含脉冲的Hopfield神经网络模型及其收敛性

利用脉冲微分方程,建立了一种新型神经网络模型,通过构造Lyapunov函数方法,讨论了网络的周期振荡性,和全局指数收敛性质及其收敛速率,并给出一实例说明所得结论.     

A neural networks algorithm for data path synthesis

This paper presents a deterministic parallel algorithm to solve the data path allocation problem in high-level synthesis. The algorithm is driven by a motion equation that determines the neurons firing conditions based on the modified Hopfield neural network model of computation. The method formulates the allocation problem using the clique partitioning problem, an NP-complete problem, and handles multicycle functional units as well as structural pipelining. The algorithm has a running time complexity of O(1) for a circuit with n operations and c shared resources. A sequential simulator was implemented on a Linux Pentium PC under X-Windows. Several benchmark examples have been implemented and favorable design comparisons to other synthesis systems are reported.     

Optically synaptic films using spiropyran J-aggregates

Spiropyran SP1822 J-aggregate LB films show a non-linear photochromic response with a threshold against the incident light intensity of a CW dye laser. Using two laser beams operating below the threshold level intensity, the logic ‘AND’ function was found to be optically stored as an overlapping region of two incident patterns. We proposed the adoption of an LB film of spiropyran J-aggregates to store the memory matrix T_ijkl as an overlapping region of learning input pattern V_ij and multi-image input pattern V_kl in order to construct an optical neural network system based on Hopfield model.     

复数Hopfield神经网络盲均衡QAM信号

为了解决复数多值信号的盲均衡问题,本文提出了基于复数Hopfield神经网络盲均衡多值信号的方法:将基于Hopfield神经网络的盲均衡算法从实数域推广到复数域.在复数域成功构造了复数Hopfield神经网络,重点针对16QAM信号进行盲均衡.并验证了此系统可以处理非统计量字符,即处理16QAM信号的Hopfield神...     

基于Hopfield神经网络的多用户信号检测器

用连续Ｈｏｐｆｉｅｌｄ神经网络实现ＣＤＭＡ通信系统中多用户信号检测的设想，并针对同步ＣＤＭＡ系统构造了基于连续Ｈｏｐｆｉｅｌｄ神经网络的用户信号检测器。计算机仿真结果表明：这种检测器的性能远远优于传统检测器的性能，它的性能可与最佳多用户信号检测相比拟。     

Optic flow estimation by a Hopfield neural network using geometrical constraints

Sparse optic flow maps are general enough to obtain useful information about camera motion. Usually, correspondences among features over an image sequence are estimated by radiometric similarity. When the camera moves under known conditions, global geometrical constraints can be introduced in order to obtain a more robust estimation of the optic flow. In this paper, a method is proposed for the computation of a robust sparse optic flow (OF) which integrates the geometrical constraints induced by camera motion to verify the correspondences obtained by radiometric-similarity-based techniques. A raw OF map is estimated by matching features by correlation. The verification of the resulting correspondences is formulated as an optimization problem that is implemented on a Hopfield neural network (HNN). Additional constraints imposed in the energy function permit us to achieve a subpixel accuracy in the image locations of matched features. Convergence of the HNN is reached in a small enough number of iterations to make the proposed method suitable for real-time processing. It is shown that the proposed method is also suitable for identifying independently moving objects in front of a moving vehicle. Received: 26 December 1995 / Accepted: 20 February 1997     

Cascade synthesis of 2-D dissipative reactance networks

In this paper, a new result, new formulas of transfer function and input impedance, for 2-D dissipative reactance network cascade synthesis is given in terms of simplified formulas to realize doubly terminated resistively 1-D dissipative reactance networks. The new result includes the more general cases, e.g. the both can be dissipative or one is dissipative and the another is a lossless reactance subnetwork and so on. Two calculation examples are given in the paper to illustrate the above realizations. Besides, considering some problems of the direct connection between two subnetworks, we also introduce one-way lines to discuss the cascade synthesis of nonreciprocal 2-D dissipative reactance networks.     

神经网络A／D转换器电路的两种改进方法

本文对Ｈｏｐｆｉｅｌｄ神经网络Ａ／Ｄ转换器电路进行了分析。对照转换条件及电路的稳态方程，讨论了输出状态与参考输入必须满足的条件。在此基础上提出了两种改进Ａ／Ｄ转换电路的途径：（１）对原电路选择适宜的参考输入；（２）根据Ｈｏｐｆｉｅｌｄ线性规划网络提出的一种新电路。文中还给出了ＰＳＰＩＣＥ模拟计算，所得结果与理论分析吻合。     

Convergence of higher-order two-state neural networks with modified updating

The Hopfield network is a standard tool for maximizing aquadratic objective function over the discrete set {− 1,1} ⁿ . It is well-known that if a Hopfield network is operated in anasynchronous mode, then the state vector of the network converges to a local maximum of the objective function; if the network is operated in asynchronous mode, then the state vector either converges to a local maximum, or else goes into a limit cycle of length two. In this paper, we examine the behaviour ofhigher-order neural networks, that is, networks used for maximizing objective functions that are not necessarily quadratic. It is shown that one can assume, without loss of generality, that the objective function to be maximized ismultilinear. Three methods are given for updating the state vector of the neural network, called the asynchronous, the best neighbour and the gradient rules, respectively. For Hopfield networks with a quadratic objective function, the asynchronous rule proposed here reduces to the standard asynchronous updating, while the gradient rule reduces to synchronous updating; the best neighbour rule does not appear to have been considered previously. It is shown that both the asynchronous updating rule and the best neighbour rule converge to a local maximum of the objective function within a finite number of time steps. Moreover, under certain conditions, under the best neighbour rule, each global maximum has a nonzero radius of direct attraction; in general, this may not be true of the asynchronous rule. However, the behaviour of the gradient updating rule is not well-understood. For this purpose, amodified gradient updating rule is presented, that incorporates bothtemporal as well as spatial correlations among the neurons. For the modified updating rule, it is shown that, after a finite number of time steps, the network state vector goes into a limit cycle of lengthm, wherem is the degree of the objective function. Ifm = 2, i.e., for quadratic objective functions, the modified updating rule reduces to the synchronous updating rule for Hopfield networks. Hence the results presented here are “true” generalizations of previously known results.