Computational capabilities of analog and evolving neural networks over infinite input streams

DOI10.1016/j.jcss.2018.11.003zbMath1410.68120OpenAlexW2900895583WikidataQ128881315 ScholiaQ128881315MaRDI QIDQ1713481

Olivier Finkel, Jérémie Cabessa

Publication date: 25 January 2019

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.2018.11.003

zbMATH Keywords

attractorsanalog computationTuring machinesanalytic setsBorel setsrecurrent neural networks\(\omega\)-languagesinfinite computationTuring machines with oraclessuper-Turing

Mathematics Subject Classification ID

Formal languages and automata (68Q45) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items

Automata complete computation with Hodgkin-Huxley neural networks composed of synfire rings

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The expressive power of analog recurrent neural networks on infinite input streams
• Expressive power of first-order recurrent neural networks determined by their attractor dynamics
• Analytic study of the memory storage capacity of a neural network
• Analog computation via neural networks
• Expressive power of evolving neural networks working on infinite input streams
• Spike timing dependent synaptic plasticity in biological systems
• On the computational power of neural nets
• The dynamic universality of sigmoidal neural networks
• The existence of persistent states in the brain
• Ambiguity of {\omega}-Languages of Turing Machines
• The Computational Power of Interactive Recurrent Neural Networks
• Expressive Power of Non-deterministic Evolving Recurrent Neural Networks in Terms of Their Attractor Dynamics
• Recurrent Neural Networks and Super-Turing Interactive Computation
• A Hierarchical Classification of First-Order Recurrent Neural Networks
• Computational power of neural networks: a characterization in terms of Kolmogorov complexity
• A Unified Approach to Building and Controlling Spiking Attractor Networks
• General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results
• Neural networks and physical systems with emergent collective computational abilities.
• Neurons with graded response have collective computational properties like those of two-state neurons.
• A logical calculus of the ideas immanent in nervous activity