小世界人工神经网络模型及其应用研究

关于优化神经网络模型的快速性和精度,为了寻找最优的神经网络结构,在复杂网络的研究方法对多层前向神经网络模型的基础上,提出一种在层次结构上处于规则型到随机型神经网络过渡的中间网络模型-NW型多层前向小世界人工神经网络模型.利用对多层前向规则神经网络中神经元以某一概率p随机化向后层跨层连接,构建新的神经网络模型,然后将不同跨层概率下的小世界人工神经网络应用于函数逼近.在设定精度相同情况下对不同概率下的收敛次数做比较,仿真发现随机化加边概率p处于p =0.08附近时的小世界人工神经网络比同规模的规则网络和随机网络具有更好的收敛速度,实验证实采用NW型小世界多层前向人工神经网络模型,在精度和收敛速度上均得到提高.     

基于层连优化的新型小世界神经网络

对多层前向小世界神经网络的网络参数、权值修正策略以及网络结构进行改进, 提出一种基于层连优化的小世界神经网络的改进算法. 通过对比现有各种不同形式的小世界神经网络, 验证了上述改进的必要性. 仿真结果表明, 改进模型比现有小世界神经网络收敛速度更快, 逼近精度更高, 模型稳定性更强.     

基于NW型小世界人工神经网络的污水出水水质预测

为了预测污水处理出水水质,针对污水处理过程具有多变量、非线性、时变性、严重滞后的特点,提出了基于NW型小世界人工神经网络的污水处理出水水质预测模型;首先根据污水处理系统确定模型输入输出变量个数,然后建立了多层前向小世界神经网络模型,并对网络模型的隐层结构进行了优化研究;借助污水处理过程的历史数据进行了仿真研究,结果表明:和同规模的多层前向人工神经网络相比,小世界神经网络对污水出水水质预测具有较高精度和收敛速度,为污水出水水质的实时预测提供了一种有效的新方法。     

前向代数神经网络的函数逼近理论及学习算法

文中对ＭＰ神经元模型进行了推广,定义了多项代数神经元、多项式代数神经网络,将多项式代数融入代数神经网络,分析了前向多项式代数神经网络函数逼近能力及理论依据,设计出了一类双输入单输出的前向４层多层式代数神经网络模型,由该模型构成的网络能够逼近于给定的二元多项式到预定的精度。给出了在Ｐ－ａｄｉｃ意义下的多项式代数神经网络函数逼近整体学习算法,在学习的过程中,不存在局部极小,通过实例表明,该算法有效,最     

多输入La}uerre正交多项式前向神经网络权值与结构确定法

为克服邵神经网络模型及其学习算法中的固有缺陷,根据多项式插值和逼近理论,构造出一种以工;agucrre正交多项式作为隐层神经元激励函数的多输入前向神经网络模型。针对该网络模型,提出了权值与结构确定法,以便快速、自动地确定该网络的最优权值和最优结构。计算机仿真与实验结果显示:该算法是有效的,并且通过该算法所得到的网络具有较优的逼近性能和良好的去噪能力。     

RBPN在模式识别研究中的应用

基于RBF(radialbasisfunction)网络和感知器 (perceptron)网络建立起一种新型四层前向神经网络———径向基感知器网络 (RBPN, radialbasisperceptronnetwork). 该网络主要有以下特点 :1)网络结构上, 两层隐层选择性连接 ;2 )学习规则上, 采用同时考虑输入输出样本信息的IOC(input outputclustering)聚类方法且聚类中心的形状参数σ自适应变化. 对材料成分分析领域的仿真结果表明, 该网络可成功地包含材料成分的构成信息,     

