Expressive power of first-order recurrent neural networks determined by their attractor dynamics

DOI10.1016/j.jcss.2016.04.006zbMath1351.68097OpenAlexW2465689145MaRDI QIDQ736603

Alessandro E. P. Villa, Jérémie Cabessa

Publication date: 4 August 2016

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jcss.2016.04.006

zbMATH Keywords

attractorsanalog computationTuring machineslearningrecurrent neural networksexpressive powerneural computationspatio-temporal patternsevolving systems

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Formal languages and automata (68Q45) Modes of computation (nondeterministic, parallel, interactive, probabilistic, etc.) (68Q10) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items

Discrete time-variant nonlinear optimization and system solving via integral-type error function and twice ZND formula with noises suppressed, Unnamed Item, Expressive Power of Non-deterministic Evolving Recurrent Neural Networks in Terms of Their Attractor Dynamics, Echo state networks are universal, Computational capabilities of analog and evolving neural networks over infinite input streams, Automata complete computation with Hodgkin-Huxley neural networks composed of synfire rings, A Survey on Analog Models of Computation

Cites Work

• The expressive power of analog recurrent neural networks on infinite input streams
• Turing machines, transition systems, and interaction
• Interactive foundations of computing
• Analog computation via neural networks
• Hypercomputation: Philosophical issues
• On the computational power of neural nets
• The dynamic universality of sigmoidal neural networks
• The case for hypercomputation
• The many forms of hypercomputation
• Wadge hierarchy and Veblen hierarchy Part I: Borel sets of finite rank
• The Computational Power of Interactive Recurrent Neural Networks
• Expressive Power of Non-deterministic Evolving Recurrent Neural Networks in Terms of Their Attractor Dynamics
• A Hierarchical Classification of First-Order Recurrent Neural Networks
• On ω-regular sets
• General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results
• On Computable Numbers, with an Application to the Entscheidungsproblem
• A logical calculus of the ideas immanent in nervous activity
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item