Continuous-Time Symmetric Hopfield Nets Are Computationally Universal
From MaRDI portal
Publication:3375307
DOI10.1162/089976603321192130zbMath1088.68148WikidataQ51639700 ScholiaQ51639700MaRDI QIDQ3375307
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
68T05: Learning and adaptive systems in artificial intelligence
Cites Work
- Analog computation via neural networks
- Computability with low-dimensional dynamical systems
- A theory of complexity for continuous time systems
- On the computational power of neural nets
- Absolute stability of global pattern formation and parallel memory storage by competitive neural networks
- Theory of neuromata
- Computational power of neural networks: a characterization in terms of Kolmogorov complexity
- Unpredictability and undecidability in dynamical systems
- Neural networks and physical systems with emergent collective computational abilities.
- Neurons with graded response have collective computational properties like those of two-state neurons.