A Hopfield-like hippocampal CA3 neural network model for studying associative memory in Alzheimer's disease

Associative memory, one of the major cognitive functions in the hippocampal CA3 region, includes auto-associative memory and hetero-associative memory. Many previous studies have shown that Alzheimer＇s disease （AD） can lead to loss of functional synapses in the central nervous system, and associative memory functions in patients with AD are often impaired, but few studies have addressed the effect of AD on hetero-associative memory in the hippocampal CA3 region. In this study, based on a simplified anatomical structure and synaptic connections in the hippocampal CA3 region, a three-layered Hopfield-like neural network model of hippocampal CA3 was proposed and then used to simulate associative memory functions in three circumstances： normal, synaptic deletion and synaptic compensation, according to Ruppin＇s synaptic deletion and compensation theory. The influences of AD on hetero-associative memory were further analyzed. The simulated results showed that the established three-layered Hopfield-like neural network model of hippocampal CA3 has both auto-associative and hetero-associative memory functions. With increasing synaptic deletion level, both associative memory functions were gradually impaired and the mean firing rates of the neurons within the network model were decreased. With gradual increasing synaptic compensation, the associative memory functions of the network were improved and the mean firing rates were increased. The simulated results suggest that the Hopfield-like neural network model can effectively simulate both associative memory functions of the hippocampal CA3 region. Synaptic deletion affects both auto-associative and hetero-associative memory functions in the hippocampal CA3 region, and can also result in memory dysfunction. To some extent, synaptic compensation measures can offset two kinds of associative memory dysfunction caused by synaptic deletion in the hippocampal CA3 area.

Self-correcting wavelet neural network control of continuous rotary electro-hydraulic servo motor

In allusion to the problem of friction,leakage,vibration and noise existing in continuous rotary motor electro-hydraulic servo system,highly nonlinearity and uncertainties affecting the system performance,based on the transfer function of electro-hydraulic servo system,a kind of Pol-Ind friction model is proposed.The parameters of Pol-Ind friction model are identified and the accurate mathematical model of friction torque is obtained by experiment.The self-correcting wavelet neural network(WNN)controller is proposed,and Adam optimization algorithm is used to perform gradient optimization on scale factor and displacement factor in wavelet basis function,so as to improve the speed and precision of parameter optimization.Through comparative simulation analysis,it is clearly that the self-correcting WNN controller can effectively improve the frequency response and tracking accuracy of continuous rotary motor electro-hydraulic servo system.

Novel stability criteria for fuzzy Hopfield neural networks based on an improved homogeneous matrix polynomials technique

The global stability problem of Takagi-Sugeno（T-S） fuzzy Hopfield neural networks（FHNNs） with time delays is investigated.Novel LMI-based stability criteria are obtained by using Lyapunov functional theory to guarantee the asymptotic stability of the FHNNs with less conservatism.Firstly,using both Finsler＇s lemma and an improved homogeneous matrix polynomial technique,and applying an affine parameter-dependent Lyapunov-Krasovskii functional,we obtain the convergent LMI-based stability criteria.Algebraic properties of the fuzzy membership functions in the unit simplex are considered in the process of stability analysis via the homogeneous matrix polynomials technique.Secondly,to further reduce the conservatism,a new right-hand-side slack variables introducing technique is also proposed in terms of LMIs,which is suitable to the homogeneous matrix polynomials setting.Finally,two illustrative examples are given to show the efficiency of the proposed approaches.

Nonlinear model predictive control based on hyper chaotic diagonal recurrent neural network

Nonlinear model predictive controllers(NMPC)can predict the future behavior of the under-controlled system using a nonlinear predictive model.Here,an array of hyper chaotic diagonal recurrent neural network(HCDRNN)was proposed for modeling and predicting the behavior of the under-controller nonlinear system in a moving forward window.In order to improve the convergence of the parameters of the HCDRNN to improve system’s modeling,the extent of chaos is adjusted using a logistic map in the hidden layer.A novel NMPC based on the HCDRNN array(HCDRNN-NMPC)was proposed that the control signal with the help of an improved gradient descent method was obtained.The controller was used to control a continuous stirred tank reactor(CSTR)with hard-nonlinearities and input constraints,in the presence of uncertainties including external disturbance.The results of the simulations show the superior performance of the proposed method in trajectory tracking and disturbance rejection.Parameter convergence and neglectable prediction error of the neural network(NN),guaranteed stability and high tracking performance are the most significant advantages of the proposed scheme.

Nonlinear model predictive control with guaranteed stability based on pseudolinear neural networks

A nonlinear model predictive control problem based on pseudo-linear neural network (PNN) is discussed, in which the second order on-line optimization method is adopted. The recursive computation of Jacobian matrix is investigated. The stability of the closed loop model predictive control system is analyzed based on Lyapunov theory to obtain the sufficient condition for the asymptotical stability of the neural predictive control system. A simulation was carried out for an exothermic first-order reaction in a continuous stirred tank reactor.It is demonstrated that the proposed control strategy is applicable to some of nonlinear systems.

