基于离散Hopfield神经网络的数字识别实现

介绍了离散Hopfield神经网络的基本概念;以MATLAB为工具,根据Hopfield神经网络的相关知识,设计了一个具有联想记忆功能的离散型Hopfield神经网络,并给出了设计思路、设计步骤和测试结果。实验结果表明,通过联想记忆,对于带有一定噪声的数字点阵,Hopfield网络可以正确地进行识别,且当噪声强度为0．1时的识别效果较好。     

Hopfield神经网络在有限元求解中的应用

计算机本身固有的计算与存储之间是一对很难解决的矛盾,许多工程力学问题因计算规模大等原因还没有突破性进展,因此,需要发展新的理论与计算方法。通过对有限元求解方法和Hopfield神经网络的深入研究,在对Hopfield神经网络适当改造后,得到了有限元的神经网络计算方法,在电路实现中避免了采用高增益传递函数的假设,进而在理论上实现了有限元神经网络计算的无误差求解。     

An investigation into sustainable product conceptualization using a design knowledge hierarchy and Hopfield network

In recent years, there has been a paradigm shift on providing design services from manufacturing/marketing to sustainability. Although a number of studies have been conducted on sustainable issues in many aspects, impacts such as multidisciplinary integration and product life-cycle consideration have not been thoroughly investigated. Therefore, it is worthwhile to investigate into the integration of functional, marketing, and commercial perspectives with product sustainability in the early stage of product conceptualization. In this study, a sustainable product conceptualization system (SPCS) is proposed. The product platform of a specific product is first generated by designers or domain experts using general sorting, a requirement acquisition technique, and design knowledge hierarchy (DKH), a knowledge representation structure. Based on the product platform, initial design options can be obtained using morphological configuration, i.e., combining different part options. Subsequently, the Hopfield network is used to narrow down initial design space based on initial design criteria solicited by domain experts. To select the preferred design options for the purpose of sustainable product conceptualization, the sustainability-cost pairs can be obtained based on the rated sustainability and cost criteria solicited using repertory grids by domain experts. Consequently, the results are discussed on the coordination between product sustainability degree and cost efficiency. A case study on cellular-phone design is conducted for system illustration.     

Hopfield神经网络在机组组合问题中的应用

提出利用多层Hopfield神经网络求解机组组合优化问题。通过构造合适的能量函数使得单层Hopfield神经网络可以解决某一时刻的机组出力问题,与之相对应的多层神经网络可以解决任意时间段的机组出力问题。多层Hopfield神经网络的层数由所需求解问题的时间段确定。给出单层及多层神经网络的能量函数及求解算法,能量函数考虑到机组升降功率和出力上下限的约束。通过对已有文献的算例进行计算比对,所得结果和遗传算法基本一致,但Hopfield神经网络通过解微分方程组来确定最优解,计算时间相对较少。     

A shortest path routing algorithm using Hopfield neural network with an improved energy function

A shortest path routing algorithm using the Hopfield neural network with a modified Lyapunov function is proposed. The modified version of the Lyapunov energy function for an optimal routing problem is proposed for determining routing order for a source and multiple destinations. The proposed energy function mainly prevents the solution path from having loops and partitions. Experiments are performed on 3000 networks of up to 50 nodes with randomly selected link costs. The performance of the proposed algorithm is compared with several conventional algorithms including Ali and Kamoun's, Park and Choi's, and Ahn and Ramakrishna's algorithms in terms of the route optimality and convergence rate. The results show that the proposed algorithm outperforms conventional methods in all cases of experiments. The proposed algorithm particularly shows significant improvements on the route optimality and convergence rate over conventional algorithms when the size of the network approaches 50 nodes.     

Agriculture satellite image segmentation using a modified artificial Hopfield neural network

Beekeeping plays an important role in increasing and diversifying the incomes of many rural communities in Kingdom of Saudi Arabia. However, despite the region’s relatively good rainfall, which results in better forage conditions, bees and beekeepers are greatly affected by seasonal shortages of bee forage. Because of these shortages, beekeepers must continually move their colonies in search of better forage. The aim of this paper is to determine the actual bee forage areas with specific characteristics like population density, ecological distribution, flowering phenology based on color satellite image segmentation. Satellite images are currently used as an efficient tool for agricultural management and monitoring. It is also one of the most difficult image segmentation problems due to factors like environmental conditions, poor resolution and poor illumination. Pixel clustering is a popular way of determining the homogeneous image regions, corresponding to the different land cover types, based on their spectral properties. In this paper Hopfield neural network (HNN) is introduced as Pixel clustering based segmentation method for agriculture satellite images.     

