基于局部收敛权阵进化的BP神经网络MapReduce训练

为提高大样本集情况下BP神经网络的训练效率,提出了一种基于局部收敛权阵进化的BP神经网络MapReduce训练方法,以各Map任务基于其输入数据分片训练产生的局部收敛权阵作为初始种群,在Reduce任务中通过种群进化,选取适应度最高的权阵作为Map任务下一轮训练的初始权阵,直至该权阵对所有输入数据分片收敛。实验结果表明,与现有方法相比,该方法可有效避免MapReduce训练BP神经网络时容易陷入局部收敛的问题,并大大减少训练时间。     

基于改进遗传算法的多示例神经网络优化

多示例神经网络是一类用于求解多示例学习问题的神经网络,但由于其中有不可微函数,使用反向传播训练方法时需要采用近似方法,因此多示例神经网络的预测准确性不高。〖BP）〗为了提高预测准确性,构造了一类优化多示例神经网络参数的改进遗传算法, 借助基于反向传播训练的局部搜索算子、排挤操作和适应性操作概率计算方式来提高收敛速度和防止早熟收敛。通过公认的数据集上实验结果的分析和对比,证实了这个改进的遗传算法能够明显地提高多示例神经网络的预测准确性,同时还具有比其他算法更快的收敛速度。     

基于三个并行BP神经网络的机器人逆运动学求解

针对传统的求逆运动学方法相当复杂,一般的神经网络收敛速度慢、精度不高的缺陷,提出一种由3个并行的BP(BackPropagation)神经网络组成的系统来解决运动学逆问题,输入数据分别通过3个并行的BP神经网络,再对输出分别求正运动学解,然后计算误差,最后选择误差最小的作为系统的输出;仿真表明,该方法可以有效地解决运动学逆问题,使用3个并行的BP神经网络可以使整个系统的误差更小,BP神经网络使用Levenberg-Marquardt训练方法,可以使学习收敛速度更快。     

基于输入分片扰乱的BP神经网络MapReduce训练方法

BP神经网络的MapReduce训练中,每个map训练任务产生的中间权阵只对该训练节点上的输入分片收敛,为提高BP神经网络的训练效率,保证MapReduce训练的全局收敛性,提出一种基于输入分片扰乱的MapReduce训练方法。通过对训练样本集进行系统抽样来扰乱输入分片,并产生新的输入分片,依靠新的输入分片以map任务的原权阵为基础进行迭代训练,可加速MapReduce训练达到收敛的进程;为提高map训练任务的局部收敛速度,在每轮次的训练完成后,选取map任务产生的权阵中全局误差最小者,作为下轮次各map训练任务的初始权阵。在Hadoop集群上的实验表明,该方法可使MapReduce训练BP神经网络的效率得到很大提升。     

Hadoop下多模式并行分类算法及其应用研究

根据人工神经网络自组织、高度并行以及具有非线性映射能力的特点,提出一种基于云计算的Hadoop多模式并行分类算法。通过将自组织映射网络与多个并行BP神经网络结合,提高多语义模式中复杂分类问题的学习效率和训练精度。采用Hadoop平台下的Map Reduce框架实现算法的并行处理,解决大规模数据样本训练时内存开销大、通信耗时长的问题。实验结果表明,与传统单BP多输出分类算法相比,该算法训练速度更快、分类精度更高,在处理大规模数据集时具有实时和高效的特性。     

基于改进BP神经网络的路由器流量预测方法

为了减少路由器的能耗,提出了一种改进的反向传播(BP)神经网络预测路由器流量的方法,在传统BP神经网络的基础上加入学习率自适应算法,提高路由器流量的预测精度和训练速度.运用MATLAB平台构建BP神经网络对网络流量进行建模、训练并预测.仿真结果表明:相较传统预测模型,运用改进的BP神经网络预测模型精度较高,训练速度较快,路由器可以更快、更准确地调整工作状态,实现了有效节能,具有很好的应用前景.     

