联想记忆神经网络的一个有效学习算法

提出一种新的联想记忆网络模型的有效学习算法,它具有下述特点:(1)可以全部存 储任意给定的训练模式集,即对于训练模式的数目和它们之间相关性的强弱没有限制;(2)最 小的训练模型吸引域达到最大;(3)在(2)的基础上,每个训练模式具有尽可能大的吸引域; (4)联想记忆神经网络是全局稳定的.大量的计算机仿真实验结果充分说明所提出的学习算 法比已有算法具有更强的存储能力和联想容错能力.     

基于极大极小准则的Hopfield联想记忆学习算法*

基于联想记忆各记忆模式的吸引域之间应保持大小平衡的思想．提出了设计Hopfield联想记忆网络的极大极小准则，即设计出的对称连接权阵应使得网络最小的记忆模式吸引域达到最大．首先提出了一种快速学习算法;再发展了一个启发性迭代学习算法，称为约束感知器优化学习算法．大量实验结果表明了本文学习算法的优越性．     

联想记忆网络的约束优化学习

本文提出了一种联想记忆网络的约束优化学习算法，学习算法是一个全局最小化过程，其初始解保证每个样本是系统的稳定状态，然后逐步增大样本的吸引域，使网络具有优化意义上的最大吸引域，在理论上，我们分析了样本的渐近稳定性和吸引域范围，以及学习算法的收敛性，大量计算机实验结果说明学习算法是行之有效的。     

基于混沌神经网络的电机故障诊断

采用全局耦合混沌神经网络模型，每个神经元的动力学行为由反对称立方映像表示。采用Hebb算法设计网络的连接权值矩阵．将记忆模式的回忆过程转化为耦合系统中参数演变的过程，从而实现了混沌神经网络的联想记忆。根据提出的能量击穿规则，扩大了样表的吸引域。在此基础上，应用该混沌神经网络对异步电机转子断条故障进行诊断。结果表明，该种方法有助于故障模式的记忆和重现。     

基于遗传算法的Hopfield联想记忆吸引域的优化

由于一般离散Hopfield神经网络存在很多伪稳定点.使稳定点的吸引域变小.网络很难获得真正的最优解.因此,提出将遗传算法应用到Hopfield联想记忆神经网络中.利用遗传算法对复杂、多峰、非线性极不可微函数实现全局搜索性质.对Hopfield联想记忆吸引域进行优化,使待联想模式跳出伪模式的吸引域.使Hopfield网络在较高噪信比的情况下保持较高的联想成功率.仿真结果证明了该方法的有效性.     

基于极大极小准则的Hopfield联想记忆学习算法

基于联想记忆各记忆模式的吸收域之间的应保持大小平衡的思想，提出了设计Ｈｏｐｆｉｅｌｄ联想记忆网络的极大极小准则，即设计出的对称连接权阵应使得网络最小的记忆模式吸收域达到最大，首选提出了一种快速算法；再发展了一个启发性迭代学习算法，称为约束感知器学习算法，大量实验结果表明了本文学习算法的优越性。     

模糊联想记忆网络的增强学习算法

针对 Kosko提出的最大最小模糊联想记忆网络存在的问题 ,通过对这种网络连接权学习规则的改进 ,给出了另一种权重学习规则 ,即把 Kosko的前馈模糊联想记忆模型发展成为模糊双向联想记忆模型 ,并由此给出了模糊快速增强学习算法 ,该算法能存储任意给定的多值训练模式对集 .其中对于存储二值模式对集 ,由于其连接权值取值 0或 1,因而该算法易于硬件电路和光学实现 .实验结果表明 ,模糊快速增强学习算法是行之有效的 .     

时变容错域的感知联想记忆模型及其实现算法

提出并用软件实现了一种时变容错域的感知联想记忆模型．该模型有以下特点：（1）模拟了大脑联想记忆的容错域随时间变化的特点．模型可以根据记忆样本的重要性，为记忆样本在不同时间设计适当的容错域;（2）实现了”维到m维空间的无穷值模式非线性联想，而且该模型的样本容错域充满整个实空间R^n，模型没有伪吸引子；（3）联想记忆速度快．     

具有期望容错域的前向掩蔽联想记忆模型的设计方法

联想记忆的综合问题是目前没有很好解决的难题.文中用作者提出的通用前馈网络和排序学习算法,提出了一种设计具有期望容错域的前向掩蔽联想记忆模型的方法.该方法一般性地解决了信息空间上联想记忆的综合难题,使设计出的联想记忆模型具有任意期望的记忆样本容错域.     

多模式对模糊联想记忆学习算法的优化

一、引言 人脑神经系统信息活动的一个重要特征是能够接收和处理模糊的、连续随机的信息,并在输出时不追求绝对精确解而只要求能找到问题的满意解。模糊联想记忆神经网络是Bart Kosko于1987年提出的采用模糊赫布型学习规则的一种单状态异联想记忆神经网络,在模糊控制、模式识别、专家系统等领域曾引起人们的关注。由于该网络的子集联想特性和不能有效地联想存储多个训练模式对而影响了它的应用[1-3]。本文提出模糊合成运算的一种微分法则,用一代价函数以反映网络性能,将梯度下降搜索技术与模糊赫布型学习规则相结合,建立了在单个模糊联想记忆神经网络中联想存储多个模式对的一种优化学习算法。理论分析和实例计算均证明该算法优于Kosko的学习规则。     

Weighted learning of bidirectional associative memories by globalminimization

A weighted learning algorithm for bidirectional associative memories (BAMs) by means of global minimization, where each desired pattern is weighted, is described. According to the cost function that measures the goodness of the BAM, the learning algorithm is formulated as a global minimization problem and solved by a gradient descent rule. The learning approach guarantees not only that each desired pattern is stored as a stable state, but also that the basin of attraction is constructed as large as possible around each desired pattern. The existence of the weights, the asymptotic stability of each desired pattern and its basin of attraction, and the convergence of the proposed learning algorithm are investigated in an analytic way. A large number of computer experiments are reported to demonstrate the efficiency of the learning rule.     

