Zobrazeno 1 - 10
of 376
pro vyhledávání: '"Nihat Ay"'
Autor:
Andreas Knauf
Publikováno v:
Jahresbericht der Deutschen Mathematiker-Vereinigung. 121:297-302
Autor:
Carlotta Langer, Nihat Ay
Publikováno v:
Frontiers in Psychology, Vol 12 (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. This involves, on the one
Externí odkaz:
https://doaj.org/article/edfec409fd2f44a79ce75947477c5b9e
Autor:
Nihat Ay, Shun-ichi Amari
Publikováno v:
Entropy, Vol 17, Iss 12, Pp 8111-8129 (2015)
A divergence function on a manifold M defines a Riemannian metric g and dually coupled affine connections ∇ and ∇ * on M. When M is dually flat, that is flat with respect to ∇ and ∇ * , a canonical divergence is known, which is uniquely deter
Externí odkaz:
https://doaj.org/article/8873c25915e344ea9d0bab51d86cc3a4
Autor:
Carlotta Langer, Nihat Ay
Publikováno v:
Entropy, Vol 22, Iss 10, p 1107 (2020)
Complexity measures in the context of the Integrated Information Theory of consciousness try to quantify the strength of the causal connections between different neurons. This is done by minimizing the KL-divergence between a full system and one with
Externí odkaz:
https://doaj.org/article/fcbb7b09addd4dc1adf16f3a8d39ce3d
Autor:
Nihat Ay
Publikováno v:
Entropy, Vol 17, Iss 4, Pp 2432-2458 (2015)
Interdependencies of stochastically interacting units are usually quantified by the Kullback-Leibler divergence of a stationary joint probability distribution on the set of all configurations from the corresponding factorized distribution. This is a
Externí odkaz:
https://doaj.org/article/e8451a91837f4ccfa8be6ed4d083dd6d
Autor:
Bastian Steudel, Nihat Ay
Publikováno v:
Entropy, Vol 17, Iss 4, Pp 2304-2327 (2015)
A directed acyclic graph (DAG) partially represents the conditional independence structure among observations of a system if the local Markov condition holds, that is if every variable is independent of its non-descendants given its parents. In gener
Externí odkaz:
https://doaj.org/article/cc622236f20540fa9ae7dca64c26488c
Autor:
Domenico Felice, Nihat Ay
Publikováno v:
Information Geometry. 4:65-130
In Riemannian geometry geodesics are integral curves of the Riemannian distance gradient. We extend this classical result to the framework of Information Geometry. In particular, we prove that the rays of level-sets defined by a pseudo-distance are g
Publikováno v:
Vietnam Journal of Mathematics. 49:237-240
Publikováno v:
Information Geometry (in Press): (2022)
The natural gradient field is a vector field that lives on a model equipped with a distinguished Riemannian metric, e.g. the Fisher–Rao metric, and represents the direction of steepest ascent of an objective function on the model with respect to th
Publikováno v:
Entropy, Vol 16, Iss 6, Pp 3207-3233 (2014)
We consider three different approaches to define natural Riemannian metrics on polytopes of stochastic matrices. First, we define a natural class of stochastic maps between these polytopes and give a metric characterization of Chentsov type in terms
Externí odkaz:
https://doaj.org/article/32d8b5aea8c547e483d30da947551e96