Theoretical Study of Continuous B-Cell Epitopes with Developed BP Neural Network

In order to identify continuous B-cell epitopes effectively and to increase the success rate of experimental identification, the modified Back Propagation artificial neural network (BP neural network) was used to predict the continuous B-cell epitopes, and finally the predictive model for the B-cells epitopes was established. Comparing with the other predictive models, the prediction performance of this model is more excellent (AUC = 0.723). For the purpose of verifying the performance of the model, the prediction to the SWISS PROT NUMBER: P08677 was carried on, and the satisfying results were obtained.

Continuous Variable Quantum MNIST Classifiers—Classical-Quantum Hybrid Quantum Neural Networks

In this paper, classical and continuous variable (CV) quantum neural network hybrid multi-classifiers are presented using the MNIST dataset. Currently available classifiers can classify only up to two classes. The proposed architecture allows networks to classify classes up to nm classes, where n represents cutoff dimension and m the number of qumodes on photonic quantum computers. The combination of cutoff dimension and probability measurement method in the CV model allows a quantum circuit to produce output vectors of size nm. They are then interpreted as one-hot encoded labels, padded with nm - 10 zeros. The total of seven different classifiers is built using 2, 3, …, 6, and 8-qumodes on photonic quantum computing simulators, based on the binary classifier architecture proposed in “Continuous variable quantum neural networks” [1]. They are composed of a classical feed-forward neural network, a quantum data encoding circuit, and a CV quantum neural network circuit. On a truncated MNIST dataset of 600 samples, a 4-qumode hybrid classifier achieves 100% training accuracy.

利用连续Hopfield网络(CHNN)实现低分辨仪器的高分辨观测

结合直接解调技术,重点推导论证了利用连续Hopfield网络实现低分辩仪器的高分辨观测,并建立了相应的神经网络模型。经实验表明了该方法的实际可行性,具有较好的推广能力。

A RESULT ON THE STRUCTURAL FEATURES OF MONOLAYERED NEURAL NETWORKS

In order to explore the structural features of neural networks and the ap-proaches to local interconnection,the geometrical structural information is introduced tothe Hopfield neural network model which is applied to associative memory.The dynamicsof the recalling is studied theoretically and cxpcrimcntally.The rcsults show that the geo-metrical structural information is helpless to the associative memory of monolayeredneural networks,furthermore,it makes the error probability increased.If the geometricalstructural information of the stored patterns is necessary to be introduced,somc new ap-proaches have to be explored.

Block and parallel modelling of broad domain nonlinear continuous mapping based on NN

The necessity of the use of the block and parallel modeling of the nonlinear continuous mappings with NN is firstly expounded quantitatively. Then, a practical approach for the block and parallel modeling of the nonlinear continuous mappings with NN is proposed. Finally, an example indicating that the method raised in this paper can be realized by suitable existed software is given. The results of the experiment of the model discussed on the 3-D Mexican straw hat indicate that the block and parallel modeling based on NN is more precise and faster in computation than the direct ones and it is obviously a concrete example and the development of the large-scale general model established by Tu Xuyan.

AN ALGORITHM FOR VLSI CHANNEL ROUTING USING NEURAL NETWORK

The algorithm for VLSI channel routing using Hopfield neural model is discussed inthis paper.The basic methods of mapping VLSI channel routing problem to Hopfield neural net-work,constructing energy function,setting initial neural status,and selecting various parametersare proposed.Finally,some experimental results are given.

On-board modeling of gravity fields of elongated asteroids using Hopfield neural networks

To rapidly model the gravity field near elongated asteroids,an intelligent inversion method using Hopfield neural networks(HNNs)is proposed to estimate on-orbit simplified model parameters.First,based on a rotating mass dipole model,the gravitational field of asteroids is characterized using a few parameters.To solve all the parameters of this simplified model,a stepped parameter estimation model is constructed based on different gravity field models.Second,to overcome linearization difficulties caused by the coupling of the parameters to be estimated and the system state,a dynamic parameter linearization technique is proposed such that all terms except the parameter terms are known or available.Moreover,the Lyapunov function of the HNNs is matched to the problem of minimizing parameter estimation errors.Equilibrium values of the Lyapunov function areused as estimated values.The proposed method is applied to natural elongated asteroids 216 Kleopatra,951 Gaspra,and 433 Eros.Simulation results indicate that this method can estimate the simplified model parameters rapidly,and that the estimated simplified model provides a good approximation of the gravity field of elongated asteroids.

