神经网络中克服局部最小的BP—EP混合算法

人工神经网络在很多领域有着成功的应用,神经网络有许多学习算法,BP算法是前向多层神经网络的典型算法,但BP算法有时会陷入局部最小解,进化规划（EP）是一种随机优化技术,它可以发现全局成解,当网络学习过程陷入局部最小时,利用EP确定BP算法中的学习速率,使学习过程逸出局部最小,结合具体例子给出了算法实现的具体操作步骤和实验结果。     

结构增强的属性网络表示学习

属性网络表示学习旨在结合结构信息与属性信息为网络中的节点学习统一的向量表示。现有的属性网络表示学习方法在学习属性信息时与其互补的结构信息增强不足,从而影响最终表示。针对这一问题,提出一种结构增强的属性网络表示学习方法,以提高表示质量。该方法基于网络归一化邻接矩阵和属性矩阵通过自动编码器提取增强网络全局结构特性的属性信息,使用skip-gram模型捕捉局部结构信息,引入一个联合损失函数使结构信息与属性信息在同一向量空间中得以表示。在三个真实属性网络数据上进行节点分类和链路预测实验,效果较目前流行的网络表示学习方法优势明显。     

Comparison of Stochastic Global Optimization Methods to Estimate Neural Network Weights

Training a neural network is a difficult optimization problem because of numerous local minima. Many global search algorithms have been used to train neural networks. However, local search algorithms are more efficient with computational resources, and therefore numerous random restarts with a local algorithm may be more effective than a global algorithm. This study uses Monte-Carlo simulations to determine the efficiency of a local search algorithm relative to nine stochastic global algorithms when using a neural network on function approximation problems. The computational requirements of the global algorithms are several times higher than the local algorithm and there is little gain in using the global algorithms to train neural networks. Since the global algorithms only marginally outperform the local algorithm in obtaining a lower local minimum and they require more computational resources, the results in this study indicate that with respect to the specific algorithms and function approximation problems studied, there is little evidence to show that a global algorithm should be used over a more traditional local optimization routine for training neural networks. Further, neural networks should not be estimated from a single set of starting values whether a global or local optimization method is used.     

基于生成对抗网络的图像去雾算法

与基于图像增强的去雾算法和基于物理模型的去雾算法相比,基于深度学习的图像去雾方法在一定程度上提高计算效率,但在场景复杂时仍存在去雾不彻底及颜色扭曲的问题.针对人眼对全局特征和局部特征的感受不同这一特性,文中构建基于生成对抗网络的图像去雾算法.首先设计多尺度结构的生成器网络,分别以全尺寸图像和分割后的图像块作为输入,提取图像的全局轮廓信息和局部细节信息.然后设计一个特征融合模块,融合全局信息和局部信息,通过判别网络判断生成无雾图像的真假.为了使生成的去雾图像更接近对应的真实无雾图像,设计多元联合损失函数,结合暗通道先验损失函数、对抗损失函数、结构相似性损失函数及平滑L1损失函数训练网络.在合成数据集和真实图像上与多种算法进行实验对比,结果表明,文中算法的去雾效果较优.     

A learning automata-based algorithm for determination of the number of hidden units for three-layer neural networks

There is no method to determine the optimal topology for multi-layer neural networks for a given problem. Usually the designer selects a topology for the network and then trains it. Since determination of the optimal topology of neural networks belongs to class of NP-hard problems, most of the existing algorithms for determination of the topology are approximate. These algorithms could be classified into four main groups: pruning algorithms, constructive algorithms, hybrid algorithms and evolutionary algorithms. These algorithms can produce near optimal solutions. Most of these algorithms use hill-climbing method and may be stuck at local minima. In this article, we first introduce a learning automaton and study its behaviour and then present an algorithm based on the proposed learning automaton, called survival algorithm, for determination of the number of hidden units of three layers neural networks. The survival algorithm uses learning automata as a global search method to increase the probability of obtaining the optimal topology. The algorithm considers the problem of optimization of the topology of neural networks as object partitioning rather than searching or parameter optimization as in existing algorithms. In survival algorithm, the training begins with a large network, and then by adding and deleting hidden units, a near optimal topology will be obtained. The algorithm has been tested on a number of problems and shown through simulations that networks generated are near optimal.     

