忆阻突触耦合Hopfield神经网络的初值敏感动力学

该文报道了3神经元Hopfield神经网络(HNN)在电磁感应电流作用下的初值敏感动力学。利用非理想忆阻突触,模拟由两个相邻神经元膜电位之差引起的电磁感应电流,构建了一种简单的4维忆阻Hopfield神经网络模型。借助理论分析和数值仿真,分析了不同忆阻突触耦合强度下的复杂动力学行为,揭示了与状态初值密切相关的特殊动力学行为。最后,设计了该忆阻HNN的模拟等效实现电路,并由PSIM电路仿真验证了MATLAB数值仿真的正确性。     

一种新型绝对值忆阻耦合自突触Hopfield神经网络的动力学分析及其电路实现

神经元作为大脑基本的组成单元能够产生复杂的动力学行为。目前大部分的研究是关于两个神经元系统的忆阻耦合突触,而忆阻耦合自突触权重的单神经元模型的研究相对较少。本文提出了绝对值忆阻耦合自突触权值的Hopfield神经网络(HNN)模型,以自耦合权重作为唯一的调节参数。利用基本的动力学分析方法,讨论了不同耦合强度下系统的动力学行为,研究了不同初始值下对称吸引子的共存行为。结果表明,这些丰富的非线性动力学行为包括周期倍增分岔、混沌、周期窗和对称自激吸引子共存。最后,通过PSpice仿真验证了所提出的忆阻HNN的理论分析结果的正确性。     

基于忆阻器的新型四阶超混沌电路

在一个三维自治系统中引入三次非线性磁控忆阻器,得到了一个新的四维忆阻超混沌系统。通过分析该系统的动力学行为,发现它具有线平衡点,存在共存吸引子。通过MATLAB编程计算出Lyapunov指数,结果证明了该系统存在超混沌行为。Simulink数值仿真得到的相图和基于忆阻等效电路设计的PSpice电路仿真相图完全对应一致,验证了系统的正确性与有效性。     

基于二值和三值忆阻器模型构建的混沌系统的特性分析

近年来,基于忆阻器的非线性动力学问题备受关注。该文以二值和三值忆阻器为例分析了二值和多值忆阻器对于混沌系统动力特性的影响。首先,将二值忆阻器引入Chen系统,构建了一个4维的基于二值忆阻器的混沌系统(BMCS)。其次,使用三值忆阻器替换上述系统中的二值忆阻器,构建一个4维的基于三值忆阻器的混沌系统(TMCS)。通过理论分析与数值仿真,从多个角度对比了两个混沌系统之间的动力学特性差异,如Lyapunov指数、分岔图、系统的平衡点、系统稳定性、对初值的敏感性以及系统的复杂度分析等。结果表明,两个基于忆阻器的混沌系统都具有无穷多个平衡点,二者产生的吸引子均为隐藏吸引子,且都存在的暂态混沌现象,但三值忆阻混沌系统具有超混沌特性,且相比二值忆阻混沌系统具有更强的初值敏感性以及更大的参数取值区间。分析得出基于三值忆阻器构建的混沌系统比基于二值忆阻器的混沌系统能够产生更为复杂的动力学特性,混沌信号也更为复杂。     

基于忆阻器的混沌、存储器及神经网络电路研究进展

忆阻器是除电阻、电容、电感之外发现的第4种基本电子元件,它是一种具有记忆特性的非线性器件,可用于混沌、存储器、神经网络等电路与系统的实现。该文对基于忆阻器的混沌电路、存储器、神经网络电路的设计与神经动力学的国内外研究进行了综述,并给出了对它们的研究展望。     

基于分数阶忆阻器的混沌电路分析与设计

提出了一种新型的分数阶忆阻混沌电路.首先,建立了分数阶忆阻器的数学模型,通过数值仿真验证了分数阶广义忆阻器满足忆阻器的基本特性.然后,将分数阶广义忆阻器与蔡氏振荡电路相结合,建立了一种基于分数阶广义忆阻器的混沌电路模型.通过稳定性理论,对分数阶系统的稳定性进行了分析.为了进一步研究电路参数对系统动态行为的影响,利用相位...     

无平衡点忆阻超混沌系统的动力学分析及电路实现

为了探索忆阻超混沌系统更加丰富的动力学行为,在一个可通过调节常数项得到对称吸引子的四维混沌系统上引入磁控忆阻器,提出一个新型无平衡点的忆阻超混沌系统。采用分岔图、Lyapunov指数谱与相图等动力学分析方法对该忆阻超混沌系统进行研究,得到如下结果：新系统存在依赖于忆阻器初值的具有对称性的隐藏超级多稳定性,随系统参数改变而呈现的复杂隐藏动力学,丰富的状态转移行为以及偏移增量控制行为等。最后,设计并实现了该忆阻超混沌系统的实物电路,验证了系统的可实现性。     

基于忆阻循环神经网络的层次化状态正则变分自编码器

变分自编码器(VAE)作为一个功能强大的文本生成模型受到越来越多的关注。然而,变分自编码器在优化过程中容易出现后验崩溃,即忽略潜在变量,退化为一个自编码器。针对这个问题,该文提出一种新的变分自编码器模型,通过层次化编码和状态正则方法,可以有效缓解后验崩溃,且相较于基线模型具有更优的文本生成质量。在此基础上,基于纳米级忆阻器,将提出的变分自编码器模型与忆阻循环神经网络(RNN)结合,设计一种基于忆阻循环神经网络的硬件实现方案,即层次化变分自编码忆组神经网络(HVAE-MNN),探讨模型的硬件加速。计算机仿真实验和结果分析验证了该文模型的有效性与优越性。     