渗透系数反演的CHNN模型方法

利用连续型Hopfield神经网络 (ContinuousHopfieldNeuralNetwork ,简称CHNN)的反馈特性 ,结合实测资料和数值计算 ,构建了岩土体渗透系数的人工神经网络反演模型 ,通过网络神经元状态的变迁而最终稳定于平衡状态 ,从而得到渗透系数反演优化计算的结果。经实例验证 ,效果较好。

精确复原退化图象的连续 Hopfield 网络研究

提出一种改进的全并行自反馈连续Ｈｏｐｆｉｅｌｄ网络模型用于图象复原．理论分析表明，该改进的Ｈｏｐｆｉｅｌｄ网络模型能使网络能量更精确地收敛到全局极小，从而提高复原图象的质量．对该网络复原匀速直线运动模糊图象的结果与Ｐａｉｌ方法得到的复原图象进行了比较，发现该方法得到的复原图象信噪比提高显著，目视效果更佳．

Hopfield神经网络的改进

提出一个改进的Hopfield神经网络模型,其连接矩阵的对角元T_n=1,同时根据大量的计算机模拟实验并从神经网络的系统能量出发,计算和分析T_n=1及T_n=0两种Hopfield神经网络的各存储样本所处能量状态的分布情况,及其与各存储样本的稳定性和纠错能力的关系,指出改步的Hopfield神经网络其容量和纠错能力均比T_n=0的Hopfield神经网络强。

基于连续Hopfield网络求解TSP的新方法

当连续Hopfield网络及其能量函数同时具有自反馈或不具有自反馈时,称之为一致连续Hopfield网络．在分析了一致连续Hopfield网络能量稳定性的基础上,进一步研究了当网络有自反馈,而其能量函数无自反馈的情况下,网络能量变化的性质,分别给出了使能量函数上升、下降和不变的条件．利用这一理论,可以克服由于梯度下降法所导致的网络能量函数总是下降,从而使网络陷入局部极小值或不可行解的现象．最后在这个理论的基础上我们给出了一种新的求解TSP(traveling salesman problem)的方法,仿真研究表明此方法对于求解TSP问题是很有效的．

基于实虚型连续多值复数Hopfield神经网络的QAM盲检测

针对统计量算法盲检测QAM信号的缺陷,该文提出了一个实虚型连续多值复数Hopfield神经网络算法,该网络的实部、虚部各含一个连续多值实激活函数.该文构造了适用于该网络的能量函数,并分别在异步和同步更新模式下证明了该神经网的稳定性.当该神经网的权矩阵借助接收数据补投影算子构成时,该实虚型连续多值复数Hopfield神经网络可有效地实现QAM信号盲检测.仿真试验表明:该算法采用较短接收数据即可到达全局真解点,并且适用于含公零点信道.

基于连续Hopfield型神经网络的QAM信号盲检测

该文利用连续Hopfield网络本身特点,提出基于连续复Hopfield网络的多值方形/非方形QAM信号的直接盲检测方法。首先完成多值信号盲检测的优化问题构造和能量函数的映射,设计了一个适用于该问题的激活函数。然后给出能量函数的设计与分析、盲检测信号权矩阵的配置方法及其神经元数目选择的一般规律。最后通过对方形QAM和非方形QAM信号的仿真现象展示和分析,验证了所提方法的有效性和鲁棒性。

应用Hopfield神经网络和小波域隐Markov树模型的图像复原

为了解决传统的Hopfield神经网络图像复原算法对噪声抑制和图像细节保护不能很好兼顾的问题,提出了一种基于改进的连续Hopfield神经网络和小波域隐Markov树(HMT)模型的复原算法。将小波域HMT模型作为图像小波系数统计关系的先验知识,并以正则化项的形式引入到神经网络模型中,最终利用Hopfield神经网络的能量收敛特性完成图像复原。同时提出了一种高度并行的网络权值矩阵计算方法,通过对模板图像进行算子操作,分批求取网络权值,避免了大型矩阵的乘法运算。实验结果表明,无论是对真实图像还是人工生成图像,算法复原的视觉效果均有明显改善,提高信噪比(ISNR)较传统同类算法增加了0.3dB以上,达到了同时抑制噪声和保护图像细节的目的。

基于离散Hopfield模式识别样本的GRNN非线性组合短期风速预测模型

利用实时风速数据,建立基于离散Hopfield模式识别样本的广义回归神经网络(GRNN)非线性组合预测模型。在风速数据样本集经二维小波阈值去噪处理后,基于离散Hopfield识别历史数据中与待预测样本最相似的数据,并作为训练样本;将支持向量机、BP神经网络和Elman神经网络分别进行单项预测的结果作为输入向量,经GRNN进行非线性组合预测。采用某风电场的实际风速数据进行预测,结果验证了该预测模型的正确性和有效性。