用改进的差分式Hopfield网络实现线性二次型最优控制

为解决差分式Hopfield网络能量函数的局部极小问题,本文对之改进得到一种具有迭代学习功能的线性差分式Hopfield网络.理论分析表明,该网络具有稳定性,且稳定状态使其能量函数达到唯一极小值.基于线性差分式Hopfield网络稳定性与其能量函数收敛特性的关系,本文将该网络用于求解多变量时变系统的线性二次型最优控制问题.网络的理论设计方法表明,网络的稳态输出就是欲求的最优控制向量.数字仿真取得了与理论分析一致的实验结果.     

基于蚁群算法的Hopfield神经网络在多空间站路径规划的应用研究*

空间机器人每次携带的燃料有限,提高空间机器人的工作效率以及延长其在轨寿命研究具有重要意义,分析了空间机器人多空间站访问问题。为了弥补传统路径规划方法容易陷入局部极小点的问题,提出利用基于蚁群算法的Hopfield神经网络来解决空间机器人多空间站访问问题。仿真实验结果表明,基于蚁群算法的Hopfiled神经网络用于多空间站访问问题,收敛速度要比Hopfield神经网络快,且比Hopfield神经网络易于跳出局部极点,该算法有利于解决多空间站路径规划问题。     

On-line emission and economic load dispatch using adaptive Hopfield neural network

This paper presents an adaptive Hopfield neural network (AHNN) based methodology, where the slope of the activation function is adjusted, for finding approximate Pareto solutions for the multi-objective optimization problem of emission and economic load dispatch (EELD). We have placed emphasis on finding solutions quickly, rather than the global Pareto solutions, so that our algorithm can be employed in large on-line power systems where variations in load are quite frequent. To enable faster convergence, adaptive learning rates have been developed by using energy function and applied to the slope adjustment method. The proposed algorithm has been tested on selected IEEE bus benchmark systems. The convergence of AHNN is found to be nearly 50% faster than the non-adaptive version.     

A Hopfield neural network approach for power optimization of real-time operating systems

The RTOS (Real-Time Operating System) is a critical component in the SoC (System-on-a-Chip), which is the main body for consuming total system energy. Power optimization based on hardware–software partitioning of a RTOS (RTOS–Power partitioning) can significantly minimize the energy consumption of a SoC. This paper presents a new model for RTOS–Power partitioning, which helps in understanding the essence of the RTOS–Power partitioning techniques. A discrete Hopfield neural network approach for implementing the RTOS–Power partitioning is proposed, where a novel energy function, operating equation and coefficients of the neural network are redefined. Simulations are carried out with comparison to other optimization techniques. Experimental results demonstrate that the proposed method can achieve higher energy savings up to 60% at relatively low costs of less than 4k PLBs while increasing the performance compared to the purely software realized SoC–RTOS.     

用连续Hopfield网络实现无限时域上的最优控制

为避免直接采用Riccati方程求解时变系统无限域最优控制问题时的计算困难,本文提出一种基于时间连续状态连续型Hopfield网络(CTCSHNN)实现无限域动态最优控制的方法．该方法通过建立CTCSHNN能量函数与移动域控制指标间的等价关系,可在线构建CTCSHNN．理论分析表明,依据该方法设计的CTCSHNN具有稳定性,而且移动域控制量可由网络稳态输出直接产生．将该方法与滚动优化策略相结合,可实现无限时域上的闭环最优控制．仿真实验验证了理论设计的正确性与采用基于CTCSHNN的移动域控制实现无限域闭环最优控制的可行性．     

Modelling microtubules in the brain as n-qudit quantum Hopfield network and beyond

The scientific approach to understand the nature of consciousness revolves around the study of the human brain. Neurobiological studies that compare the nervous system of different species have accorded the highest place to humans on account of various factors that include a highly developed cortical area comprising of approximately 100 billion neurons, that are intrinsically connected to form a highly complex network. Quantum theories of consciousness are based on mathematical abstraction and the Penrose–Hameroff Orch-OR theory is one of the most promising ones. Inspired by the Penrose–Hameroff Orch-OR theory, Behrman et al. have simulated a quantum Hopfield neural network with the structure of a microtubule. They have used an extremely simplified model of the tubulin dimers with each dimer represented simply as a qubit, a single quantum two-state system. The extension of this model to n-dimensional quantum states or n-qudits presented in this work holds considerable promise for even higher mathematical abstraction in modelling consciousness systems.     

