A broad class of discrete-time hypercomplex-valued Hopfield neural networks. (February 2020)

• Record Type: Journal Article
• Authors: de Castro, Fidelis Zanetti; Valle, Marcos Eduardo
• Is Part Of: Neural networks. Volume 122(2020)
• Page Start: 54
• Page End: 67
• Publication Date: 2020-02
• Subjects: Hopfield neural network -- Hypercomplex-valued neural network -- Stability analysis -- Clifford algebra -- Cayley–Dickson algebra; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2019.09.040
• Languages: English
• ISSNs: 0893-6080

Abstract

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 B -projection functions. Broadly speaking, a B -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. Highlights: New hypercomplex number systems and a broad class of activation functions. Stability analysis of discrete-time hypercomplex-valued Hopfield neural networks. Hopfield-type neural networks on Cayley–Dickson and Clifford algebras. Possible applications for multidimensional data processing.