基于特征聚合的假新闻内容检测模型

针对假新闻内容检测中分类算法模型的检测性能与泛化性能无法兼顾的问题,提出了一种基于特征聚合的假新闻检测模型CCNN。首先,通过双向长短时循环神经网络提取文本的全局时序特征,并采用卷积神经网络（CNN）提取窗口范围内的词语或词组特征;然后,在卷积神经网络池化层之后,采用基于双中心损失训练的特征聚合层;最后,将双向长短时记忆网络（Bi-LSTM）和CNN的特征数据按深度方向拼接成一个向量之后提供给全连接层,采用均匀损失函数uniform-sigmoid训练模型后输出最终的分类结果。实验结果表明,该模型的F1值为80.5%,在训练集和验证集上的差值为1.3个百分点;与传统的支持向量机（SVM）、朴素贝叶斯（NB）和随机森林（RF）模型相比,所提模型的F1值提升了9~14个百分点;与长短时记忆网络（LSTM）、快速文本分类（FastText）等神经网络模型相比,所提模型的泛化性能提升了1.3~2.5个百分点。由此可见,所提模型能够在提高分类性能的同时保证一定的泛化能力,提升整体性能。     

基于神经网络的过程软测量

提出基于神经网络的软测量技术的一般框架,并针对一个实际的催化裂化装置,采用多层前向网络和推广随机逼近算法对粗汽油干点的软测量进行了研究.理论分析和模拟表明,该模型可以很好地描述实际对象特性.     

基于有向小世界网络的加速分布式一致性收敛速度研究

在有向平衡规则网络基础上,采用随机添加捷径的方法建立两个有向小世界网络模型,并使有向小世界网络为平衡网络.通过仿真分析,基于有向小世界网络的分布式一致性算法的收敛速度得到了极大的提高.     

FUZZY ARTMAP神经网络综述

1.引言神经网络模拟人脑神经功能,用大量简单关系连接来表示复杂的函数关系,具有很多特殊优点,已在系统建模、模式识别、图像处理、知识发现和控制等领域得到了广泛的应用。但当使用前向神经网络,如多层感知器(MLP)和径向基函数(RBF)网络时,需要依赖一些试探法去选择最优的网络尺寸和参数,此外这些网络在学习后通常是静止的,不具备增量学习能力(在     

不同重连概率的小世界脉冲神经网络抗扰功能研究

现今各种电磁干扰对电子系统造成的不良影响越来越严重,传统防护方式的局限性日益凸显。电磁仿生学由此被提出,目的是通过借鉴生物体的自适应抗扰的优良特性,以期建立新的防护模式。构建了以Izhikevich神经元模型为节点,兴奋性和抑制性突触可塑性模型共同调节基于小世界网络拓扑的小世界脉冲神经网络;基于复杂网络理论对比分析了不同重连概率的小世界网络的拓扑特性;对比分析了不同重连概率的小世界脉冲神经网络在高斯白噪声刺激下的抗扰功能。实验结果表明:小世界网络的平均路径长度和全局效率值受重连概率的影响较小,平均聚类系数和小世界属性受重连概率的影响较大;构建的不同重连概率的脉冲神经网络均具有一定抗扰功能且高聚类系数和低平均路径长度显著的小世界脉冲神经网络抗扰功能最优。     

Approximate Feedback Linearisation Using Multilayer Neural Networks

In this paper we introduce the approximate feedback linearisation using multilayer feedforward neural networks. We propose to approximate a basis of the one-dimensional codistribution of an affine nonlinear system with the derivative of a multilayer neural network [6] and form a change of coordinates with n multilayer neural networks [5]. In this paper we will prove that the transformation can define a local diffeomorphism, with which a local stabilising feedback law can be designed for a kind of non-linearisable nonlinear systems.     

The Chebyshev-polynomials-based unified model neural networks forfunction approximation

In this paper, we propose the approximate transformable technique, which includes the direct transformation and indirect transformation, to obtain a Chebyshev-Polynomials-Based (CPB) unified model neural networks for feedforward/recurrent neural networks via Chebyshev polynomials approximation. Based on this approximate transformable technique, we have derived the relationship between the single-layer neural networks and multilayer perceptron neural networks. It is shown that the CPB unified model neural networks can be represented as a functional link networks that are based on Chebyshev polynomials, and those networks use the recursive least square method with forgetting factor as learning algorithm. It turns out that the CPB unified model neural networks not only has the same capability of universal approximator, but also has faster learning speed than conventional feedforward/recurrent neural networks. Furthermore, we have also derived the condition such that the unified model generating by Chebyshev polynomials is optimal in the sense of error least square approximation in the single variable ease. Computer simulations show that the proposed method does have the capability of universal approximator in some functional approximation with considerable reduction in learning time.     

