Continuous-Time Symmetric Hopfield Nets Are Computationally Universal

DOI10.1162/089976603321192130MaRDI QIDQ3375307zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Jiří Šíma, Pekka Orponen

Publication date 7 March 2006

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/089976603321192130

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Continuous-Time Symmetric Hopfield Nets Are Computationally Universal
• Computing with continuous-time Liapunov systems
• scientific article; zbMATH DE number 1849152
• scientific article; zbMATH DE number 1490012
• On the computational power of discrete Hopfield nets

Cites work

• A theory of complexity for continuous time systems
• Absolute stability of global pattern formation and parallel memory storage by competitive neural networks
• Analog computation via neural networks
• Computability with low-dimensional dynamical systems
• Computational power of neural networks: a characterization in terms of Kolmogorov complexity
• Neural networks and physical systems with emergent collective computational abilities
• Neurons with graded response have collective computational properties like those of two-state neurons
• On the computational power of neural nets
• Theory of neuromata
• Unpredictability and undecidability in dynamical systems

Cited in

(5)

• scientific article; zbMATH DE number 1849152 (Why is no real title available?)
• Storing cycles in Hopfield-type networks with pseudoinverse learning rule: admissibility and network topology
• A Survey on Analog Models of Computation
• On the computational efficiency of symmetric neural networks
• On the computational power of discrete Hopfield nets

This page was built for publication: Continuous-Time Symmetric Hopfield Nets Are Computationally Universal

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3375307)