Results 41 to 50 of about 1,600,993 (289)
The Information Geometry of Chaos
, 2016 We present a new theoretical information-geometric framework (IGAC, Information Geometrodynamical Approach to Chaos) suitable to characterize chaotic dynamical behavior of arbitrary complex systems.
Carlo Cafaro
openalex +4 more sources
Information geometry approach to parameter estimation in Markov chains [PDF]
, 2014 We consider the parameter estimation of Markov chain when the unknown transition matrix belongs to an exponential family of transition matrices. Then, we show that the sample mean of the generator of the exponential family is an asymptotically efficient ...
Masahito Hayashi, Shun Watanabe
openalex +4 more sources
Capturing Outlines of Planar Generic Images by Simultaneous Curve Fitting and Sub-division [PDF]
Journal of Artificial Intelligence and Data Mining, 2020 In this paper, a new technique has been designed to capture the outline of 2D shapes using cubic B´ezier curves. The proposed technique avoids the traditional method of optimizing the global squared fitting error and emphasizes the local control of data ...
A.R. Ebrahimi +2 more
doaj +1 more source
Biology, geometry and information [PDF]
Theory in Biosciences, 2021 AbstractThe main thesis developed in this article is that the key feature of biological life is the a biological process can control and regulate other processes, and it maintains that ability over time. This control can happen hierarchically and/or reciprocally, and it takes place in three-dimensional space.
openaire +3 more sources
Unified framework for information integration based on information geometry. [PDF]
Proc Natl Acad Sci U S A, 2016 We propose a unified theoretical framework for quantifying spatio-temporal interactions in a stochastic dynamical system based on information geometry.
Oizumi M, Tsuchiya N, Amari SI.
europepmc +2 more sources
Neural Dynamics under Active Inference: Plausibility and Efficiency of Information Processing
Entropy, 2021 Active inference is a normative framework for explaining behaviour under the free energy principle—a theory of self-organisation originating in neuroscience.
Lancelot Da Costa +3 more
doaj +1 more source
Pullback Bundles and the Geometry of Learning
Entropy, 2023 Explainable Artificial Intelligence (XAI) and acceptable artificial intelligence are active topics of research in machine learning. For critical applications, being able to prove or at least to ensure with a high probability the correctness of algorithms
Stéphane Puechmorel
doaj +1 more source
Statistical Analysis of Plasma Dynamics in Gyrokinetic Simulations of Stellarator Turbulence
Entropy, 2023 A geometrical method for assessing stochastic processes in plasma turbulence is investigated in this study. The thermodynamic length methodology allows using a Riemannian metric on the phase space; thus, distances between thermodynamic states can be ...
Aristeides D. Papadopoulos +4 more
doaj +1 more source
How Morphological Computation Shapes Integrated Information in Embodied Agents
Frontiers in Psychology, 2021 The Integrated Information Theory provides a quantitative approach to consciousness and can be applied to neural networks. An embodied agent controlled by such a network influences and is being influenced by its environment.
Carlotta Langer +5 more
doaj +1 more source
F‐Manifolds and geometry of information [PDF]
Bulletin of the London Mathematical Society, 2020 The theory of $F$-manifolds, and more generally, manifolds endowed with commutative and associative multiplication of their tangent fields, was discovered and formalised in various models of quantum field theory involving algebraic and analytic geometry, at least since 1990's. The focus of this paper consists in the demonstration that various spaces of
Combe , N., Manin, Y.
openaire +5 more sources