Locality of Global Stochastic Interaction in Directed Acyclic Networks

DOI10.1162/089976602760805368zbMath1079.68582OpenAlexW2168157907WikidataQ52111145 ScholiaQ52111145MaRDI QIDQ4815045

Nihat Ay

Publication date: 19 August 2004

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/089976602760805368

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (9)

Information geometry on complexity and stochastic interaction ⋮ On the locality of the natural gradient for learning in deep Bayesian networks ⋮ Optimally approximating exponential families ⋮ Finite State Automata Resulting from Temporal Information Maximization and a Temporal Learning Rule ⋮ Representations of Space and Time in the Maximization of Information Flow in the Perception-Action Loop ⋮ Recurrent Infomax Generates Cell Assemblies, Neuronal Avalanches, and Simple Cell-Like Selectivity ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Factorized mutual information maximization

Cites Work

• An information-geometric approach to a theory of pragmatic structuring
• Information geometry on hierarchy of probability distributions
• On Information and Sufficiency

This page was built for publication: Locality of Global Stochastic Interaction in Directed Acyclic Networks