Finite-time stability on a class of SICNNs with neutral proportional delays

In this paper, the finite-time stability for a class of shunting inhibitory cellular neural networks with neutral proportional delays is discussed. By employing differential inequality techniques, several sufficient conditions are obtained to ensure the finite-time stability for the considered neural networks. Meanwhile, the generalized exponential synchronization is also established. An example along with its numerical simulation is presented to demonstrate the validity of the proposed results.

     

Finite-time stability analysis for fractional-order Cohen–Grossberg BAM neural networks with time delays

In this paper, the problem of finite-time stability for a class of fractional-order Cohen–Grossberg BAM neural networks with time delays is investigated. Using some inequality techniques, differential mean value theorem and contraction mapping principle, sufficient conditions are presented to ensure the finite-time stability of such fractional-order neural models. Finally, a numerical example and simulations are provided to demonstrate the effectiveness of the derived theoretical results.

     

Projective synchronization for fractional-order memristor-based neural networks with time delays

In this paper, the global projective synchronization for fractional-order memristor-based neural networks with multiple time delays is investigated via combining open loop control with the time-delayed feedback control. A comparison theorem for a class of fractional-order systems with multiple time delays is proposed. Based on the given comparison theorem and Lyapunov method, the synchronization conditions are derived under the framework of Filippov solution and differential inclusion theory. Several feedback control strategies are given to ensure the realization of complete synchronization, anti-synchronization and the stabilization for the fractional-order memristor-based neural networks with time delays. Finally, a numerical example is given to illustrate the effectiveness of the theoretical results.

     

Design and economic optimization of shell-and-tube heat exchanger using cohort intelligence algorithm

In this paper, the stability analysis problem is investigated for a new class of discrete-time singular neural networks with Markovian jump and mixed time-delays. The jumping parameters are generated from a discrete-time homogeneous Markov process, which are governed by a Markov process with discrete and finite state space. The mixed time-delays are composed of discrete and distributed delays. The activation functions are not required to be strictly monotonic and be differentiable. The purpose of this paper is to derive some delay-dependent sufficient conditions such that the singular neural networks to be regular, causal and stochastically stable in the mean square. Finally, numerical examples are also provided to illustrate the effectiveness of the proposed methods.

     

Pseudo Almost Periodic Solution of Recurrent Neural Networks with D Operator on Time Scales

This paper is concerned with a class of neutral type recurrent neural networks with time-varying delays, distributed delay and D operator on time–space scales which unify the continuous-time and the discrete-time recurrent neural networks under the same framework. Some sufficient conditions are given for the existence and the global exponential stability of the pseudo almost periodic solution by using inequality analysis techniques on time scales, fixed point theorem and the theory of calculus on time scales. An example is given to show the effectiveness of the derived results via computer simulations.

     

Pinning Synchronization of Complex Dynamical Networks on Time Scales

The purpose of this paper is to investigate the synchronization problem of complex dynamical networks on time scales, which includes the synchronization problem of continuous-time and discrete-time complex dynamical networks as special cases. A pinning control strategy is designed to achieve synchronization of complex dynamical networks on time scales. Based on the theory of calculus on time scales and the Lyapunov method, pinning synchronization criteria for complex dynamical networks on time scales are established. Moreover, a numerical example is given to verify the effectiveness of theoretical results.

     

Multistability of complex-valued neural networks with distributed delays

This paper addresses the multistability problem for the complex-valued neural networks with appropriate real–imaginary-type activation functions and distributed delays. Based on the geometrical properties of the activation functions and the fixed point theory, several sufficient criteria are obtained which not only guarantee the existence of \(9^n\) equilibrium points but also assure the local exponential stability for the \(4^n\) equilibrium points of them. Furthermore, the attraction basins of the \(4^n\) equilibrium points are also estimated, which infers that the attraction basins could be enlarged under some mild restrictions. Finally, one numerical example is provided to illustrate the effectiveness of the obtained results.

     

Stability results for Takagi–Sugeno fuzzy uncertain BAM neural networks with time delays in the leakage term

This paper deals with the delay-dependent asymptotic stability analysis problem for a class of fuzzy bidirectional associative memory (BAM) neural networks with time delays in the leakage term by Takagi–Sugeno (T–S) fuzzy model. The nonlinear delayed BAM neural networks are first established as a modified T–S fuzzy model in which the consequent parts are composed of a set of BAM neural networks with time-varying delays. The parameter uncertainties are assumed to be norm bounded. Some new delay-dependent stability conditions are derived in terms of linear matrix inequality by constructing a new Lyapunov–Krasovskii functional and introducing some free-weighting matrices. Even there is no leakage delay, the obtained results are also less restrictive than some recent works. It can be applied to BAM neural networks with activation functions without assuming their boundedness, monotonicity, or differentiability. Numerical examples are given to demonstrate the effectiveness of the proposed methods.