The Object Perceptron Learning Algorithm on Generalised Hopfield Networks for Associative Memory

We present a study of generalised Hopfield networks for associative memory. By analysing the radius of attraction of a stable state, the Object Perceptron Learning Algorithm (OPLA) and OPLA scheme are proposed to store a set of sample patterns (vectors) in a generalised Hopfield network with their radii of attraction as large as we require. OPLA modifies a set of weights and a threshold in a way similar to the perceptron learning algorithm. The simulation results show that the OPLA scheme is more effective for associative memory than both the sum-of-outer produce scheme with a Hopfield network and the weighted sum-of-outer product scheme with an asymmetric Hopfield network.     

Object detection and classification: a joint selection and fusion strategy of deep convolutional neural network and SIFT point features

Multimedia Tools and Applications - In the area of machine learning and pattern recognition, object classification is getting an attraction due to its range of applications such as visual...     

基于自适应吸引半径的萤火虫算法的粒子滤波

针对粒子滤波算法对粒子数目的大量需求等弊端,提出一种基于改进的萤火虫算法的粒子滤波。首先,在萤火虫的亮度公式中引入观测值信息以提高算法跟踪的准确性;其次,提出自适应吸引半径参数来控制萤火虫群寻优时的吸引范围,使算法的实时性更好;最终利用萤火虫算法的迭代寻优来进行粒子更新。对比实验表明,该算法在跟踪精度和运行时间上都有所优化,说明该算法即使在粒子数目较少的条件下也能保证目标跟踪的准确性和实时性。     

What influences college students to continue using business simulation games? The Taiwan experience

Previous studies have pointed out that computer games could improve students’ motivation to learn, but these studies have mostly targeted teachers or students in elementary and secondary education and are without user adoption models. Because business and management institutions in higher education have been increasingly using educational simulation games in recent years, factors influencing the continuing use of business simulation games by higher-education students are worth probing into. This research adopted the technology acceptance model, expectation confirmation theory, and agency theory as its theoretical base. Moreover, learning motivation and classroom climate from the perspective of learning, as well as perceived attractiveness and perceived playfulness from the perspective of playfulness and attractiveness were also added to the final research model. A total of 185 valid student respondents in Taiwan’s higher education who have used business simulation games in their classes participated in the survey. The results show that perceived playfulness and learning performance positively influence students’ satisfaction, which further influence the intention to use computer simulation games. Furthermore, perceived ease of use and perceived attraction play a critical role in determining perceived playfulness. Perceived ease of use was also positively influenced by perceived attraction. The research results on the students’ perspective provide a strong support for the teachers to adopt or continue using computer simulation games in classrooms. However, the agency theory failed to be sustained as a useful tool in motivating students’ learning activities, which is worthy of further research.     

基于深度无监督学习的多小区蜂窝网资源分配方法

针对多小区蜂窝网络资源分配所要求的低能耗、高速率和低延时问题,提出一种基于深度无监督学习的多小区蜂窝网络资源分配方法.首先,构建基于无监督学习的深度功率控制神经网络,通过约束处理输出优化的信道功率控制方案以最大化能量效率的期望;然后,构建基于无监督学习的深度信道分配神经网络,通过约束处理输出优化的信道分配方案,并联合前期训练好的深度功率控制神经网络拟合输出优化的信道功率,进一步优化能量效率的期望.仿真结果表明,所提出的方法在保证低计算时延的同时可获得优于其他算法的能量效率和传输速率.     

Programming based learning algorithms of neural networks withself-feedback connections

Discusses the learning problem of neural networks with self-feedback connections and shows that when the neural network is used as associative memory, the learning problem can be transformed into some sort of programming (optimization) problem. Thus, the rather mature optimization technique in programming mathematics can be used for solving the learning problem of neural networks with self-feedback connections. Two learning algorithms based on programming technique are presented. Their complexity is just polynomial. Then, the optimization of the radius of attraction of the training samples is discussed using quadratic programming techniques and the corresponding algorithm is given. Finally, the comparison is made between the given learning algorithm and some other known algorithms     

双向联想记忆学习与回忆的研究

本文对双向联想记忆(BAM)的学习与回忆过程进行了详细的分析。在学习过程中,先是运用自适应非对称BAM算法进行学习,进而采用设置印象门限的反复记忆算法进行学习,本文从理论上证明了印象门限与样本吸引域之间的关系,指出反复记忆方法的理论依据。回忆过程中,采用非零阈值函数的运行方程,提出了阈值学习方法,并且从理论上证明了非零阈值函数的运行方程的采用,可进一步扩大吸引域。为了进一步扩大网络的信息存储量,本文引入了并联的BAM结构。本文方法的采纳,使得BAM网络的信息存储量、误差校正能力等得到很大程度的提高。