A broad class of discrete-time hypercomplex-valued Hopfield neural networks

DOI10.1016/J.NEUNET.2019.09.040zbMATH Open1445.30023arXiv1902.05478OpenAlexW2981196140WikidataQ91057257 ScholiaQ91057257MaRDI QIDQ2185682FDOQ2185682

Fidelis Zanetti de Castro, Marcos Eduardo Valle

Publication date: 5 June 2020

Published in: Neural Networks (Search for Journal in Brave)

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 $mathcalB$-projection functions. Broadly speaking, a $mathcalB$-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.

Full work available at URL: https://arxiv.org/abs/1902.05478

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

zbMATH Keywords

Clifford algebraHopfield neural networkCayley-Dickson algebrahypercomplex-valued neural network

Mathematics Subject Classification ID

Functions of hypercomplex variables and generalized variables (30G35)

Cites Work

• Neural networks and physical systems with emergent collective computational abilities.
• ``Neural computation of decisions in optimization problems
• Title not available (Why is that?)
• Clifford algebra to geometric calculus. A unified language for mathematics and physics
• Quaternion involutions and anti-involutions
• Title not available (Why is that?)
• Title not available (Why is that?)
• Applications of Clifford's geometric algebra
• Matrix representations of octonions and their applications
• Complex-valued neural networks
• An Introduction to Clifford Algebras and Spinors
• From the theory of ``congeneric surd equations to ``Segre's bicomplex numbers
• Large annihilators in Cayley-Dickson algebras. II
• Title not available (Why is that?)

Cited In (11)

• Bicomplex Projection Rule for Complex-Valued Hopfield Neural Networks
• Continuous-Time Symmetric Hopfield Nets Are Computationally Universal
• Noise Robust Projection Rule for Klein Hopfield Neural Networks
• Title not available (Why is that?)
• Quaternion-valued recurrent projection neural networks on unit quaternions
• Tessarine signal processing under the \(\mathbb{T}\)-properness condition
• Linking discrete orthogonality with dilation and translation for incomplete sigma-pi neural networks of Hopfield-type
• \(2p\)-th mean dynamic behaviors for semi-discrete stochastic competitive neural networks with time delays
• Asymptotical stability and synchronization of Riemann-Liouville fractional delayed neural networks
• Hybrid impulsive and switching Hopfield neural networks with state-dependent impulses
• Hyperbolic-Valued Hopfield Neural Networks in Synchronous Mode

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)