Hopfield neural networks

A Hopfield Neural Network (HNN) with a new weight update rule can be treated as a second order Estimation of Distribution Algorithm (EDA) or Fitness Function Model (FFM) for solving optimisation problems. The HNN models promising solutions and has a capacity for storing a certain number of local optima as low energy attractors. Solutions are generated by sampling the patterns stored in the attractors. The number of attractors a network can store (its capacity) has an impact on solution diversity and, consequently solution quality. This paper introduces two new HNN learning rules and presents the Hopfield EDA (HEDA), which learns weight values from samples of the fitness function. It investigates the attractor storage capacity of the HEDA and shows it to be equal to that known in the literature for a standard HNN. The relationship between HEDA capacity and linkage order is also investigated.

Communicable diseases pose significant threats at local, regional, and global levels, often leading to epidemics or pandemics. An epidemic refers to a sudden increase in the number of cases of an infectious disease above what is normally expected in a given population. Examples include cholera, measles, malaria, and dengue fever. Pandemics, however, can result in widespread illness, significant loss of life, and severe social and economic consequences. Concerns about potential pandemic diseases, such as new strains of influenza and severe acute respiratory syndrome (SARS) remain critical. This study presents a deep learning framework based on Geographic Information Systems (GIS) to predict the spatial distribution of epidemic infectious diseases. The framework combines the strengths of deep learning and GIS techniques, both of which offer exceptional capabilities in the field of epidemiology. The study outlines the key steps involved in developing the proposed framework and explains its operational functionality. The proposed framework aims to enhance decision-making efficiency, assist governmental authorities in generating sustainable strategies, and establish appropriate protocols to control epidemics, particularly in highrisk areas. By predicting vulnerable areas, the framework helps mitigate the risks associated with outbreaks and protects social and economic stability. Choosing an appropriate framework requires consideration of several key factors, including those relevant to the spread of diseases or epidemics, accuracy, flexibility, and validation.

From a brain processing perspective, the perception of creative thinking is rooted in the underlying cognitive process, which facilitates exploring and cultivating novel avenues and problem-solving strategies. However, it is challenging to emulate the intricate complexity of how the human brain presents a novel way to uncover unique solutions. One potential approach to mitigate this complexity is incorporating creative cognition within the evolving artificial intelligence systems and associated neural models. Hopfield Neural Networks (HNN) are commonly acknowledged as a simplified neural model, renowned for their biological plausibility to store and retrieve information, specifically patterns of neurons. Therefore, we propose for the first time using HNN to generate a potential model that emulates specific cognitive processes of creative thinking based on generating meaningful links between seemingly disparate concepts.

A Hopfield Neural Network (HNN) with a new weight update rule can be treated as a second order Estimation of Distribution Algorithm (EDA) or Fitness Function Model (FFM) for solving optimisation problems. The HNN models promising solutions and has a capacity for storing a certain number of local optima as low energy attractors. Solutions are generated by sampling the patterns stored in the attractors. The number of attractors a network can store (its capacity) has an impact on solution diversity and, consequently solution quality. This paper introduces two new HNN learning rules and presents the Hopfield EDA (HEDA), which learns weight values from samples of the fitness function. It investigates the attractor storage capacity of the HEDA and shows it to be equal to that known in the literature for a standard HNN. The relationship between HEDA capacity and linkage order is also investigated.

From a brain processing perspective, the perception of creative thinking is rooted in the underlying cognitive process, which facilitates exploring and cultivating novel avenues and problem-solving strategies. However, it is challenging to emulate the intricate complexity of how the human brain presents a novel way to uncover unique solutions. One potential approach to mitigate this complexity is incorporating creative cognition within the evolving artificial intelligence systems and associated neural models. Hopfield Neural Networks (HNN) are commonly acknowledged as a simplified neural model, renowned for their biological plausibility to store and retrieve information, specifically patterns of neurons. Therefore, we propose for the first time using HNN to generate a potential model that emulates specific cognitive processes of creative thinking based on generating meaningful links between seemingly disparate concepts.

This paper is concerned with the global asymptotic stability analysis problem for a class of uncertain stochastic Hopfield neural networks with discrete and distributed time-delays. By utilizing a Lyapunov-Krasovskii functional, using the well-known S-procedure and conducting stochastic analysis, we show that the addressed neural networks are robustly, globally, asymptotically stable if a convex optimization problem is feasible. Then, the stability criteria are derived in terms of linear matrix inequalities (LMIs), which can be effectively solved by some standard numerical packages. The main results are also extended to the multiple time-delay case. Two numerical examples are given to demonstrate the usefulness of the proposed global stability condition.

A numerical method for computational implementation of gradient dynamical systems is presented. The method is based upon the development of geometric integration numerical methods, which aim at preserving the dynamical properties of the original ordinary differential equation under discretization. In particular, the proposed method belongs to the class of discrete gradients methods, which substitute the gradient of the continuous equation with a discrete gradient, leading to a map that possesses the same Lyapunov function of the dynamical system, thus preserving the qualitative properties regardless of the step size. In this work, we apply a discrete gradient method to the implementation of Hopfield neural networks. Contrary to most geometric integration methods, the proposed algorithm can be rewritten in explicit form, which considerably improves its performance and stability. Simulation results show that the preservation of the Lyapunov function leads to an improved performance, compared to the conventional discretization.

