We consider the problem of reconstructing the signal and the hidden variables from observations coming from a multi-layer network with rotationally invariant weight matrices. The multi-layer structure models inference from deep generative priors, and the rotational invariance imposed on the weights generalizes the i.i.d.\ Gaussian assumption by allowing for a complex correlation structure, which is typical in applications. In this work, we present a new class of approximate message passing (AMP) algorithms and give a state evolution recursion which precisely characterizes their performance in the large system limit. In contrast with the existing multi-layer VAMP (ML-VAMP) approach, our proposed AMP -- dubbed multi-layer rotationally invariant generalized AMP (ML-RI-GAMP) -- provides a natural generalization beyond Gaussian designs, in the sense that it recovers the existing Gaussian AMP as a special case. Furthermore, ML-RI-GAMP exhibits a significantly lower complexity than ML-VAMP, as the computationally intensive singular value decomposition is replaced by an estimation of the moments of the design matrices. Finally, our numerical results show that this complexity gain comes at little to no cost in the performance of the algorithm.
translated by 谷歌翻译
User-generated-content (UGC) videos have dominated the Internet during recent years. While many methods attempt to objectively assess the quality of these UGC videos, the mechanisms of human quality perception in the UGC-VQA problem is still yet to be explored. To better explain the quality perception mechanisms and learn more robust representations, we aim to disentangle the effects of aesthetic quality issues and technical quality issues risen by the complicated video generation processes in the UGC-VQA problem. To overcome the absence of respective supervisions during disentanglement, we propose the Limited View Biased Supervisions (LVBS) scheme where two separate evaluators are trained with decomposed views specifically designed for each issue. Composed of an Aesthetic Quality Evaluator (AQE) and a Technical Quality Evaluator (TQE) under the LVBS scheme, the proposed Disentangled Objective Video Quality Evaluator (DOVER) reach excellent performance (0.91 SRCC for KoNViD-1k, 0.89 SRCC for LSVQ, 0.88 SRCC for YouTube-UGC) in the UGC-VQA problem. More importantly, our blind subjective studies prove that the separate evaluators in DOVER can effectively match human perception on respective disentangled quality issues. Codes and demos are released in https://github.com/teowu/dover.
translated by 谷歌翻译
The high emission and low energy efficiency caused by internal combustion engines (ICE) have become unacceptable under environmental regulations and the energy crisis. As a promising alternative solution, multi-power source electric vehicles (MPS-EVs) introduce different clean energy systems to improve powertrain efficiency. The energy management strategy (EMS) is a critical technology for MPS-EVs to maximize efficiency, fuel economy, and range. Reinforcement learning (RL) has become an effective methodology for the development of EMS. RL has received continuous attention and research, but there is still a lack of systematic analysis of the design elements of RL-based EMS. To this end, this paper presents an in-depth analysis of the current research on RL-based EMS (RL-EMS) and summarizes the design elements of RL-based EMS. This paper first summarizes the previous