     

On finite-time and fixed-time consensus algorithms for dynamic networks switching among disconnected digraphs

ABSTRACT

This paper aims to analyse the stability of a class of consensus algorithms with finite-time or fixed-time convergence for dynamic networks composed of agents with first-order dynamics. In particular, in the analysed class a single evaluation of a nonlinear function of the consensus error is performed per each node. The classical assumption of switching among connected graphs is dropped here, allowing to represent failures and intermittency in the communications between agents. Thus, conditions to guarantee finite and fixed-time convergence, even while switching among disconnected graphs, are provided. Moreover, the algorithms of the considered class are computationally simpler than previously proposed finite-time consensus algorithms for dynamic networks, which is an essential feature in scenarios with computationally limited nodes and energy efficiency requirements such as in sensor networks. Simulations illustrate the performance of the proposed consensus algorithms. In the presented scenarios, results show that the settling time of the considered algorithms grows slower than other consensus algorithms for dynamic networks as the number of nodes increases.     

Resilient Filtering for Delayed Markov Jump Neural Networks via Event-triggered Strategy

This paper deals with the event triggered filtering problem for a class of delayed discrete-time Markov jump neural networks, where a resilient filter with parameter uncertainties is adopted. The aim of this paper is to design a suitable filter which ensures that the filtering error system is stochastically stable and satisfies a prescribed mixed passivity and H_∞ performance. Sufficient conditions for solvability of such a problem are developed. Based on the obtained conditions, an explicit expression of the desired resilient filter is proposed. Finally, an example is presented to show the usefulness of the proposed scheme.

     

An MLP-based representation of neural tensor networks for the RDF data models

In this paper, a new representation of neural tensor networks is presented. Recently, state-of-the-art neural tensor networks have been introduced to complete RDF knowledge bases. However, mathematical model representation of these networks is still a challenging problem, due to tensor parameters. To solve this problem, it is proposed that these networks can be represented as two-layer perceptron network. To complete the network topology, the traditional gradient based learning rule is then developed. It should be mentioned that for tensor networks there have been developed some learning rules which are complex in nature due to the complexity of the objective function used. Indeed, this paper is aimed to show that the tensor network can be viewed and represented by the two-layer feedforward neural network in its traditional form. The simulation results presented in the paper easily verify this claim.

     

Stability analysis of stochastic memristor-based recurrent neural networks with mixed time-varying delays

In this paper, the stability problem of stochastic memristor-based recurrent neural networks with mixed time-varying delays is investigated. Sufficient conditions are established in terms of linear matrix inequalities which can guarantee that the stochastic memristor-based recurrent neural networks are asymptotically stable and exponentially stable in the mean square, respectively. Two examples are given to demonstrate the effectiveness of the obtained results.

     

Rethinking labelling in road segmentation

ABSTRACT

Deep models are extremely data hungry. Their success is being driven by the availability of large amounts of data for training. For semantic segmentation tasks on aerial and satellite imagery, a major dilemma at present is that it still relies heavily on manual labelling of data. Among these tasks, the semantic segmentation of road is special since it is possible to use auxiliary data, such as GPS track data, to automatically label data. For a better understanding of this possibility, this paper proposes to rethink some basic issues of labelling approaches for roads.

We experimentally investigated the unavoidable class imbalance problem in road segmentation tasks through simulated and real datasets and quantitatively show that class imbalance has a serious detrimental impact on deep model’s generalization performance. We also observed that the detrimental impact even outweighs the benefits of strictly annotating roads – expanding road labels can give deep networks better segmentation accuracy, even though the segmentation location is no longer the edge of the road. We think this is because the impact of class imbalance is much overwhelming than the sensitivity of DNN on the edges of real roads. This finding is valuable for supporting the use of centreline-based approaches in place of edge-based approaches in some applications for better cost-effective solutions.

We proposed a guided Random Sample Consensus (RANSAC) algorithm to determine the optimal expansion ratio of road label. On these bases, we further proposed a general framework to combine two networks to achieve better performance than the state-of-the-art performance of using alone. We attribute this to the alleviation of the class imbalance problem because simply cascading the two networks does not achieve the purpose of improving accuracy in our experiments. We believe that this work is enlightening for studies of road segmentation.     

