基于统计分析的分阶段进行神经网络方法

基于统计分析和分阶段进化，提出一种新的进化神经网络设计方法，本文方法的进化过程分三个阶段：第一阶段，首先按训练样本统计特性设计较小规模的神经网络，第二阶段，引入所有训练样本，在第一阶段的基础上，逐步扩展网络结构，天加的神经元总是单独训练并以抵消原网络的输出误差为其训练目标，直至训练网络达到误差要求，第三阶段，利用统计方法，将网络中非线性变换作用相似的神经元合并，简化网络结构，本文方法一方面减轻了进化算法的压力，另一方面指出了网络进化的方向使得进化网络的学习过程不再是黑箱问题，计算机仿真实验表明，该方法是有效的。     

基于进化规划的神经网络群的设计方法

提出一种基于进化规划的神经网络群的自动设计方法．该方法不仅使得神经网络群中的个体网络倾向于完成不同的子任务，同时各神经网络个体在进化过程中不断寻找最好的协作关系，而且神经网络群的规模和结构不需预先设定．仿真试验表明，该算法是有效的。     

基于模糊进化规划和分层方法的神经网络设计方法

本文提出一种模糊进化规划，用于前向神经网络的设计．该方法通过对神经元的部分解群体的进化，缩短了个体的编码长度，显著地减轻了计算量，同时这种方法不但能够在很大程度上简化适应值的计算，更重要的是能够降低适应值空间的复杂性，从而能够加速进化算法收敛到全局最优点．仿真结果显示，本文提出的算法能够有效抑制进化规划算法初期收敛的发生，有效地提高多层前向神经网络收敛精度，并可获得更为简洁的网络结构．     

SEFNN:一种基于结构进化的前馈神经网络设计算法

遗传算法是一种模拟自然选择和进化的随机搜索算法，它的搜索能够遍及整个解空间，容易得到全局最优解．目前主要的编码方式都是将结构和连接权值等信息编码成串式的基因，这不利于在遗传过程中保留个体的子结构信息，也难于设计兼顾基因型与表现型的遗传算子；在前馈神经网络的进化中引入BP训练方面，也不分良莠对所有后代进行训练，形成资源浪费．为克服这些问题，提出了一种基于结构进化的前馈神经网络设计算法SEFNN，该算法使用一种紧缩矩阵编码、新型结构化交叉算子、修订的变异算子和精英训练法则，充分考虑了基因型与表现型之间的关系，适当加大变异搜索速度，并采用选拔训练方式，从而提高了进化神经网络的效率．实验表明该算法获得的解无论在网络规模还是测试精度上都有优越的性能表现，并已应用于肺癌早期细胞病理诊断系统，具有良好的效果．     

进化策略求解Hopfield神经网络

提出了一种进化策略求解ＨＯｐｆｉｅｌｄ神经网络的方法。该进化策略分三个阶段,即第一阶段只在较小区间上求出局部优化解;然后,在此基础上,由第二阶段求出较大区间上的局部优化解;最后由第三阶段求出全局优化解。同时采用Ｈｏｐｆｉｅｌｄ神经网络动态方程指导第一阶段的局部进化策略的进化方向,因而大大加快了优化搜索速度。在分阶段的进化策略中,其第一阶段只需搜索较小区间、第二和第三阶段的搜索则建立在其前一阶段的基     

神经网络结构设计的准则和方法

神经网络结构设计一直是一个很有意义但又难以解决的问题，文中回顾并总结了近年来神经网络结构设计的研究状况。首先分析了在神经网络结构设计中应考虑的４个准则，即神经网络的函数逼近误差、网络结构的复杂性、网络的泛化能力和网络的容错性，随后从构造法、删除法和进化方法３个方面介绍了各种神经网络的设计，并提出了今后研究的展望。     

进化神经网络研究综述

进化算法(EAs)与神经网络(NN)的结合已形成了一个新的领域一进化神经网络,在神经网络的研究中举足轻重。本文通过讨论和总结进化神经网络中的关键技术和现状，概述了其设计与构造的趋势。所讨论的是：(1)进化神经网络的研究方法；(2)进化模型；(3)应用实例及关键技术；(4)研究方向。     

