Finite State Automata Resulting from Temporal Information Maximization and a Temporal Learning Rule

DOI10.1162/0899766054615671zbMath1090.68064OpenAlexW2146121105WikidataQ51966352 ScholiaQ51966352MaRDI QIDQ5703546

Thomas Wennekers, Nihat Ay

Publication date: 8 November 2005

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

Full work available at URL: https://doi.org/10.1162/0899766054615671

zbMATH Keywords

stochastic interactionKullback-Leibler divergence of a Markov chain

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Formal languages and automata (68Q45)

Related Items (5)

Information geometry on complexity and stochastic interaction ⋮ INFORMATION FLOWS IN CAUSAL NETWORKS ⋮ Representations of Space and Time in the Maximization of Information Flow in the Perception-Action Loop ⋮ Pursuit of food \textit{versus} pursuit of information in a Markovian perception-action loop model of foraging ⋮ Unnamed Item

Cites Work

• Detecting higher-order interactions among the spiking events in a group of neurons
• The connectivity of the brain: multi-level quantitative analysis
• Local feature analysis: a general statistical theory for object representation
• Hidden Markov modelling of simultaneously recorded cells in the associative cortex of behaving monkeys
• Information geometry on hierarchy of probability distributions
• Information-Geometric Measure for Neural Spikes
• Locality of Global Stochastic Interaction in Directed Acyclic Networks
• Spike-Timing-Dependent Plasticity and Relevant Mutual Information Maximization

This page was built for publication: Finite State Automata Resulting from Temporal Information Maximization and a Temporal Learning Rule