|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Dropout Rademacher complexity of deep neural networks显示文摘Great successes of deep neural networks have been witnessed in various real applications. Many algorithmic and implementation techniques have been developed; however, theoretical understanding of many aspects of deep neural networks is far from clear. A particular interesting issue is the usefulness of dropout,which was motivated from the intuition of preventing complex co-adaptation of feature detectors. In this paper,we study the Rademacher complexity of different types of dropouts, and our theoretical results disclose that for shallow neural networks(with one or none hidden layer) dropout is able to reduce the Rademacher complexity in polynomial, whereas for deep neural networks it can amazingly lead to an exponential reduction. | Wei GAO Zhi-Hua ZHOU | 2016 | Science China(Information Sciences)2016，59，7： | 8 |
| 2 | 稀疏L1范数最小二乘支持向量机显示文摘为了提高最小二乘支持向量机的训练速度,提出一种稀疏最小二乘支持向量机L1SLSSVM。该模型采用权重向量的L1范数控制分类间隔,最小二乘损失函数度量误差。将线性和核空间最小二乘支持向量机的训练归结为同一形式,均转化为仅有部分变量具非负约束的凸二次规划。对比SVM、LSSVM与SLSSVM的数值实验结果表明,L1SLSSVM具有好的稀疏性、高的分类精度和短的训练时间。 | 梁锦锦 吴德 | 2014 | 计算机工程与设计2014，35，1： | 6 |
| 3 | Kernel selection with spectral perturbation stability of kernel matrix显示文摘Kernel selection is one of the key issues both in recent research and application of kernel methods.This is usually done by minimizing either an estimate of generalization error or some other related performance measure. Use of notions of stability to estimate the generalization error has attracted much attention in recent years. Unfortunately, the existing notions of stability, proposed to derive the theoretical generalization error bounds, are difficult to be used for kernel selection in practice. It is well known that the kernel matrix contains most of the information needed by kernel methods, and the eigenvalues play an important role in the kernel matrix. Therefore, we aim at introducing a new notion of stability, called the spectral perturbation stability,to study the kernel selection problem. This proposed stability quantifies the spectral perturbation of the kernel matrix with respect to the changes in the training set. We establish the connection between the spectral perturbation stability and the generalization error. By minimizing the derived generalization error bound, we propose a new kernel selection criterion that can guarantee good generalization properties. In our criterion,the perturbation of the eigenvalues of the kernel matrix is efficiently computed by solving the derivative of a newly defined generalized kernel matrix. Both theoretical analysis and experimental results demonstrate that our criterion is sound and effective. | LIU Yong LIAO ShiZhong | 2014 | Science China(Information Sciences)2014，57，11： | 5 |