一种新型的动态递归神经网络及其全自动设计算法

本文基于非线形自回归滑动平均模型NARMA模 型和前馈神经网络建模的思想,提出一种输入层与输出层神经元递归的动态递归神经网络; 基于进化计算中遗传算法和进化策略与自寻优BP算法的不同结合方式,提出两种动态递归神 经网络全自动高效设计算法,实现了网络结构、权重和自反馈增益同时优化学习,实例应用 表明所提网络结构及其设计算法的有效性．     

B—P网络泛化性能的改善

在神经网络的训练过程中存在“过度吻合”的现象,即训练样本的误差已达到非常小的一个值,但是非训练样本的误差非常大,造成神经网络的泛化性能不好。本文说明了泛化性能与隐层节点数的关系,并提出了通过改变性能函数来改善B－P网络的泛化性能的方法。     

基于进化式模糊神经网络的时间序列预测系统

文章介绍了一种基于进化式模糊神经网络时间预测系统，它是一种快速自适应的局部学习模型；进化式模糊神经网络是一个特殊类型的神经网络，它能通过进化其结构和参数来容纳新的数据。文章重点介绍了网络结构、学习方法及创建、修剪、聚合规则节点的算法；实验结果表明：模糊隶属函数的个数，规则的修剪和聚合等训练参数，与网络的行为和预测结果有很重要的关系。     

基于进化计算的神经网络设计与实现

基于进化算法可有产解决神经网络设计和实现中存在的一些问题,使网络具有更优的性能。在此对基于进化计算的神经网络设计和实现的研究内容及进展情况进行综述,讲座了网络实现的关键问题,包括网络权重的进化训练,网络结构进化设计,学习规则进化选取以及进化操作算子设计等,并分析了相关的研究和发展方向。     

进化神经网络研究进展

进化神经网络是将进化算法应用于神经网络的构造、学习而得到的神经网络，具有很强的鲁棒适应性。综述了进化神经网络方法及其应用研究新进展，对研究中出现的一些问题进行了讨论与展望。     

Memetic evolutionary training for recurrent neural networks: an application to time-series prediction

Abstract: Artificial neural networks are bio-inspired mathematical models that have been widely used to solve complex problems. The training of a neural network is an important issue to deal with, since traditional gradient-based algorithms become easily trapped in local optimal solutions, therefore increasing the time taken in the experimental step. This problem is greater in recurrent neural networks, where the gradient propagation across the recurrence makes the training difficult for long-term dependences. On the other hand, evolutionary algorithms are search and optimization techniques which have been proved to solve many problems effectively. In the case of recurrent neural networks, the training using evolutionary algorithms has provided promising results. In this work, we propose two hybrid evolutionary algorithms as an alternative to improve the training of dynamic recurrent neural networks. The experimental section makes a comparative study of the algorithms proposed, to train Elman recurrent neural networks in time-series prediction problems.     

基于超像素的人工神经网络图像分类

基于人工神经网络对图像标签分类,为简化后续数据处理,先用Normalized Cut将图像分割为超像素,提取特征向量,通过输入训练样本集,对网络进行训练,在最小均方误差意义下得到网络参数,最后在Matlab的仿真实验中基于不同隐藏层节点,使用BP神经网络模型对图像超像素进行分类。     

基于进化神经网络的短期电网负荷预测算法

本文提出了一种基于进化神经网络的短期电网负荷预测算法。该算法使用改进的人工蜂群算法与BP神经网络融合生成进化神经网络,然后使用改进的人工蜂群算法对进化神经网络的偏置和权重进行优化。该算法将火电历史负荷数据作为输入,使用进化神经网络训练预测模型,预测未来一段时间内的电网负荷。首先,获取历史负荷数据。然后,将获取到的数据输入到进化神经网络模型中进行训练。在训练过程中,采用了改进的人工蜂群算法对进化神经网络对神经网络的权重和偏置进行优化,提高模型的预测精度。人工蜂群算法作为一种全局搜索算法,可以有效地探索模型参数空间,找到最优的模型参数组合,从而提高模型的预测精度。为了验证所提出的负荷预测方法的有效性,我们使用了火电网负荷数据进行了测试。实验结果表明本文提出的进化神经网络在短期电网负荷预测方面表现出了良好的预测精度和实用性。与传统的预测方法相比,该算法的预测误差更小,预测结果更加准确可靠。     

