A broad class of discrete-time hypercomplex-valued Hopfield neural networks
From MaRDI portal
(Redirected from Publication:2185682)
Abstract: In this paper, we address the stability of a broad class of discrete-time hypercomplex-valued Hopfield-type neural networks. To ensure the neural networks belonging to this class always settle down at a stationary state, we introduce novel hypercomplex number systems referred to as real-part associative hypercomplex number systems. Real-part associative hypercomplex number systems generalize the well-known Cayley-Dickson algebras and real Clifford algebras and include the systems of real numbers, complex numbers, dual numbers, hyperbolic numbers, quaternions, tessarines, and octonions as particular instances. Apart from the novel hypercomplex number systems, we introduce a family of hypercomplex-valued activation functions called -projection functions. Broadly speaking, a -projection function projects the activation potential onto the set of all possible states of a hypercomplex-valued neuron. Using the theory presented in this paper, we confirm the stability analysis of several discrete-time hypercomplex-valued Hopfield-type neural networks from the literature. Moreover, we introduce and provide the stability analysis of a general class of Hopfield-type neural networks on Cayley-Dickson algebras.
Recommendations
- Stability conditions of bicomplex-valued Hopfield neural networks
- Generalized stability for discontinuous complex-valued Hopfield neural networks via differential inclusions
- Global stability of complex-valued neural networks on time scales
- Global stability analysis in Hopfield neural networks
- Multistability of complex-valued recurrent neural networks with real-imaginary-type activation functions
Cites work
- scientific article; zbMATH DE number 43688 (Why is no real title available?)
- scientific article; zbMATH DE number 45410 (Why is no real title available?)
- scientific article; zbMATH DE number 53607 (Why is no real title available?)
- scientific article; zbMATH DE number 193215 (Why is no real title available?)
- An introduction to Clifford algebras and spinors
- Applications of Clifford's geometric algebra
- Clifford algebra to geometric calculus. A unified language for mathematics and physics
- Complex-valued neural networks
- From the theory of ``congeneric surd equations to ``Segre's bicomplex numbers
- Large annihilators in Cayley-Dickson algebras. II
- Matrix representations of octonions and their applications
- Neural networks and physical systems with emergent collective computational abilities
- Quaternion involutions and anti-involutions
- ``Neural computation of decisions in optimization problems
Cited in
(12)- Asymptotical stability and synchronization of Riemann-Liouville fractional delayed neural networks
- Quaternion-valued recurrent projection neural networks on unit quaternions
- Tessarine signal processing under the \(\mathbb{T}\)-properness condition
- Hybrid impulsive and switching Hopfield neural networks with state-dependent impulses
- Continuous-Time Symmetric Hopfield Nets Are Computationally Universal
- Bicomplex projection rule for complex-valued Hopfield neural networks
- Stability conditions of bicomplex-valued Hopfield neural networks
- Hyperbolic-Valued Hopfield Neural Networks in Synchronous Mode
- \(2p\)-th mean dynamic behaviors for semi-discrete stochastic competitive neural networks with time delays
- Noise Robust Projection Rule for Klein Hopfield Neural Networks
- scientific article; zbMATH DE number 2108089 (Why is no real title available?)
- Linking discrete orthogonality with dilation and translation for incomplete sigma-pi neural networks of Hopfield-type
This page was built for publication: A broad class of discrete-time hypercomplex-valued Hopfield neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2185682)
