Multitasking attractor networks with neuronal threshold noise
From MaRDI portal
Abstract: We consider the multitasking associative network in the low-storage limit and we study its phase diagram with respect to the noise level and the degree of dilution in pattern entries. We find that the system is characterized by a rich variety of stable states, among which pure states, parallel retrieval states, hierarchically organized states and symmetric mixtures (remarkably, both even and odd), whose complexity increases as the number of patterns grows. The analysis is performed both analytically and numerically: Exploiting techniques based on partial differential equations, allows us to get the self-consistencies for the order parameters. Such self-consistence equations are then solved and the solutions are further checked through stability theory to catalog their organizations into the phase diagram, which is completely outlined at the end. This is a further step toward the understanding of spontaneous parallel processing in associative networks.
Recommendations
- Associative networks with diluted patterns: dynamical analysis at low and medium load
- Retrieval properties of diluted attractor neural networks
- An associative network with spatially organized connectivity
- scientific article; zbMATH DE number 1164156
- Parallel retrieval of correlated patterns: from Hopfield networks to Boltzmann machines
Cites work
- scientific article; zbMATH DE number 1273988 (Why is no real title available?)
- scientific article; zbMATH DE number 2211481 (Why is no real title available?)
- A mechanical approach to mean field spin models
- A thermodynamic perspective of immune capabilities
- Finite connectivity attractor neural networks
- Modeling Brain Function
- Neural networks and physical systems with emergent collective computational abilities
- Neural networks: A review from a statistical perspective. With comments and a rejoinder by the authors
- On the equivalence of Hopfield networks and Boltzmann machines
- Parallel retrieval of correlated patterns: from Hopfield networks to Boltzmann machines
- Replicated transfer matrix analysis of Ising spin models on small world lattices
Cited in
(7)- A new mechanical approach to handle generalized Hopfield neural networks
- Non-convex multi-species Hopfield models
- Parallel learning by multitasking neural networks
- Associative networks with diluted patterns: dynamical analysis at low and medium load
- Asynchronous threshold networks with multisorted signals
- Dreaming neural networks: rigorous results
- Immune networks: multi-tasking capabilities at medium load
This page was built for publication: Multitasking attractor networks with neuronal threshold noise
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q461183)