基于对比学习的全局增强动态异质图神经网络

图神经网络由于其对图结构数据的强大表征能力近年来受到广泛关注. 现有图神经网络方法主要建模静态同质图数据,然而现实世界复杂系统往往包含多类型动态演化的实体及关系,此类复杂系统更适合建模为动态异质图. 目前,动态异质图表示学习方法主要集中于半监督学习范式,其存在监督信息昂贵和泛化性较差等问题. 针对以上问题,提出了一种基于对比学习的全局增强动态异质图神经网络. 具体地,所提网络首先通过异质层次化注意力机制根据历史信息来生成未来的邻近性保持的节点表示,然后通过对比学习最大化局部节点表示和全局图表示的互信息来丰富节点表示中的全局语义信息. 实验结果表明,提出的自监督动态异质图表示学习方法在多个真实世界数据集的链路预测任务上的AUC指标平均提升了3.95%.

     

A statistical complement to deterministic algorithms for the retrieval of aerosol optical thickness from radiance data

As a complement to the conventional deterministic geophysical algorithms, we consider a faster, but less accurate approach: training regression models to predict aerosol optical thickness (AOT) from radiance data. In our study, neural networks trained on a global data set are employed as a global retrieval method. Inverse distance spatial interpolation and region-specific neural networks trained on restricted, localized areas provide local models. We then develop two integrated statistical methods: local error correction of global retrievals and an optimal weighted average of global and local components. The algorithms are evaluated on the problem of deriving AOT from raw radiances observed by the Multi-angle Imaging SpectroRadiometer (MISR) instrument onboard NASA's Terra satellite. Integrated statistical approaches were clearly superior to global and local models alone. The best compromise between speed and accuracy was obtained through the weighted averaging of global neural networks and spatial interpolation. The results show that, while much faster, statistical retrievals can be quite comparable in accuracy to the far more computationally demanding deterministic methods. Differences in quality vary with season and model complexity.     

全局和局部信息融合的案情关键要素识别

司法人工智能中主要挑战性问题之一是案情关键要素识别,现有方法仅将案情要素作为一个命名实体识别任务,导致识别出的多数信息是无关的.另外,也缺乏对文本的全局信息和词汇局部信息的有效利用,导致要素边界识别的效果不佳.针对这些问题,提出一种融合全局和局部信息的关键案情要素识别方法.所提方法首先利用BERT模型作为司法文本的输入共享层以提取文本特征.然后,在共享层之上建立司法案情要素识别、司法文本分类(全局信息)、司法中文分词(局部信息)这3个子任务进行联合学习模型.最后,在两个公开数据集上测试所提方法的效果,结果表明:所提方法 F1值均超过了现有的先进方法,提高了要素实体分类的准确率并减少了识别边界错误问题.     

Locally recurrent neural networks for wind speed prediction using spatial correlation

This paper deals with the wind speed prediction in wind farms, using spatial information from remote measurement stations. Owing to the temporal complexity of the problem, we employ local recurrent neural networks with internal dynamics, as advanced forecast models. To improve the prediction performance, the training task is accomplished using on-line learning algorithms based on the recursive prediction error (RPE) approach. A global RPE (GRPE) learning scheme is first developed where all adjustable weights are simultaneously updated. In the following, through weight grouping we devise a simplified method, the decoupled RPE (DRPE), with reduced computational demands. The partial derivatives required by the learning algorithms are derived using the adjoint model approach, adapted to the architecture of the networks being used. The efficiency of the proposed approach is tested on a real-world wind farm problem, where multi-step ahead wind speed estimates from 15 min to 3 h are sought. Extensive simulation results demonstrate that our models exhibit superior performance compared to other network types suggested in the literature. Furthermore, it is shown that the suggested learning algorithms outperform three gradient descent algorithms, in training of the recurrent forecast models.     