A fast procedure for the training of neural networks

A new training paradigm for artificial neural networks is described. The technique utilizes a polynomial approximation to the sigmoidal processing function and directly integrates principal components analysis (PCA) into the network training philosophy. A major benefit of the new technique is that off-line network training is ‘one-shot’, contrary to the standard iterative techniques available in the literature. Further training may be performed on-line in a recursive fashion, yielding an adaptive neural network. Additionally, the new philosophy incorporates a systematic procedure for determining the number of neurons in the hidden layer of the network. The training procedure is first described and the implications of the training philosophy discussed. Some results, including applications to industrial chemical processes, are then presented to highlight the power of the technique. The systems considered are a continuous stirred tank reactor and a polymerization reactor.     

Evolutionary Learning of Modular Neural Networks with Genetic Programming

Evolutionary design of neural networks has shown a great potential as a powerful optimization tool. However, most evolutionary neural networks have not taken advantage of the fact that they can evolve from modules. This paper presents a hybrid method of modular neural networks and genetic programming as a promising model for evolutionary learning. This paper describes the concepts and methodologies for the evolvable model of modular neural networks, which might not only develop new functionality spontaneously, but also grow and evolve its own structure autonomously. We show the potential of the method by applying an evolved modular network to a visual categorization task with handwritten digits. Sophisticated network architectures as well as functional subsystems emerge from an initial set of randomly-connected networks. Moreover, the evolved neural network has reproduced some of the characteristics of natural visual system, such as the organization of coarse and fine processing of stimuli in separate pathways.     

A novel model by evolving partially connected neural network for stock price trend forecasting

This paper proposes a novel model by evolving partially connected neural networks (EPCNNs) to predict the stock price trend using technical indicators as inputs. The proposed architecture has provided some new features different from the features of artificial neural networks: (1) connection between neurons is random; (2) there can be more than one hidden layer; (3) evolutionary algorithm is employed to improve the learning algorithm and training weights. In order to improve the expressive ability of neural networks, EPCNN utilizes random connection between neurons and more hidden layers to learn the knowledge stored within the historic time series data. The genetically evolved weights mitigate the well-known limitations of gradient descent algorithm. In addition, the activation function is defined using sin(x) function instead of sigmoid function. Three experiments were conducted which are explained as follows. In the first experiment, we compared the predicted value of the trained EPCNN model with the actual value to evaluate the prediction accuracy of the model. Second experiment studied the over fitting problem which occurred in neural network training by taking different number of neurons and layers. The third experiment compared the performance of the proposed EPCNN model with other models like BPN, TSK fuzzy system, multiple regression analysis and showed that EPCNN can provide a very accurate prediction of the stock price index for most of the data. Therefore, it is a very promising tool in forecasting of the financial time series data.     

Differential Evolution Training Algorithm for Feed-Forward Neural Networks

An evolutionary optimization method over continuous search spaces, differential evolution, has recently been successfully applied to real world and artificial optimization problems and proposed also for neural network training. However, differential evolution has not been comprehensively studied in the context of training neural network weights, i.e., how useful is differential evolution in finding the global optimum for expense of convergence speed. In this study, differential evolution has been analyzed as a candidate global optimization method for feed-forward neural networks. In comparison to gradient based methods, differential evolution seems not to provide any distinct advantage in terms of learning rate or solution quality. Differential evolution can rather be used in validation of reached optima and in the development of regularization terms and non-conventional transfer functions that do not necessarily provide gradient information. This revised version was published online in June 2006 with corrections to the Cover Date.