Results 91 to 100 of about 1,328,298 (163)

Stochastic Thermodynamic Interpretation of Information Geometry [PDF]

Physical Review Letters, 2018
13 pages, 3 ...
openaire   +3 more sources

Affine Calculus for Constrained Minima of the Kullback–Leibler Divergence

Stats
The non-parametric version of Amari’s dually affine Information Geometry provides a practical calculus to perform computations of interest in statistical machine learning.
Giovanni Pistone
doaj   +1 more source

Fine-Grained Recognition of Mixed Signals with Geometry Coordinate Attention

Sensors
With the advancement of technology, signal modulation types are becoming increasingly diverse and complex. The phenomenon of signal time–frequency overlap during transmission poses significant challenges for the classification and recognition of mixed ...
Qingwu Yi, Qing Wang, Jianwu Zhang, Xiaoran Zheng, Zetao Lu   +4 more
doaj   +1 more source

Connecting Information Geometry and Geometric Mechanics

Entropy, 2017
The divergence function in information geometry, and the discrete Lagrangian in discrete geometric mechanics each induce a differential geometric structure on the product manifold Q × Q .
Melvin Leok, Jun Zhang
doaj   +1 more source

Intrinsic Information-Theoretic Models

Entropy
With this follow-up paper, we continue developing a mathematical framework based on information geometry for representing physical objects. The long-term goal is to lay down informational foundations for physics, especially quantum physics.
D. Bernal-Casas, J. M. Oller
doaj   +1 more source

Fuzzy geometry, entropy, and image information [PDF]

Presented here are various uncertainty measures arising from grayness ambiguity and spatial ambiguity in an image, and their possible applications as image information measures.
Pal, Sankar K.
core   +1 more source

Weyl Geometry and  The Gradient-Flow Equations in Information Geometry

, 2022
Tatsuaki Wada
openalex   +1 more source

The Simple Geometry of Perfect Information Games [PDF]

Perfect information games have a particularly simple structure of equilibria in the associated normal form. For generic such games each of the finitely many connected components of Nash equilibria is contractible. For every perfect information game there
Demichelis, Stefano, Ritzberger, Klaus, Swinkels, Jeroen M.   +2 more
core  

Information-theoretic gradient flows in mouse visual cortex

Frontiers in Neuroinformatics
IntroductionNeural activity can be described in terms of probability distributions that are continuously evolving in time. Characterizing how these distributions are reshaped as they pass between cortical regions is key to understanding how information ...
Erik D. Fagerholm, Hirokazu Tanaka, Milan Brázdil   +2 more
doaj   +1 more source

Improving Flat Maxima with Natural Gradient for Better Adversarial Transferability

Big Data and Cognitive Computing
Deep neural networks are vulnerable and susceptible to adversarial examples, which can induce erroneous predictions by injecting imperceptible perturbations.
Yunfei Long, Huosheng Xu
doaj   +1 more source