Stability and bifurcation of disease spreading in complex networks

A general nonlinear model of disease spreading is proposed, describing the effect of the new link-adding probability p in the topological transition of the N-W small-world network model. The new nonlinear model covers both limiting cases of regular lattices and random networks, and presents a more flexible internal nonlinear interaction than a previous model. Hopf bifurcation is proved to exist during disease spreading in all typical cases of regular lattices, small-world networks, and random networks described by this model. It is shown that probability p not only determines the topological transition of the N-W small-world network model, but also dominates the stability of the local equilibria and bifurcating periodic solutions, and moreover can be further applied to stabilize a periodic spreading behaviour onto a stable equilibrium over the network.     

多输出神经元模型的多层前向神经网络及其应用

研究了一种新的多输出神经元模型.首先,给出这类模型的一般形式,并将该模型应用于多层前向神经网络;其次,给出了其学习算法,即递推最小二乘算法,最后通过几个模拟实验表明,采用多输出神经元模型的多层前向神经网络,具有结构简单,泛化能力强,收敛速度快,收敛精度高等特点,其性能远远优于激活函数可调模型的多层前向神经网络.     

基于阻尼最小二乘法的神经网络自校正一步预测控制器

针对非线性控制器设计中遇到的模型结构及模型参数辨识问题,采用多层前馈神经网络去逼近任意的非线性系统,并使用收敛速度快且稳定性好的阻尼最小二乘法在线学习网络的仅植。基于估计的神经网络模型,依据辨识与控制的对偶原则,设计了基于阻尼最小二乘法的一步向前预测控制器。仿真研究表明,这种神经网络自校正控制器不仅具有很好的性能,而且不会产生参数爆发现象。     

基于神经网络的机器人轨迹跟踪控制

针对机器人模型未知情况，讨论了用神经网络和反馈控制实现机械手的跟踪控制。提出一种基于参考误差的投影算法来训练网络权值，训练后网络输出能逼近期望的前馈力矩，并从理论上证明跟踪误差的收敛性。仿真结果表明方案具有较好的跟踪性能和较强的抗干扰能力。     

多层前向神经网络结构的研究进展*

本文综述了的牢来多层前向神经网络结构的研究进展，总结了多怪前向网络结构调整的各种方法，并对各种方法进行了比较分析，最后提出了若干研究的问题。     

Genetic design of biologically inspired receptive fields for neural pattern recognition

This paper proposes a new method for the design, through simulated evolution, of biologically inspired receptive fields in feedforward neural networks (NNs). The method is intended to enhance pattern recognition performance by creating new neural architectures specifically tuned for a particular pattern recognition problem. It proposes a combined neural architecture composed of two networks in cascade: a feature extraction network (FEN) followed by a neural classifier. The FEN is composed of several layers with receptive fields constructed by additive superposition of excitatory and inhibitory fields. A genetic algorithm (GA) is used to select receptive field parameters to improve classification performance. The parameters are receptive field size, orientation, and bias as well as the number of different receptive fields in each layer. Based on a random initial population where each individual represents a different neural architecture, the GA creates new enhanced individuals. The method is applied to handwritten digit classification and face recognition. In both problems, results show strong dependency between NN classification performance and receptive field architecture. GA selected parameters of the receptive fields produced improvements in the classification performance on the test set up to 90.8% for the problem of handwritten digit classification and up to 84.2% for the face recognition problem. On the same test sets, results were compared advantageously to standard feedforward multilayer perceptron (MLP) NNs where receptive fields are not explicitly defined. The MLP reached a maximum classification performance of 84.9% and 77.5% in both problems, respectively.     

A learning law for density estimation

Probability density functions are estimated by an exponential family of densities based on multilayer feedforward networks. The role of the multilayer feedforward networks, in the proposed estimator, is to approximate the logarithm of the probability density functions. The method of maximum likelihood is used, as the main contribution, to derive an unsupervised backpropagation learning law to estimate the probability density functions. Computer simulation results demonstrating the use of the derived learning law are presented.