应用模糊神经网络预测油田产量

为了研究受多变量、时变和不确定因素影响的油田产量预测问题,将模糊逻辑推理技术与人工神经网络相结合,构建具有模糊逻辑推理和学习功能的模糊神经网络(FNN)系统。该系统基于现有的油田开发历史数据,建立相应的规则集,使用神经网络的训练方法(如梯度下降学习算法),在训练过程中调整参数,并自适应增加规则,以使系统的输出最佳地逼近于目标样本。通过对某油田的实际开发历史数据的拟合与测试,结果表明该模糊神经网络能够较精确地预测未来的油产量,与常规的BP神经网络相比,其预测精度更高、训练速度更快。因此,基于模糊神经网络(FNN)的油田产量预测方法研究具有较好的实际应用价值。     

一种改进的BP神经网络

BP神经网络利厢误差的反向传播调整神经网络的权值,BP神经网络的训练速度和训练误差很大程度上取决于学习逑率和动量因子的设置。本文提出了一种改进的BP神经网络模型,学习速率和动量因子随误差实时调节,并进行了仿真。仿真结果表明,改进的BP神经网络比传统的BP神经网络收敛更快,误差更小。     

基于改进遗传算法的神经网络手写体数字识别

BP网络作为人工神经网络的重要分支,已经广泛应用于手写数字识别。然而BP神经网络存在训练时间长、易陷入局部最小的问题。为了克服这些问题,提出了一种改进的遗传算法,并用该算法来优化神经网络的权值和阈值。最后,利用基于该算法的神经网络对大量USPS手写数字样本集进行训练。实验结果表明,该算法比单纯的BP算法具有更快的识别速率。     

粗集神经网络及其在齿轮箱故障识别中的应用

为有效解决故障诊断中的故障识别问题,提出了一种以强耦合方式进行集成的粗集-神经网络的故障识别方法.该方法通过粗糙集对获得的故障属性进行降维预处理并获取粗集规则,再以所得的粗集规则与BP神经网络进行强耦合对故障进行识别.对该方法以齿轮箱故障识别进行了仿真实验,与BP神经网络的识别效果进行对比,结果表明了粗集神经网络在训练速度、测试精度方面的有效性.     

A novel virtual sample generation method based on Gaussian distribution

Traditional machine learning algorithms are not with satisfying generalization ability on noisy, imbalanced, and small sample training set. In this work, a novel virtual sample generation (VSG) method based on Gaussian distribution is proposed. Firstly, the method determines the mean and the standard error of Gaussian distribution. Then, virtual samples can be generated by such Gaussian distribution. Finally, a new training set is constructed by adding the virtual samples to the original training set. This work has shown that training on the new training set is equivalent to a form of regularization regarding small sample problems, or cost-sensitive learning regarding imbalanced sample problems. Experiments show that given a suitable number of virtual sample replicates, the generalization ability of the classifiers on the new training sets can be better than that on the original training sets.     

Learning from imperfect data

For a supervised learning method, the quality of the training data or the training supervisor is very important in generating reliable neural networks. However, for real world problems, it is not always easy to obtain high quality training data sets. In this research, we propose a learning method for a neural network ensemble model that can be trained with an imperfect training data set, which is a data set containing erroneous training samples. With a competitive training mechanism, the ensemble is able to exclude erroneous samples from the training process, thus generating a reliable neural network. Through the experiment, we show that the proposed model is able to tolerate the existence of erroneous training samples in generating a reliable neural network.The ability of the neural network to tolerate the existence of erroneous samples in the training data lessens the costly task of analyzing and arranging the training data, thus increasing the usability of the neural networks for real world problems.     

