Multivariate time series forecasting constitutes important functionality in cyber-physical systems, whose prediction accuracy can be improved significantly by capturing temporal and multivariate correlations among multiple time series. State-of-the-art deep learning methods fail to construct models for full time series because model complexity grows exponentially with time series length. Rather, these methods construct local temporal and multivariate correlations within subsequences, but fail to capture correlations among subsequences, which significantly affect their forecasting accuracy. To capture the temporal and multivariate correlations among subsequences, we design a pattern discovery model, that constructs correlations via diverse pattern functions. While the traditional pattern discovery method uses shared and fixed pattern functions that ignore the diversity across time series. We propose a novel pattern discovery method that can automatically capture diverse and complex time series patterns. We also propose a learnable correlation matrix, that enables the model to capture distinct correlations among multiple time series. Extensive experiments show that our model achieves state-of-the-art prediction accuracy.
translated by 谷歌翻译
Deep learning based change detection methods have received wide attentoion, thanks to their strong capability in obtaining rich features from images. However, existing AI-based CD methods largely rely on three functionality-enhancing modules, i.e., semantic enhancement, attention mechanisms, and correspondence enhancement. The stacking of these modules leads to great model complexity. To unify these three modules into a simple pipeline, we introduce Relational Change Detection Transformer (RCDT), a novel and simple framework for remote sensing change detection tasks. The proposed RCDT consists of three major components, a weight-sharing Siamese Backbone to obtain bi-temporal features, a Relational Cross Attention Module (RCAM) that implements offset cross attention to obtain bi-temporal relation-aware features, and a Features Constrain Module (FCM) to achieve the final refined predictions with high-resolution constraints. Extensive experiments on four different publically available datasets suggest that our proposed RCDT exhibits superior change detection performance compared with other competing methods. The therotical, methodogical, and experimental knowledge of this study is expected to benefit future change detection efforts that involve the cross attention mechanism.
translated by 谷歌翻译
在线影响最大化旨在通过选择一些种子节点,最大程度地利用未知网络模型的社交网络中内容的影响。最近的研究遵循非自适应设置,在扩散过程开始之前选择种子节点,并且在扩散停止时更新网络参数。我们考虑了与内容相关的在线影响最大化问题的自适应版本,其中种子节点是根据实时反馈依次激活的。在本文中,我们将问题提出为无限马在线性扩散过程中的折扣MDP,并提出了基于模型的增强学习解决方案。我们的算法维护网络模型估算,并适应种子用户,探索社交网络,同时乐观地改善最佳策略。我们建立了$ \ widetilde o(\ sqrt {t})$遗憾的算法。合成网络的经验评估证明了我们的算法效率。
translated by 谷歌翻译
深度加强学习(RL)由Q函数的神经网络近似,具有巨大的经验成功。虽然RL的理论传统上专注于线性函数近似(或雕刻尺寸)方法,但是关于非线性RL的近似已知Q功能的神经网络近似。这是这项工作的重点,在那里我们研究了与双层神经网络的函数逼近(考虑到Relu和多项式激活功能)。我们的第一个结果是在两层神经网络的完整性下的生成模型设置中的计算上和统计学高效的算法。我们的第二个结果考虑了这个设置,而是通过神经网络函数类的可实现性。这里,假设确定性动态,样本复杂度在代数维度中线性缩放。在所有情况下,我们的结果显着改善了线性(或雕刻尺寸)方法可以获得的。
translated by 谷歌翻译
We present a novel neural surface reconstruction method called NeuralRoom for reconstructing room-sized indoor scenes directly from a set of 2D images. Recently, implicit neural representations have become a promising way to reconstruct surfaces from multiview images due to their high-quality results and simplicity. However, implicit neural representations usually cannot reconstruct indoor scenes well because they suffer severe shape-radiance ambiguity. We assume that the indoor scene consists of texture-rich and flat texture-less regions. In texture-rich regions, the multiview stereo can obtain accurate results. In the flat area, normal estimation networks usually obtain a good normal estimation. Based on the above observations, we reduce the possible spatial variation range of implicit neural surfaces by reliable geometric priors to alleviate shape-radiance ambiguity. Specifically, we use multiview stereo results to limit the NeuralRoom optimization space and then use reliable geometric priors to guide NeuralRoom training. Then the NeuralRoom would produce a neural scene representation that can render an image consistent with the input training images. In addition, we propose a smoothing method called perturbation-residual restrictions to improve the accuracy and completeness of the flat region, which assumes that the sampling points in a local surface should have the same normal and similar distance to the observation center. Experiments on the ScanNet dataset show that our method can reconstruct the texture-less area of indoor scenes while maintaining the accuracy of detail. We also apply NeuralRoom to more advanced multiview reconstruction algorithms and significantly improve their reconstruction quality.
