Back to Search
Start Over
Multistability of delayed neural networks with hard-limiter saturation nonlinearities
- Source :
- Neurocomputing. 293:41-54
- Publication Year :
- 2018
- Publisher :
- Elsevier BV, 2018.
-
Abstract
- The paper considers a class of nonsmooth neural networks where hard-limiter saturation nonlinearities are used to constrain solutions of a linear system with concentrated and distributed delays to evolve within a closed hypercube of R n . Such networks are termed delayed linear systems in saturated mode (D-LSSMs) and they are a generalization to the delayed case of a relevant class of neural networks previously introduced in the literature. The paper gives a rigorous foundation to the D-LSSM model and then it provides a fundamental result on convergence of solutions toward equilibrium points in the case where there are nonsymmetric cooperative (nonnegative) interconnections between neurons. The result ensures convergence for any finite value of the maximum delay and is physically robust with respect to perturbations of the interconnections. More importantly, it encompasses situations where there exist multiple stable equilibria, thus guaranteeing multistability of cooperative D-LSSMs. From an application viewpoint the delays in combination with the property of multistability make D-LSSMs potentially useful in the fields of associative memories, motion detection and processing of temporal patterns.
- Subjects :
- Equilibrium point
Delayed neural networks
Artificial neural network
Generalization
Computer science
Cognitive Neuroscience
020208 electrical & electronic engineering
Linear system
Cooperative systems
Hard-limiter saturation nonlinearities
Multistability
Nonsmooth dynamical systems
Computer Science Applications1707 Computer Vision and Pattern Recognition
Artificial Intelligence
02 engineering and technology
Topology
Computer Science Applications
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Hypercube
Subjects
Details
- ISSN :
- 09252312
- Volume :
- 293
- Database :
- OpenAIRE
- Journal :
- Neurocomputing
- Accession number :
- edsair.doi.dedup.....390314a36c8ef254ce3cf258d5d40f0b