Experimental verification of a memristive neural network

This paper presents an electronic circuit able to emulate the behavior of a neural network based on memristive synapses. The latter is built with two flux-controlled floating memristor emulator circuits operating at high frequency and two passive resistors. Synapses are connected in a way that a bridge circuit is obtained, and its dynamical behavioral model is derived from characterizing memristive synapses. Analysis of the memristor characteristics for obtaining a suitable synaptic response is also described. A neural network of one neuron and two inputs is connected using the proposed topology, where synaptic positive and negative weights can easily be reconfigured. The behavior of the proposed artificial neural network based on memristors is verified through MATLAB, HSPICE simulations and experimental results. Synaptic multiplication is performed with positive and negative weights, and its behavior is also demonstrated through experimental results getting 6% of error.     

Initial offset boosting coexisting attractors in memristive multi-double-scroll Hopfield neural network

Nonlinear Dynamics - Memristors are widely considered to be promising candidates to mimic biological synapses. In this paper, by introducing a non-ideal flux-controlled memristor model into a...     

Hyperchaotic memristive ring neural network and application in medical image encryption

Nonlinear Dynamics - Neural networks are favored by academia and industry because of their diversity of dynamics. However, it is difficult for ring neural networks to generate complex dynamical...     

Chimera states and synchronization behavior in multilayer memristive neural networks

To study the effect of electromagnetic induction on the spatiotemporal dynamic behavior of neural networks, in this paper, we have mainly studied both the synchronization behavior and the evolution of chimera states (CS) in coupled neural networks. To do this, a multilayer memristive neural network was constructed by selecting the Hindmarsh–Rose neurons as the network nodes, and the effect of electromagnetic induction is introduced by using the cubic flux-controlled memristive model as synapse. For simplicity, the following coupling scheme is adopted: only the coupling connections for the neurons between different layers are considered with memristive synapses, while those neurons in each layer are still bidirectional coupled with the classical electrical synapses. It is found that, by adjusting the coupled strength of electrical synapses and the parameters of memristive synapses, the coexistence behavior of coherent and incoherent states, i.e., the CS, could appear in each layer. It is interesting that the CS are also found in inter-layer memristive synapse network. Furthermore, we have discussed the synchronization behavior in this multilayer memristive neural network, one can find when the whole multilayer network is in a synchronization state, not only the spatiotemporal consistency of the CS in each layer neural networks is observed, but also the memductance of all memristive synapses is completely synchronized. Our results suggest that the electromagnetic induction may play an important role in regulating the dynamic behavior of neural networks, and the introduction of memristive synapse into the biological neural network will provide useful clues for revealing the memory behavior of the neural system in human brain.     

On properties of hyperchaos: Case study

Some properties of hyperchaos are exploited by studying both uncoupled and coupled CML. In addition to usual properties of chaotic strange attractors, there are other interesting properties, such as: the number of unstable periodic points embedded in the strange attractor increases dramatically increasing and a large number of low-dimensional chaotic invariant sets are contained in the strange attractor. These properties may be useful for regarding the edge of chaos as the origin of complexity of dynamical systems. The project supported by the National Natural Science Foundation of China     

On the asymptotic stability of a neural network on a time scale

We establish sufficient conditions for the global asymptotic stability of an equilibrium state of a neural network on a time scale. We give new sufficient conditions for the function of the system to be regressive and new sufficient conditions for the existence and uniqueness of an equilibrium state of a neural network.     

Different impulsive effects on synchronization of fractional-order memristive BAM neural networks

This paper considered exponential synchronization in fractional-order memristive BAM neural networks (FMBAMNNs) with time delay via switching jumps mismatch. Exponential function is introduced for studying fractional-order differential system. According to double-layer structure of FMBAMNNs, two controllers are designed for the response FMBAMNNs. Particularly, more wide ranges of impulsive effects, which are affected by fractional-order \(\alpha \), are discussed in detail. One case is that the impulsive effect contributes to system convergence, and the other is that the impulsive effect destroys the system convergence. Based on the fractional stability theory and the definition of average impulsive interval, several criteria for achieving synchronization of FMBAMNNs are established. For different impulsive effects, the rate of convergence is precisely expressed. Finally, numerical examples verify the validity of the theoretical results.     

Stability in a model of a delayed neural network

The stability of the null solution in a system of coupled cells is investigated. Each cell evolves according to Hopfield's equation for an analog circuit, with a delay incorporated to account for finite switching speed of amplifiers. A necessary and sufficient condition on the connection matrix is obtained for delay-induced oscillations to be possible in a general (not necessarily symmetric) network.     