基于循环密集连接融合更多局部特征的肝脏分割

由于腹部图像中肝脏区域的复杂性和传统分割方法特征提取上的局限性等原因,肝脏分割领域仍存在着很多挑战.针对现有分割网络在肝脏区域的全局信息和局部信息处理上存在的不足,设计了一种融合更多局部特征的循环密集连接网络的分割方法.该方法将循环密集连接模块和局部特征补充模块整合为编码过程的学习单元,使编码单元融合深层次全局信息和更多尺度的局部特征信息.最后,在解码过程后,利用softmax函数输出分割结果.在LiTS数据集上该方法在多个评价指标中表现优异,精确度达到了95.1％.此外,在Data_67数据集上的相关实验也证明了该方法具有很好的泛化性能.实验表明,密集连接融合更多的局部信息,能够使肝脏分割模型的性能更加优异.     

基于双鉴别网络的生成对抗网络图像修复方法

针对现有神经网络图像修复方法的修复结果在视觉连通性上存在结构扭曲、训练过程中易陷入过度学习等问题,提出了一种基于双鉴别网络的生成对抗网络（GAN）图像修复方法。该方法的修复模型使用了修复网络、全局鉴别网络和局部鉴别网络。修复网络将待修复图像破损区域用相似信息填充后作为输入,极大地提高了生成图像的速度与质量;全局鉴别网络综合采用图像全局的边缘结构信息和特征信息以保证修复网络输出的修复图像结果符合视觉连通性;而局部鉴别网络在鉴别输出图像的同时,利用在多个图像中寻找到的辅助特征块来提高鉴别的泛化能力,很好地抑制了修复网络在特征过于集中或单一时容易过度学习的问题。实验结果表明,所提修复方法在人脸类图像上具有较好的修复效果,且在不同种类图像上有非常好的适用性,其峰值信噪比（PSNR）和结构相似性（SSIM）指标比当前基于深度学习且修复效果较好的几种方法更优。     

Enhancing MLP networks using a distributed data representation

Multilayer perceptron (MLP) networks trained using backpropagation can be slow to converge in many instances. The primary reason for slow learning is the global nature of backpropagation. Another reason is the fact that a neuron in an MLP network functions as a hyperplane separator and is therefore inefficient when applied to classification problems in which decision boundaries are nonlinear. This paper presents a data representational approach that addresses these problems while operating within the framework of the familiar backpropagation model. We examine the use of receptors with overlapping receptive fields as a preprocessing technique for encoding inputs to MLP networks. The proposed data representation scheme, termed ensemble encoding, is shown to promote local learning and to provide enhanced nonlinear separability. Simulation results for well known problems in classification and time-series prediction indicate that the use of ensemble encoding can significantly reduce the time required to train MLP networks. Since the choice of representation for input data is independent of the learning algorithm and the functional form employed in the MLP model, nonlinear preprocessing of network inputs may be an attractive alternative for many MLP network applications.     

Nonlinear Systems Identification via Two Types of Recurrent Fuzzy CMAC

Normal fuzzy CMAC neural network performs well for nonlinear systems identification because of its fast learning speed and local generalization capability for approximating nonlinear functions. However, it requires huge memory and the dimension increases exponentially with the number of inputs. It is difficult to model dynamic systems with static fuzzy CMACs. In this paper, we use two types of recurrent techniques for fuzzy CMAC to overcome the above problems. The new CMAC neural networks are named recurrent fuzzy CMAC (RFCMAC) which add feedback connections in the inner layers (local feedback) or the output layer (global feedback). The corresponding learning algorithms have time-varying learning rates, the stabilities of the neural identifications are proven.     

Global exponential stability of recurrent neural networks forsolving optimization and related problems

Global exponential stability is a desirable property for dynamic systems. The paper studies the global exponential stability of several existing recurrent neural networks for solving linear programming problems, convex programming problems with interval constraints, convex programming problems with nonlinear constraints, and monotone variational inequalities. In contrast to the existing results on global exponential stability, the present results do not require additional conditions on the weight matrices of recurrent neural networks and improve some existing conditions for global exponential stability. Therefore, the stability results in the paper further demonstrate the superior convergence properties of the existing neural networks for optimization.     