In this paper we introduce an impulsive Hopfield-type neural network system with piecewise constant argument of generalized type. Sufficient conditions for the existence of the unique equilibrium are obtained. Existence and uniqueness of solutions of such systems are established. Stability criterion based on linear approximation is proposed. Some sufficient conditions for the existence and stability of periodic solutions are derived. An example with numerical simulations is given to illustrate our results.

In this paper we introduce an impulsive Hopfield-type neural network system with piecewise constant argument of generalized type. Sufficient conditions for the existence of the unique equilibrium are obtained. Existence and uniqueness of solutions of such systems are established. Stability criterion based on linear approximation is proposed. Some sufficient conditions for the existence and stability of periodic solutions are derived. An example with numerical simulations is given to illustrate our results.

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

This paper proposes the optimization relaxation approach based on the analogue Hopfield Neural Network (HNN) for cluster refinement of pre-classified Polarimetric Synthetic Aperture Radar (PolSAR) image data. We consider the initial classification provided by the maximum-likelihood classifier based on the complex Wishart distribution, which is then supplied to the HNN optimization approach. The goal is to improve the classification results obtained by the Wishart approach. The classification improvement is verified by computing a cluster separability coefficient and a measure of homogeneity within the clusters. During the HNN optimization process, for each iteration and for each pixel, two consistency coefficients are computed, taking into account two types of relations between the pixel under consideration and its corresponding neighbors. Based on these coefficients and on the information coming from the pixel itself, the pixel under study is reclassified. Different experiments are carried out to verify that the proposed approach outperforms other strategies, achieving the best results in terms of separability and a trade-off with the homogeneity preserving relevant structures in the image. The performance is also measured in terms of computational central processing unit (CPU) times.

A numerical method for computational implementation of gradient dynamical systems is presented. The method is based upon the development of geometric integration numerical methods, which aim at preserving the dynamical properties of the original ordinary differential equation under discretization. In particular, the proposed method belongs to the class of discrete gradients methods, which substitute the gradient of the continuous equation with a discrete gradient, leading to a map that possesses the same Lyapunov function of the dynamical system, thus preserving the qualitative properties regardless of the step size. In this work, we apply a discrete gradient method to the implementation of Hopfield neural networks. Contrary to most geometric integration methods, the proposed algorithm can be rewritten in explicit form, which considerably improves its performance and stability. Simulation results show that the preservation of the Lyapunov function leads to an improved performance, compared to the conventional discretization.

A numerical method for computational implementation of gradient dynamical systems is presented. The method is based upon the development of geometric integration numerical methods, which aim at preserving the dynamical properties of the original ordinary differential equation under discretization. In particular, the proposed method belongs to the class of discrete gradients methods, which substitute the gradient of the continuous equation with a discrete gradient, leading to a map that possesses the same Lyapunov function of the dynamical system, thus preserving the qualitative properties regardless of the step size. In this work, we apply a discrete gradient method to the implementation of Hopfield neural networks. Contrary to most geometric integration methods, the proposed algorithm can be rewritten in explicit form, which considerably improves its performance and stability. Simulation results show that the preservation of the Lyapunov function leads to an improved performance, compared to the conventional discretization.

In this paper we introduce an impulsive Hopfield-type neural network system with piecewise constant argument of generalized type. Sufficient conditions for the existence of the unique equilibrium are obtained. Existence and uniqueness of solutions of such systems are established. Stability criterion based on linear approximation is proposed. Some sufficient conditions for the existence and stability of periodic solutions are derived. An example with numerical simulations is given to illustrate our results.

In this paper we introduce an impulsive Hopfield-type neural network system with piecewise constant argument of generalized type. Sufficient conditions for the existence of the unique equilibrium are obtained. Existence and uniqueness of solutions of such systems are established. Stability criterion based on linear approximation is proposed. Some sufficient conditions for the existence and stability of periodic solutions are derived. An example with numerical simulations is given to illustrate our results.

In this paper, we address the stability of a broad class of discrete-time hypercomplexvalued 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.

In this paper, we review three discrete-time complex-valued Hopfield neural networks (CvMHNNs) proposed recently in the literature. Contrary to what has been stated, we provide examples in which the sequences produced by these CvMHNN fails to converge under the usual conditions on the synaptic weight matrix, that is, the synaptic weight matrix is hermitian with non-negative diagonal elements. Furthermore, we present one CvMHNN model that always settle down to a stationary state under the usual conditions on the synaptic weights.

In this paper we introduce an impulsive Hopfield-type neural network system with piecewise constant argument of generalized type. Sufficient conditions for the existence of the unique equilibrium are obtained. Existence and uniqueness of solutions of such systems are established. Stability criterion based on linear approximation is proposed. Some sufficient conditions for the existence and stability of periodic solutions are derived. An example with numerical simulations is given to illustrate our results.

In this paper, we address the stability of a broad class of discrete-time hypercomplexvalued 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.

In this paper, we review three discrete-time complex-valued Hopfield neural networks (CvMHNNs) proposed recently in the literature. Contrary to what has been stated, we provide examples in which the sequences produced by these CvMHNN fails to converge under the usual conditions on the synaptic weight matrix, that is, the synaptic weight matrix is hermitian with non-negative diagonal elements. Furthermore, we present one CvMHNN model that always settle down to a stationary state under the usual conditions on the synaptic weights.