Hopfield神经网络的存贮容量

我们把理论推导与数值模拟相结合得出一个较好的误差函数近似解析式。应用该解析式分析了Ｈｏｐｆｉｅｌｄ神经网络绝对存同容量，得到了一更严格的结果。     

Object recognition using multilayer Hopfield neural network

An object recognition approach based on concurrent coarse-and-fine matching using a multilayer Hopfield neural network is presented. The proposed network consists of several cascaded single-layer Hopfield networks, each encoding object features at a distinct resolution, with bidirectional interconnections linking adjacent layers. The interconnection weights between nodes associating adjacent layers are structured to favor node pairs for which model translation and rotation, when viewed at the two corresponding resolutions, are consistent. This interlayer feedback feature of the algorithm reinforces the usual intralayer matching process in the conventional single-layer Hopfield network in order to compute the most consistent model-object match across several resolution levels. The performance of the algorithm is demonstrated for test images containing single objects, and multiple occluded objects. These results are compared with recognition results obtained using a single-layer Hopfield network.     

动态泛回归神经网络预测的研究与仿真

在HUATECA3000过程控制实验系统上选取实验对象,研究了三容水箱液位非线性控制系统,提出了一种动态泛回归神经网络预测控制算法.先后通过开环与闭环控制,搭建了SIMUUNK仿真模型研究算法的有效性.仿真结果表明闭环预测控制改进了系统在干扰作用下的稳态和动态性能.     

Block truncation coding using Hopfield neural network

The authors extend the analysis of the block truncation coding (BTC) algorithm using a Hopfield neural network (HNN). They show that its performance is suboptimum (in the mean square error sense) and that alternative (non-neural network) BTC algorithms are available with virtually the same performance.<>     

QoS provisioning dynamic connection-admission control for multimedia wireless networks using a Hopfield neural network

This paper presents a quality-of-service (QoS) provisioning dynamic connection-admission control (CAC) algorithm for multimedia wireless networks. A multimedia connection consists of several substreams (i.e., service classes), each of which presets a range of feasible QoS levels (e.g., data rates). The proposed algorithm is mainly devoted to finding the best possible QoS levels for all the connections (i.e., QoS vector) that maximize resource utilization by fairly distributing wireless resources among the connections while maximizing the statistical multiplexing gain (i.e., minimizing the blocking and dropping probabilities). In the case of congestion (overload), the algorithm uniformly degrades the QoS levels of the existing connections (but only slightly) in order to spare some resources for serving new or handoff connections, thereby naturally minimizing the blocking and dropping probabilities (it amounts to maximizing the statistical multiplexing gain). The algorithm employs a Hopfield neural network (HNN) for finding a QoS vector. The problem itself is formulated as a multi-objective optimization problem. Hardware-based HNN exhibits high (computational) speed that permits real time running of the CAC algorithm. Simulation results show that the algorithm can maximize resource utilization and maintain fairness in resource sharing, while maximizing the statistical multiplexing gain in providing acceptable service grades. Furthermore, the results are relatively insensitive to handoff rates.     

Applying Hopfield neural network to QoS routing in communication network

The main goal of routing solutions is to satisfy the requirements of the Quality of Service （QoS） for every admitted connection as well as to achieve a global efficiency in resource utilization. In this paper proposes a solution based on Hopfield neural network （HNN） to deal with one of representative routing problems in uni-cast routing, i. e. the multi-constrained（MC） routing problem. Computer simulation shows that we can obtain the optimal path very rapidly with our new Lyapunov energy functions.     

Superresolution algorithms for a modified Hopfield neural network

The authors describe the implementation of a superresolution (or spectral extrapolation) procedure on a neural network, based on the Hopfield (1982) model. They show the computational advantages and disadvantages of such an approach for different coding schemes and for networks consisting of very simple two-state elements as well as those made up of more complex nodes capable of representing a continuum. It is demonstrated that, with the appropriate hardware, there is a computational advantage in using the Hopfield architecture over some alternative methods for computing the same solution. The relationship between a particular mode of operation of the neural network and the regularized Gerchberg (1974) and Papoulis (1975) algorithm is also discussed     

Shortest path routing algorithm using Hopfield neural network

A near-optimal routing algorithm employing a modified Hopfield neural network (HNN) is presented. Since it uses every piece of information that is available at the peripheral neurons, in addition to the highly correlated information that is available at the local neuron, faster convergence and better route optimality is achieved than with existing algorithms that employ the HNN. Furthermore, all the results are relatively independent of network topology for almost all source-destination pairs     

Two-neuron-based non-autonomous memristive Hopfield neural network: Numerical analyses and hardware experiments

This paper explores a two-neuron-based non-autonomous memristive Hopfield neural network (mHNN) through numerical analyses and hardware experiments. It is interested that the locus and stability of the AC equilibrium point for the mHNN change with the time evolution. Dynamical behaviors associated with the self-coupling strength of the memristive synapse are numerically investigated by bifurcation diagrams, Lyapunov exponents and phase portraits. Particularly, bursting behaviors are revealed when the order gap exists between the natural frequency and external stimulus frequency. The interesting phenomena are illustrated through phase portraits, transmitted phase portraits, and time-domain waveforms of two cases. Moreover, breadboard experimental investigations are carried out, which effectively verify the numerical simulations.