and exact search for the partition with minimal information loss
• A unifying framework for mean-field theories of asymmetric kinetic Ising systems
• Nonequilibrium uncertainty principle from information geometry
• General anesthesia reduces complexity and temporal asymmetry of the informational structures derived from neural recordings in Drosophila
• Unified framework for the entropy production and the stochastic interaction based on information geometry
• Integrated information in the thermodynamic limit
• Comparing Information-Theoretic Measures of Complexity in Boltzmann Machines
• Integrated Information in the Spiking-Bursting Stochastic Model
• Geometry of Information Integration
• Integrated information and dimensionality in continuous attractor dynamics
• Decomposing information into copying versus transformation
• Complexity as Causal Information Integration
• Homotopy Theoretic and Categorical Models of Neural Information Networks
• Information Geometry Connecting Wasserstein Distance and Kullback-Leibler Divergence via the Entropy-Relaxed Transportation Problem
• Examining the causal structures of deep neural networks using information theory
• Iterative Scaling Algorithm for Channels