Incremental training of support vector machines

We propose a new algorithm for the incremental training of support vector machines (SVMs) that is suitable for problems of sequentially arriving data and fast constraint parameter variation. Our method involves using a "warm-start" algorithm for the training of SVMs, which allows us to take advantage of the natural incremental properties of the standard active set approach to linearly constrained optimization problems. Incremental training involves quickly retraining a support vector machine after adding a small number of additional training vectors to the training set of an existing (trained) support vector machine. Similarly, the problem of fast constraint parameter variation involves quickly retraining an existing support vector machine using the same training set but different constraint parameters. In both cases, we demonstrate the computational superiority of incremental training over the usual batch retraining method.     

不平衡指派问题的差额法求解及其应用

提出了用差额法求解最大值的不平衡指派问题,并在训练评估与决策系统中,应用该方法求解在单位数多于任务数时的任务分配方案,使得训练指数达到最大。经验证用这个方法求解最大值的不平衡指派问题,操作简单,易于编程。     

团队项目训练法在《国际贸易实务》教学中的应用

团队项目训练法是项目教学法的延伸和发展,也是设计教学法、体验教学法、情景模拟教学法等行动导向教学方式的综合运用。文章浅析了团队项目训练法在高职《国际贸易实务》课程教学中的应用,说明团队项目训练法对于调动学生积极性和主动性、培养学生思考能力和观察能力、提高教学效果等方面具有显著的成效,并总结了开展团队项目训练需要注意的问题。     

计算机类专业实训教学项目化研究

针对计算机类专业"两旺两难"的办学情况,分析当前实训教学存在的问题,提出使用项目教学解决这些问题的原则和具体办法,并给出实训教学项目化案例。教学实践表明,项目化能提高计算机类专业学生的专业能力。     

基于双阈值的增强型AdaBoost快速算法

在应用AdaBoost算法的人脸检测中,针对训练时间太长及权重调整过适应等问题,提出一种基于特征值等分和双阈值的增强型AdaBoost快速训练算法,给出了双阈值的快速搜索方法。在MIT-CBCL人脸和非人脸训练库上对算法进行了实现。实验结果显示,改进后的双阈值增强型AdaBoost算法简化了训练过程,训练速度提高50倍,收敛速度也更快。使用训练得到的检测器对MIT+CMU人脸测试库进行了测试,结果表明,该方法在检测精度和速度等方面都优于单阈值方法。     

Lazy Learning in Radial Basis Neural Networks: A Way of Achieving More Accurate Models

Radial Basis Neural Networks have been successfully used in a large number of applications having in its rapid convergence time one of its most important advantages. However, the level of generalization is usually poor and very dependent on the quality of the training data because some of the training patterns can be redundant or irrelevant. In this paper, we present a learning method that automatically selects the training patterns more appropriate to the new sample to be approximated. This training method follows a lazy learning strategy, in the sense that it builds approximations centered around the novel sample. The proposed method has been applied to three different domainsan artificial regression problem and two time series prediction problems. Results have been compared to standard training method using the complete training data set and the new method shows better generalization abilities.     

基于信息熵和深度学习的无参考图像质量评价方法研究*

现有使用卷积神经网络进行图像质量评价的方法,存在训练数据量不足、局部图像块失真分数不能确定等问题。针对这些问题,本文提出了一种基于信息熵的卷积网络训练方法,在考虑信息熵对图像质量影响的基础上,将LIVE数据集中的失真图像进行分块处理,扩大训练集。同时,用分块后的信息熵代表不同分块对失真图像的质量影响程度,并根据该信息熵对卷积神经网络的损失函数进行了调整。实验结果表明,本文提出的模型预测结果更为接近人类视觉感知。     

Multiclass Lagrangian support vector machine

A support vector machine (SVM) has been developed for two-class problems, although its application to multiclass problems is not straightforward. This paper proposes a new Lagrangian SVM (LSVM) for application to multiclass problems. The multiclass Lagrangian SVM is formulated as a single optimization problem considering all the classes together, and a training method tailored to the multiclass problem is presented. A multiclass output representation matrix is defined to simplify the optimization formulation and associated training method. The proposed method is applied to some benchmark datasets in repository, and its effectiveness is demonstrated via simulation.