applications of RL in EMS from five aspects: algorithm, perception scheme, decision scheme, reward function, and innovative training method. The contribution of advanced algorithms to the training effect is shown, the perception and control schemes in the literature are analyzed in detail, different reward function settings are classified, and innovative training methods with their roles are elaborated. Finally, by comparing the development routes of RL and RL-EMS, this paper identifies the gap between advanced RL solutions and existing RL-EMS. Finally, this paper suggests potential development directions for implementing advanced artificial intelligence (AI) solutions in EMS.
translated by 谷歌翻译
多源机电耦合使燃料电池电动汽车(FCEV)的能源管理相对非线性和复杂,尤其是在4轮驱动(4WD)FCEV的类型中。复杂的非线性系统的准确观察状态是FCEV中出色的能源管理的基础。为了释放FCEV的节能潜力,为4WD FCEV提出了一种基于学习的新型鲁棒模型预测控制(LRMPC)策略,从而有助于多个能源之间的合适功率分布。基于机器学习(ML)的精心设计的策略将非线性系统的知识转化为具有出色稳健性能的显式控制方案。首先,具有高回归准确性和出色概括能力的ML方法是离线训练的,以建立SOC的精确状态观察者。然后,使用国家观察者生成的SOC的显式数据表用于抓住准确的状态更改,其输入功能包括车辆状态和车辆组件状态。具体来说,提供未来速度参考的车辆速度估计是由深森林构建的。接下来,将包括显式数据表和车辆速度估计的组件与模型预测控制(MPC)结合使用,以释放FCEV中多释放系统的最新能源节能能力,其名称是LRMPC。最后,在模拟测试中进行详细评估以验证LRMPC的进步性能。相应的结果突出了LRMPC的最佳控制效应和强大的实时应用能力。
translated by 谷歌翻译
准确的交通状况预测为车辆环境协调和交通管制任务提供了坚实的基础。由于道路网络数据在空间分布中的复杂性以及深度学习方法的多样性,有效定义流量数据并充分捕获数据中复杂的空间非线性特征变得具有挑战性。本文将两种分层图池方法应用于流量预测任务,以减少图形信息冗余。首先,本文验证了流量预测任务中层次图池方法的有效性。分层图合并方法与其他基线在预测性能上形成鲜明对比。其次,应用了两种主流分层图池方法,节点群集池和节点下降池,用于分析流量预测中的优势和弱点。最后,对于上述图神经网络,本文比较了不同图网络输入对流量预测准确性的预测效应。分析和汇总定义图网络的有效方法。
translated by 谷歌翻译
近年来,在运输电气化方面取得了重大进展。作为主要的储能设备,锂离子电池(LIB)已受到广泛关注。准确地预测健康状况(SOH)不仅可以缓解用户对电池寿命的焦虑,而且还可以为电池管理提供重要信息。本文提出了一种基于视觉变压器(VIT)模型的SOH的预测方法。首先,预定义电压范围的离散充电数据用作输入数据矩阵。然后,电池的循环特征是由VIT捕获的,可以获得可以获得全局特征,并且通过将循环特征与完整连接(FC)层相结合来获得SOH。同时,引入了转移学习(TL),并根据目标任务电池的早期周期数据进一步微调基于源任务电池训练的预测模型,以提供准确的预测。实验表明,与现有的深度学习方法相比,我们的方法可以获得更好的特征表达,从而可以实现更好的预测效果和传递效果。
translated by 谷歌翻译
颜色和结构是结合形象的两个支柱。对神经网络识别的关键结构感兴趣,我们通过将颜色空间限制为几个位来隔离颜色的影响,并找到能够在此类约束下实现网络识别的结构。为此,我们提出了一个颜色量化网络Colorcnn,该网络通过最大程度地减少分类损失来学习在有限的颜色空间中构建图像。在Colorcnn的体系结构和见解的基础上,我们介绍了ColorCnn+,该+支持多种颜色空间大小的配置,并解决了以前的识别精度差的不良问题和在大型颜色空间下的不良视觉保真度。通过一种新颖的模仿学习方法,Colorcnn+学会了群集颜色,例如传统的颜色量化方法。这减少了过度拟合,并有助于在大颜色空间下的视觉保真度和识别精度。实验验证ColorCNN+在大多数情况下取得了非常有竞争力的结果,可以保留具有准确颜色的网络识别和视觉保真度的关键结构。我们进一步讨论关键结构和准确颜色之间的差异及其对网络识别的具体贡献。对于潜在应用,我们表明ColorCNN可以用作网络识别的图像压缩方法。
translated by 谷歌翻译
半监督的语义细分需要对未标记的数据进行丰富而强大的监督。一致性学习强制执行相同的像素在不同的增强视图中具有相似的特征,这是一个强大的信号,但忽略了与其他像素的关系。相比之下,对比学习考虑了丰富的成对关系,但是为像素对分配二进制阳性阴性监督信号可能是一个难题。在本文中,我们竭尽所能,并提出多视图相关性一致性(MVCC)学习:它考虑了自相关矩阵中的丰富成对关系,并将它们匹配到视图中以提供强大的监督。加上这种相关性一致性损失,我们提出了一个视图增强策略,可以保证不同观点之间的像素像素对应关系。在两个数据集上的一系列半监督设置中,我们报告了与最先进方法相比的竞争精度。值得注意的是,在CityScapes上,我们以1/8标记的数据达到76.8%的MIOU,比完全监督的Oracle差0.6%。
translated by 谷歌翻译
节点注入对图神经网络(GNN)的攻击已作为一种实际的攻击场景而引起了人们的注意,攻击者会注入恶意节点,而不是修改节点功能或边缘以降低GNN的性能。尽管节点注射攻击最初取得了成功,但我们发现,通过防御方法,可以通过防御方法和限制其在实践中限制其攻击性能,从而很容易将注射的节点与原始正常节点区分开。为了解决上述问题,我们致力于伪装节点注入攻击,即伪装注入恶意节点(结构/属性)是对防御方法似乎合理/不察觉的普通淋巴结。图形数据的非欧亚人性质和缺乏人类的先验性质给伪装上伪装的形式化,实施和评估带来了巨大挑战。在本文中,我们首先提出并制定了从注射节点围绕的自我网络的忠诚度和多样性中注入的节点的伪装。然后,我们为节点注射攻击(即Cana)设计了一个对抗性伪装框架,以改善伪装,同时确保攻击性能。进一步设计了几种用于图形伪装的新型指标,以进行全面的评估。实验结果表明,当将现有的节点注入攻击方法与我们提出的CANA框架配置时,针对防御方法的攻击性能以及节点伪装将显着改善。
translated by 谷歌翻译
流量预测在智能运输系统中交通控制和调度任务的实现中起着重要作用。随着数据源的多元化,合理地使用丰富的流量数据来对流量流中复杂的时空依赖性和非线性特征进行建模是智能运输系统的关键挑战。此外,清楚地评估从不同数据中提取的时空特征的重要性成为一个挑战。提出了双层 - 空间时间特征提取和评估(DL -STFEE)模型。 DL-STFEE的下层是时空特征提取层。流量数据中的空间和时间特征是通过多画图卷积和注意机制提取的,并生成了空间和时间特征的不同组合。 DL-STFEE的上层是时空特征评估层。通过高维自我注意力发项机制产生的注意力评分矩阵,空间特征组合被融合和评估,以便获得不同组合对预测效应的影响。在实际的流量数据集上进行了三组实验,以表明DL-STFEE可以有效地捕获时空特征并评估不同时空特征组合的重要性。
translated by 谷歌翻译