基于深度卷积神经网络的SAR图像舰船小目标检测

针对合成孔径雷达(SAR)图像舰船目标背景复杂的特点,提出一种基于改进YOLOv3的SAR图像舰船小目标检测算法。首先,通过分析残差网络的设计原理,针对不同场景下舰船目标的特点,重新设计底层残差单元;其次,改进特征金字塔的网络结构,解决感受野与定位之间的矛盾问题,提高了小尺度舰船的检测效果;最后,通过引入平衡因子,优化损失函数中的小目标权重。实验结果显示,相比原始YOLOv3方法,所提方法在舰船目标公开数据集上F1值提高6.3%,同时,较快的检测速度使得所提算法可用于实时目标检测。     

Global stability and stabilization for inertial memristive neural networks with unbounded distributed delays

Nonlinear Dynamics - This paper investigates the stability and stabilization of inertial memristive neural networks (IMNNs) with discrete and unbounded distributed delays. The considered IMNNs are...     

Hopf-zero bifurcation in a generalized Gopalsamy neural network model

In this paper, we study Hopf-zero bifurcation in a generalized Gopalsamy neural network model. By using multiple time scales and center manifold reduction methods, we obtain the normal forms near a Hopf-zero critical point. A comparison between these two methods shows that the two normal forms are equivalent. Moreover, bifurcations are classified in two-dimensional parameter space near the critical point, and numerical simulations are presented to demonstrate the applicability of the theoretical results.     

Chaotic dynamics in a neural network under electromagnetic radiation

In this paper, a small Hopfield neural network with three neurons is studied, in which one of the three neurons is considered to be exposed to electromagnetic radiation. The effect of electromagnetic radiation is modeled and considered as magnetic flux across membrane of the neuron, which contributes to the formation of membrane potential, and a feedback with a memristive type is used to describe coupling between magnetic flux and membrane potential. With the electromagnetic radiation being considered, the previous steady neural network can present abundant chaotic dynamics. It is found that hidden attractors can be observed in the neural network under different conditions. Moreover, periodic motion and chaotic motion appear intermittently with variations in some system parameters. Particularly, coexistence of periodic attractor, quasiperiodic attractor, and chaotic strange attractor, coexistence of bifurcation modes and transient chaos can be observed. In addition, an electric circuit of the neural network is implemented in Pspice, and the experimental results agree well with the numerical ones.     

ON THE ASYMPTOTIC BEHAVIOR OF HOPFIELD NEURAL NETWORK WITH PERIODIC INPUTS

ＩｎｔｒｏｄｕｃｔｉｏｎＳｉｎｃｅｔｈｅｓｐｅｃｉａｌｓｕｐｅｒｉｏｒｉｔｙｏｆａｒｔｉｆｉｃｉａｌｎｅｕｒａｌｎｅｔｗｏｒｋｓｔｅｃｈｎｏｌｏｇｙｉｎｖａｒｉｏｕｓｅｎｇｉｎｅｅｒｉｎｇｔｅｃｈｎｉｑｕｅｓｆｉｅｌｄｓ,ｓｕｃｈａｓｏｐｔｉｍｉｚａｔｉｏｎ ,ａｓｓｏｃｉａｔｉｖｅｍｅｍｏｒｉｅｓ,ｐａｔｔｅｒｎｒｅｃｏｇｎｉｔｉｏｎ ,ｓｉｇｎａｌｐｒｏｃｅｓｓｉｎｇａｎｄａｕｔｏｍａｔｉｃｃｏｎｔｒｏｌ,ｔｈｅｒｅｈａｓｂｅｅｎｉｎｃｒｅａｓｉｎｇｉｎｔｅｒｅｓｔｉｎｔｈｅｉｎｖｅｓｔｉｇａｔｉ…     

Dynamics of a multiplex neural network with delayed couplings

Multiplex networks have drawn much attention since they have been observed in many systems, e.g., brain, transport, and social relationships. In this paper, the nonlinear dynamics of a multiplex network with three neural groups and delayed interactions is studied. The stability and bifurcation of the network equilibrium are discussed, and interesting neural activities of the network are explored. Based on the neuron circuit,transfer function circuit, and time delay circuit, a circuit platform of...     

四旋翼飞行器分散PID神经元网络控制

针对四旋翼飞行器的非线性控制问题,提出了一种分散PID神经元网络(PIDNN)控制方法。首先通过牛顿—欧拉方程建立了四旋翼飞行器的动力学模型。其次,提出了一种嵌套控制器,内环基于分散PIDNN方法以实现姿态控制,外环采用经典的PID控制方法,PIDNN控制器的在线学习通过误差反向传播法实现。搭建了自主研制的四旋翼飞行器系统,并通过实验的方式研究了控制器的控制性能。实验结果表明控制器具有较强的控制稳定性、机动性和鲁棒性。     

Stability of a class of neural network models with delay

ＩｎｔｒｏｄｕｃｔｉｏｎＲｅｃｅｎｔｌｙ,ｔｈｅｏｒｅｔｉｃａｌａｎｄａｐｌｉｅｄｓｔｕｄｉｅｓｏｆｎｅｕｒａｌｎｅｔｗｏｒｋｍｏｄｅｌｈａｖｅｂｅｎｔｈｅｎｅｗｆｏｃｕｓｏｆｓｔｕｄｉｅｓｉｎｔｈｅｗｏｒｌｄ．Ｉｔｉｓｗｅｌ＿ｋｎｏｗｎｔｈａｔｑｕ...