translated by 谷歌翻译
基于深度学习的高光谱图像(HSI)恢复方法因其出色的性能而广受欢迎,但每当任务更改的细节时,通常都需要昂贵的网络再培训。在本文中,我们建议使用有效的插入方法以统一的方法恢复HSI,该方法可以共同保留基于优化方法的灵活性,并利用深神经网络的强大表示能力。具体而言,我们首先开发了一个新的深HSI DeNoiser,利用了门控复发单元,短期和长期的跳过连接以及增强的噪声水平图,以更好地利用HSIS内丰富的空间光谱信息。因此,这导致在高斯和复杂的噪声设置下,在HSI DeNosing上的最新性能。然后,在处理各种HSI恢复任务之前,将提议的DeNoiser插入即插即用的框架中。通过对HSI超分辨率,压缩感测和内部进行的广泛实验,我们证明了我们的方法经常实现卓越的性能,这与每个任务上的最先进的竞争性或甚至更好任何特定任务的培训。
translated by 谷歌翻译
目的:卷积神经网络(CNN)在脑部计算机界面(BCI)领域表现出巨大的潜力,因为它们能够直接处理无人工特征提取而直接处理原始脑电图(EEG)。原始脑电图通常表示为二维(2-D)矩阵,由通道和时间点组成,忽略了脑电图的空间拓扑信息。我们的目标是使带有原始脑电图信号的CNN作为输入具有学习EEG空间拓扑特征的能力,并改善其分类性能,同时实质上保持其原始结构。方法:我们提出了一个EEG地形表示模块(TRM)。该模块由(1)从原始脑电图信号到3-D地形图的映射块和(2)从地形图到与输入相同大小的输出的卷积块组成。我们将TRM嵌入了3个广泛使用的CNN中,并在2种不同类型的公开数据集中测试了它们。结果:结果表明,使用TRM后,两个数据集都在两个数据集上提高了3个CNN的分类精度。在模拟驾驶数据集(EBDSDD)和2.83 \%,2.17 \%和2.17 \%\%和2.17 \%和2.00 \%的紧急制动器上,具有TRM的DeepConvnet,Eegnet和ShandowConvnet的平均分类精度提高了4.70 \%,1.29 \%和0.91 \%高γ数据集(HGD)。意义:通过使用TRM来挖掘脑电图的空间拓扑特征,我们在2个数据集上提高了3个CNN的分类性能。另外,由于TRM的输出的大小与输入相同,因此任何具有RAW EEG信号的CNN作为输入可以使用此模块而无需更改原始结构。
translated by 谷歌翻译
深度学习技术在各种任务中都表现出了出色的有效性,并且深度学习具有推进多种应用程序(包括在边缘计算中)的潜力,其中将深层模型部署在边缘设备上,以实现即时的数据处理和响应。一个关键的挑战是,虽然深层模型的应用通常会产生大量的内存和计算成本,但Edge设备通常只提供非常有限的存储和计算功能,这些功能可能会在各个设备之间差异很大。这些特征使得难以构建深度学习解决方案,以释放边缘设备的潜力,同时遵守其约束。应对这一挑战的一种有希望的方法是自动化有效的深度学习模型的设计,这些模型轻巧,仅需少量存储,并且仅产生低计算开销。该调查提供了针对边缘计算的深度学习模型设计自动化技术的全面覆盖。它提供了关键指标的概述和比较,这些指标通常用于量化模型在有效性,轻度和计算成本方面的水平。然后,该调查涵盖了深层设计自动化技术的三类最新技术:自动化神经体系结构搜索,自动化模型压缩以及联合自动化设计和压缩。最后,调查涵盖了未来研究的开放问题和方向。
translated by 谷歌翻译
遥感图像的更改检测(CD)是通过分析两个次时图像之间的差异来检测变化区域。它广泛用于土地资源规划,自然危害监测和其他领域。在我们的研究中,我们提出了一个新型的暹罗神经网络,用于变化检测任务,即双UNET。与以前的单独编码BITEMAL图像相反,我们设计了一个编码器差分注意模块,以关注像素的空间差异关系。为了改善网络的概括,它计算了咬合图像之间的任何像素之间的注意力权重,并使用它们来引起更具区别的特征。为了改善特征融合并避免梯度消失,在解码阶段提出了多尺度加权方差图融合策略。实验表明,所提出的方法始终优于流行的季节性变化检测数据集最先进的方法。
translated by 谷歌翻译
及时调整尝试更新预训练模型中的一些特定任务参数。它的性能与在语言理解和发电任务上的完整参数设置的微调相当。在这项工作中,我们研究了迅速调整神经文本检索器的问题。我们引入参数效率的及时调整,以调整跨内域,跨域和跨主题设置的文本检索。通过广泛的分析,我们表明该策略可以通过基于微调的检索方法来减轻两个问题 - 参数 - 信息和弱推广性。值得注意的是,它可以显着改善检索模型的零零弹性概括。通过仅更新模型参数的0.1%,及时调整策略可以帮助检索模型获得比所有参数更新的传统方法更好的概括性能。最后,为了促进回猎犬的跨主题概括性的研究,我们策划并发布了一个学术检索数据集,其中包含18K查询的87个主题,使其成为迄今为止特定于特定于主题的主题。
translated by 谷歌翻译