1D convolutional neural networks for chart pattern classification in financial time series

This paper proposes a novel deep learning-based approach for financial chart patterns classification. Convolutional neural networks (CNNs) have made notable achievements in image recognition and computer vision applications. These networks are usually based on two-dimensional convolutional neural networks (2D CNNs). In this paper, we describe the design and implementation of one-dimensional convolutional neural networks (1D CNNs) for the classification of chart patterns from financial time series. The proposed 1D CNN model is compared against support vector machine, extreme learning machine, long short-term memory, rule-based and dynamic time warping. Experimental results on synthetic datasets reveal that the accuracy of 1D CNN is highest among all the methods evaluated. Results on real datasets also reveal that chart patterns identified by 1D CNN are also the most recognized instances when they are compared to those classified by other methods.

     

Bifurcation Mechanisation of a Fractional-Order Neural Network with Unequal Delays

The theme of bifurcation for a class of fractional-order neural networks (FONNs) with unique delay has been incalculably elucidated. It exhibits that multiple delays are capable of increasing the complicacy of realistic FONNs, but this has been insufficiently probed into. This paper attempts to conduct a research on the stability and bifurcation for a FONN with two unequal delays. By intercalating one delay and taking remnant delay as a bifurcation parameter, the incongruent critical values of diverse delays-induced bifurcations are exactly gained. Eventually, confirmation experiments are offered to endorse the procured theory.

     

时延复杂网络的自适应周期间歇同步控制

研究同时具有耦合时延和节点时延复杂网络的自适应周期间歇同步控制问题.运用 Lyapunov 稳定性理论,自适应控制、牵制控制和间歇控制方法,给出保证该时延复杂网络全局指数同步、且保守性更小的判定准则,并给出相应的自适应和牵制自适应间歇同步控制器设计,该控制策略对节点间的耦合强度和网络的拓扑结构等具有较强的鲁棒性.最后以时延非线性动力系统为节点对复杂网络进行数值仿真,验证了结论的正确性和有效性.     

New exponential passivity of BAM neural networks with time-varying delays

In this paper, the exponential passivity for bidirectional associative memory (BAM) neural networks with time-varying delays is considered. In our study, the lower and upper bounds of the activation functions are allowed to be either positive, negative or zero. By constructing new and improved Lyapunov–Krasovskii functional and introducing free-weighting matrices, a new and improved delay-dependent exponential passivity criterion for BAM neural networks with time-varying delays is derived in the form of linear matrix inequality (LMI). A numerical example is given to show that the derived condition is less conservative than some existing results given in the literature.

     

PROPERTIES OF ANALOGUE NEURAL NETWORKS

Abstract

Spatially discrete analogue neural networks and spatially continuous analogue neural networks are considered in this paper in studying the fundamental properties of analogue neural networks. A model of neural networks is discussed.     

New stochastic synchronization criteria for fuzzy Markovian hybrid neural networks with random coupling strengths

This paper focuses on the stochastic synchronization problem for a class of fuzzy Markovian hybrid neural networks with random coupling strengths and mode-dependent mixed time delays in the mean square. First, a novel free-matrix-based single integral inequality and two novel free-matrix-based double integral inequalities are established. Next, by employing a novel augmented Lyapunov–Krasovskii functional with several mode-dependent matrices, applying the theory of Kronecker product of matrices, Barbalat’s Lemma and the new free-matrix-based integral inequalities, two delay-dependent conditions are established to achieve the globally stochastic synchronization for the mode-dependent fuzzy hybrid coupled neural networks. Finally, two numerical examples with simulation are provided to illustrate the effectiveness of the presented criteria.

     

A metrology-based approach for measuring the social dimension of cognitive trust in collaborative networks

This paper addresses the measurement of the social dimension of cognitive trust in collaborative networks. Trust indicators are typically measured and combined in literature in order to calculate partners’ trustworthiness. When expressing the result of a measurement, some quantitative indication of the quality of the result—the uncertainty of measurement—should be given. However, currently this is not taken into account for the measurement of the social dimension of cognitive trust in collaborative networks. In view of this, an innovative metrology-based approach for the measurement of social cognitive trust indicators in collaborative networks is presented. Thus, a measurement result is always accompanied by its uncertainty of measurement, as well as by information traditionally used to properly interpret the results: the sample size, and the standard deviation of the sample.