Hopfield在计算机编程中的应用与研究

Hopfield网络,又称联想记忆网络。文中根据Hopfleld神经网络构造一个应用于计算机代码编程中的联想存储器。联想记忆是该存储器的重要功能,它具有信息记忆和信息联想的特点,能够从不完整的或模糊的信息联想出存储在记忆中的某个完整清晰的信息模式。根据这一原理,用H0pfield联想存储器知识和eclipse插件机制来搭建嵌入在eclipse开发工具中一个知识可拓展的动态帮助插件,实现根据残缺不全的java代码联想到完整的java代码的功能,并进一步阐述Hopfield神经网络在计算机代码编程中的应用前景和发展方向。     

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     

基于Hopfield网络的PID在直流伺服电机中的应用

针对直流伺服电机的非线性和时变性因素,本文结合传统PID控制器特点,介绍了一种基于Hopfield神经网络PID控制方法。该方法利用Hopfield神经网络的自学习能力,经过有限次的训练可以得到了PID控制器所需要的最优参数。采用Matlab软件对构造的系统模型进行了仿真和跟踪实验。实验表明这种方法既简化了经典控制PID参数整定,同时使系统具较好的实时性、稳定性和跟踪性,控制效果比较理想。     

Hopfield神经网络在二维码污损复原中的应用

针对传统Hopfield神经网络记忆功能的局限性,以Hopfield神经网络的理论知识为依据,提出了一种改进的Hopfield神经网络.在学习阶段,通过对连接关系矩阵的修正来提高网络的记忆能力.运用Matlab为工具,设计了一个可以对信息进行联想记忆的网络,实现了不同污损程度二维码的复原.对改进前后网络的复原结果进行了比较分析,结果表明:改进后的Hopfield神经网络对污损二维码的复原较好.     

无线传感网使用网络编码的新型数据传输方法

网络编码能提高无线传感器网络数据传输可靠性,针对现有基于网络编码的数据传输策略随机选取编码向量和使用固定路径所带来的缺陷,设计了一个新的编码矩阵构造方法,并提出了一种新型的基于网络编码的可靠数据传输方法。该编码方案能保证任意k个编码向量线性无关,且不用传输编码向量。数据转发使用"区域推进"机制,自动选取最佳转发节点,将数据包可靠地向sin"k推进",并实现了最少冗余传输和网络均衡能耗。分析与仿真表明,新的数据传输策略能消除现有方法的缺陷,提高数据传输可靠性,降低能耗。     

A hill-jump algorithm of Hopfield neural network for shortest path problem in communication network

In this paper, we present a hill-jump algorithm of the Hopfield neural network for the shortest path problem in communication networks, where the goal is to find the shortest path from a starting node to an ending node. The method is intended to provide a near-optimum parallel algorithm for solving the shortest path problem. To do this, first the method uses the Hopfield neural network to get a path. Because the neural network always falls into a local minimum, the found path is usually not a shortest path. To search the shortest path, the method then helps the neural network jump from local minima of energy function by using another neural network built from a part of energy function of the problem. The method is tested through simulating some randomly generated communication networks, with the simulation results showing that the solution found by the proposed method is superior to that of the best existing neural network based algorithm.     

机会网络中基于社区的高效消息传输算法

针对机会社会网络中现有基于社区的消息传输算法(OSNCMTS)在社区内存在节点积压消息分发任务、在社区间存在盲目选择活跃节点转发信息的问题,提出一种基于社区的高效机会网络路由算法(HECMTS)。在HECMTS算法中,首先,采用极值优先(EO)算法划分社区并将划分的社区矩阵分发给社区节点;其次,采用社区矩阵和消息到目的节点成功率相结合的方法分配社区内消息副本数;最后,利用活跃节点往返不同社区的机会收集活跃节点信息,然后查询这些活跃节点信息从中选取合适的活跃节点完成社区间消息传输。仿真结果表明,与OSNCMTS算法相比,HECMTS算法在路由开销性能和平均端到端时延性能上分别至少下降了19%和16%。     

模糊PID和Hopfield神经网络在矿井通风系统中的应用

针对传统的PID控制或者单一的模糊控制无法准确控制矿井通风系统风量的问题,提出了一种采用模糊PID调节器和Hopfield神经网络调节器对矿井通风机的转速、风门、风量进行控制的方法。该方法利用模糊控制器对PID参数进行实时修正,并结合Hopfield神经网络的联想记忆功能和反馈调节特性,实现矿井通风机风量的快速、稳定输出。仿真与实验结果表明,模糊PID调节器和Hopfield神经网络调节器可以准确控制矿井通风机的转速和风量,实现通风系统的稳定输出。