| 4 | 基于动态数据驱动的改进灰色马尔科夫模型黄金价格预测显示文摘将黄金数据的尖峰厚尾、异方差性及杠杆效应等统计特征与马尔科夫概率转移矩阵所具有的动态变化规律结合,提出一种改进的灰色马尔科夫模型.模型首先对数据进行统计分析,建立相应的概率统计模型并用此模型对系统发展变化趋势进行拟合.在拟合序列的基础上利用马尔科夫链的动态转移变化建立状态转移概率矩阵,采用动态数据驱动原理对未来每一步数据进行动态预测.模型既是统计方法与数据动态驱动的结合,克服了传统的灰色马尔科夫模型中对数据内在统计规律的忽视,实证表明其预测精度较灰色马尔科夫模型预测高,具有较好的实用性. | 张延利 张德生 | 2016 | 数学的实践与认识2016，46，13： | 2 |
| 5 | 基于灰色模型的节水灌溉面积非线性组合预测显示文摘对数据进行建模预测分析时,较多采用单个模型,而单个模型难以全面反映数据的变化规律.为发挥单个模型自身优势,利用组合原理将单模型组合形成组合预测模型,以提高预测精度.组合模型中常采用线性组合方法,然而被组合模型拟合值与原始数据不具有线性关系时采用该方法效果较差.利用神经网络的高度非线性拟合能力,构建BP神经网络的非线性组合模型,并应用到我国节水灌溉面积年度数据预测上.实证表明,非线性组合预测模型精度优于单模型及基于最优加权的线性组合预测模型. | 宁艳艳 樊颖军 方小艳 | 2016 | 河南科学2016，34，8： | 1 |
| 6 | A novel unsupervised method for new word extraction显示文摘New words could benefit many NLP tasks such as sentence chunking and sentiment analysis. However, automatic new word extraction is a challenging task because new words usually have no fixed language pattern, and even appear with the new meanings of existing words. To tackle these problems, this paper proposes a novel method to extract new words. It not only considers domain specificity, but also combines with multiple statistical language knowledge. First, we perform a filtering algorithm to obtain a candidate list of new words. Then, we employ the statistical language knowledge to extract the top ranked new words. Experimental results show that our proposed method is able to extract a large number of new words both in Chinese and English corpus, and notably outperforms the state-of-the-art methods. Moreover, we also demonstrate our method increases the accuracy of Chinese word segmentation by 10% on corpus containing new words. | Lili MEI Heyan HUANG Xiaochi WEI Xianling MAO | 2016 | Science China(Information Sciences)2016，59，9： | 0 |
| 7 | 原空间最小二乘支持向量机显示文摘最小二乘支持向量机在对偶空间训练,而原空间优化的近似解优于对偶空间优化的近似解,为此构造原空间最小二乘支持向量机(primal least square support vector machine,PLS-SVM)。将等式约束纳入目标函数构造无约束优化模型,根据最优解条件导出线性系统。对核矩阵进行三角分解,将线性和非线性最小二乘支持向量机的训练归结为相同形式,利用共轭梯度法求解。对比SVM和LS-SVM的仿真结果表明,PLS-SVM具有最高的分类精度和最短的训练时间。 | 梁锦锦 吴德 | 2014 | 计算机工程与设计2014，35，7： | 0 |
| 8 | 树上自旋系统的快速采样算法显示文摘自旋系统是统计物理学中用来描述微观粒子相互作用的重要框架,其可以描述伊辛模型,硬核模型,玻茨模型等统计物理学中的重要模型;通过求解自旋系统的配分函数可以得出物质的能量、磁矩等物理性质.作为一种重要的图模型,自旋系统在理论计算机、人工智能、概率论等领域中被称作马尔可夫随机场而广泛应用,其可以描述着色问题、图同态问题等图论中的重要问题.对图中的点和边赋予非负权重,自旋系统可以诱导出著名的吉布斯分布;配分函数的近似计算可以归约到对应的吉布斯采样问题,通过吉布斯采样可以求解系统的相关物理性质和统计规律.作为模型的简化,树上的自旋系统受到广泛研究;本文研究树上自旋系统的采样算法,并将其推广到树宽较小的图上.我们的主要工作可以列举如下:对于无外场的伊辛模型,基于节点的两种状态的对称性,可以直接计算出任意节点对应的边缘分布,然后通过简单变量的组合来模拟吉布斯分布.类似地,着色问题和玻茨模型也可以基于状态的对称性用简单变量来模拟吉布斯分布.对于一般的自旋系统,无法保证状态的对称性,我们先递归地计算出所有节点的边缘分布,然后基于这些边缘分布进行采样,并通过简单变量的组合来模拟吉布斯分布.对于普通图,我们引入树宽的概念来度量图与树的相似性,并且基于节点间的独立性将算法推广到树宽为2的伪森林和仙人掌图中.我们的算法仅需要线性时间来得到吉布斯分布中的一个样本,在时间复杂度上优于基于马尔可夫链蒙特卡洛模拟的采样算法. | 白宗磊 王捍贫 曹永知 王璐璐 | 2022 | 计算机学报2022，45，10： | 0 |
| 9 | 基于双向差分GM(1,1)模型当季国内生产总值预测显示文摘以灰色系统理论建模中的GM(1,1)模型为基础,结合双向差分原理,建立基于双向差分的GM(1,1)模型.该模型克服了大数据建模中对数据量的限制,为'贫数据'及'数据信息不确定'的这类数据提供一种建模思路.实证分析表明,基于双向差分的GM(1,1)模型预测精度优于灰色GM(1,1)模型及大样本建模中的ARMA模型. | 吕海侠 张延利 | 2017 | 河南科学2017，35，8： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员