The expressive power of analog recurrent neural networks on infinite input streams

DOI10.1016/J.TCS.2012.01.042MaRDI QIDQ428898zbMATH OpenOpenAlexFDO

Authors Jérémie Cabessa, Alessandro E. P. Villa

Publication date 25 June 2012

Published in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.tcs.2012.01.042

zbMATH Keywords

topologyanalog computationTuring machinesanalytic setsBorel sets\(\omega \)-automataanalog neural networks

Mathematics Subject Classification ID

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

Recommendations

• Computational capabilities of analog and evolving neural networks over infinite input streams
• Expressive power of evolving neural networks working on infinite input streams
• Expressive power of non-deterministic evolving recurrent neural networks in terms of their attractor dynamics
• Expressive power of first-order recurrent neural networks determined by their attractor dynamics
• Analog neuron hierarchy

Cites work

• scientific article; zbMATH DE number 3139352 (Why is no real title available?)
• scientific article; zbMATH DE number 4002078 (Why is no real title available?)
• scientific article; zbMATH DE number 1260390 (Why is no real title available?)
• scientific article; zbMATH DE number 722611 (Why is no real title available?)
• scientific article; zbMATH DE number 1142314 (Why is no real title available?)
• scientific article; zbMATH DE number 1166155 (Why is no real title available?)
• scientific article; zbMATH DE number 2080910 (Why is no real title available?)
• scientific article; zbMATH DE number 1909824 (Why is no real title available?)
• scientific article; zbMATH DE number 1909830 (Why is no real title available?)
• scientific article; zbMATH DE number 2206109 (Why is no real title available?)
• scientific article; zbMATH DE number 3310089 (Why is no real title available?)
• scientific article; zbMATH DE number 3311755 (Why is no real title available?)
• A hierarchical classification of first-order recurrent neural networks
• A logical calculus of the ideas immanent in nervous activity
• Analog computation via neural networks
• Automata Studies. (AM-34)
• Automata, logics, and infinite games. A guide to current research
• Borel ranks and Wadge degrees of context free $\omega$-languages
• Computational power of neural networks: a characterization in terms of Kolmogorov complexity
• How We Think of Computing Today
• Interactive Computation
• On Computable Numbers, with an Application to the Entscheidungsproblem
• On the computational power of neural nets
• Set Theory
• The dynamic universality of sigmoidal neural networks
• Turing computability with neural nets
• \(X\)-automata on \(\omega\)-words

Cited in

(12)

• A hierarchical classification of first-order recurrent neural networks
• Analog neuron hierarchy
• Expressive power of first-order recurrent neural networks determined by their attractor dynamics
• Automata complete computation with Hodgkin-Huxley neural networks composed of synfire rings
• Expressive power of evolving neural networks working on infinite input streams
• Subrecursive neural networks
• Expressive power of non-deterministic evolving recurrent neural networks in terms of their attractor dynamics
• A new design formula exploited for accelerating Zhang neural network and its application to time-varying matrix inversion
• Computational capabilities of analog and evolving neural networks over infinite input streams
• Discrete-time formulation, control, solution and verification of pendulum systems with zeroing neural dynamics
• From mathematical equivalence such as Ma equivalence to generalized Zhang equivalency including gradient equivalency
• A Survey on Analog Models of Computation

This page was built for publication: The expressive power of analog recurrent neural networks on infinite input streams

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q428898)