基于视觉强化学习的数字芯片全局布局方法

在数字芯片后端设计中,全局布局需要同时兼顾线长与合法化,是一个组合优化问题。传统的退火算法或者遗传算法耗时且容易陷入局部最优,目前强化学习的解决方案也很少利用布局的整体视觉信息。为此,提出一种融合视觉信息的强化学习方法实现端到端的全局布局。在全局布局中,将电路网表信息映射为多个图像级特征,采用卷积神经网络(convolutional neural network, CNN)和图卷积网络(graph convolutional network, GCN)将图像特征和网表信息相融合,设计了一整套策略网络和价值网络,实现对全局布局的全面分析和优化。在ISPD2005基准电路上进行实验,结果证明设计的网络收敛速度加快7倍左右,布局线长减少10%～32%,重叠率为0%,可为数字芯片全局布局任务提供高效合理的方案。     

一种基于局部加权均值的领域适应学习框架

最大均值差异(Maximum mean discrepancy, MMD)作为一种能有效度量源域和目标域分布差异的标准已被成功运用.然而, MMD作为一种全局度量方法一定程度上反映的是区域之间全局分布和全局结构上的差异.为此, 本文通过引入局部加权均值的方法和理论到MMD中, 提出一种具有局部保持能力的投影最大局部加权均值差异(Projected maximum local weighted mean discrepancy, PMLWD)度量,%从而一定程度上使得PMLWD更能有效度量源域和目标域中局部分块之间的分布和结构上的差异,结合传统的学习理论提出基于局部加权均值的领域适应学习框架(Local weighted mean based domain adaptation learning framework, LDAF), 在LDAF框架下, 衍生出两种领域适应学习方法: LDAF_MLC和 LDAF_SVM.最后,通过测试人工数据集、高维文本数据集和人脸数据集来表明LDAF比其他领域适应学习方法更具优势.     

一种基于区间优化的神经网络学习算法

神经网络的学习算法通常是采用梯度下降法,此方法容易陷入局部极小而得到次最优解。另外,对于有些应用来说,用于训练网络的样本的输入／输出数据无法精确给出,而只能以一定的范围的形式给出,这就给传统的神经网络带来了困难。该文提出了一种基于区间优化的神经网络学习算法,可以很好地解决上面所提到的传统神经网络学习算法的缺点。     

遗传BP网络在机载雷达故障诊断中的应用研究

对遗传算法优化的BP神经网络在某型机载雷达发射机中故障诊断应用进行了研究,目的是应用遗传算法的全局最优性解决BP神经网络容易陷入局部极小的问题,从而提高BP神经网络的学习速度和精度.通过MATLAB仿真,GA-BP神经网络在发射机故障诊断中网络训练收敛速度和误差精度都明显优于BP网络,进一步验证了遗传BP神经网络学习速度快、预测精度高、泛化效果好,很适合应用于雷达等电子设备的故障诊断.     

基于反传混沌粒子群训练的前馈神经网络研究

为了解决前馈神经网络训练收敛速度慢、易陷入局部极值及对初始权值依赖性强等缺点, 提出了一种基于反传的无限折叠迭代混沌粒子群优化(ICMICPSO)算法训练前馈神经网络(FNNs)参数。该方法在充分利用BP算法的误差反传信息和梯度信息的基础上, 引入了ICMIC混沌粒子群的概念, 将ICMIC粒子群(ICMICPS)作为全局搜索器, 梯度下降信息作为局部搜索器来调整网络的权值和阈值, 使得粒子能够在全局寻优的基础上对整个空间进行搜索。通过仿真实验与多种算法进行对比, 结果表明在训练和泛化能力上ICMICPSO-BPNN方法明显优于其他算法。     

基于混合全局池化的回环检测算法

基于深度学习的回环检测算法已被验证性能优于传统方法。然而深度学习计算量大,在移动机器人上往往难以部署大型卷积神经网络,而小型卷积神经网络在大型场景中表现欠佳。对此,本文提出一种将大型卷积神经网络部署在移动机器人上的方案。首先,利用混合全局池化层将特征图转换为特征向量,实验表明该方法与其他更复杂方法性能相当,计算更简单。然后提出一种基于块浮点数的卷积神经网络加速引擎,可显著地降低运算能耗,在不需要重新训练的情况下,几乎没有导致性能损失。