众所周知，深度神经网络（DNNS）通过特别注意某些特定像素来对输入图像进行分类。对每个像素的注意力的图形表示称为显着图。显着图用于检查分类决策基础的有效性，例如，如果DNN对背景而不是图像的主题更加关注，则它不是分类的有效基础。语义扰动可以显着改变显着性图。在这项工作中，我们提出了第一种注意鲁棒性的验证方法，即显着映射对语义扰动的组合的局部稳健性。具体而言，我们的方法确定了扰动参数的范围（例如，亮度变化），该参数维持实际显着性映射变化与预期的显着映射图之间的差异低于给定的阈值。我们的方法基于激活区域遍历，重点是最外面的鲁棒边界，以在较大的DNN上可伸缩。实验结果表明，无论语义扰动如何，我们的方法都可以显示DNN可以与相同基础进行分类的程度，并报告激活区域遍历的性能和性能因素。

复发性神经网络已被证明是高能量物理中许多任务的有效体系结构，因此已被广泛采用。然而，由于在现场可编程门阵列（FPGAS）上实现经常性体系结构的困难，它们在低延迟环境中的使用受到了限制。在本文中，我们介绍了HLS4ML框架内两种类型的复发性神经网络层（长期短期内存和封闭式复发单元）的实现。我们证明，我们的实施能够为小型和大型模型生产有效的设计，并且可以定制以满足推理潜伏期和FPGA资源的特定设计要求。我们显示了多个神经网络的性能和合成设计，其中许多是专门针对CERN大型强子对撞机的喷气识别任务的培训。

Hypergraphs, encoding structured interactions among any number of system units, have recently proven a successful tool to describe many real-world biological and social networks. Here we propose a framework based on statistical inference to characterize the structural organization of hypergraphs. The method allows to infer missing hyperedges of any size in a principled way, and to jointly detect overlapping communities in presence of higher-order interactions. Furthermore, our model has an efficient numerical implementation, and it runs faster than dyadic algorithms on pairwise records projected from higher-order data. We apply our method to a variety of real-world systems, showing strong performance in hyperedge prediction tasks, detecting communities well aligned with the information carried by interactions, and robustness against addition of noisy hyperedges. Our approach illustrates the fundamental advantages of a hypergraph probabilistic model when modeling relational systems with higher-order interactions.

社区检测和层级提取通常被认为是网络上的单独推理任务。考虑到研究真实数据时只有其中一个可以是一种过度简化。在这项工作中，我们提出了一种基于社区和分层结构之间的相互作用的生成模型。它假设每个节点在交互机制中的偏好和具有相同偏好的节点更有可能相互作用，而仍然允许异构交互。算法实现是有效的，因为它利用网络数据集的稀疏性。我们展示了我们对综合和实世界数据的方法，并比较了与社区检测和排名提取的两个标准方法的性能。我们发现该算法在不同场景中准确地检索每个节点的偏好，我们表明它可以区分表现出与大多数不同的节点的小子集。结果，该模型可以识别网络是否具有整体优选的交互机制。这在没有明确的“先验”信息的情况下是相关的，关于结构良好地解释了观察到的网络数据集。我们的模型允许从业者自动从数据中学习。

由于它们的时间加工能力及其低交换（尺寸，重量和功率）以及神经形态硬件中的节能实现，尖峰神经网络（SNNS）已成为传统人工神经网络（ANN）的有趣替代方案。然而，培训SNNS所涉及的挑战在准确性方面有限制了它们的表现，从而限制了他们的应用。因此，改善更准确的特征提取的学习算法和神经架构是SNN研究中的当前优先级之一。在本文中，我们展示了现代尖峰架构的关键组成部分的研究。我们在从最佳执行网络中凭经验比较了图像分类数据集中的不同技术。我们设计了成功的残余网络（Reset）架构的尖峰版本，并测试了不同的组件和培训策略。我们的结果提供了SNN设计的最新版本，它允许在尝试构建最佳视觉特征提取器时进行明智的选择。最后，我们的网络优于CIFAR-10（94.1％）和CIFAR-100（74.5％）数据集的先前SNN架构，并将现有技术与DVS-CIFAR10（71.3％）相匹配，参数较少而不是先前的状态艺术，无需安静转换。代码在https://github.com/vicenteax/spiking_resnet上获得。

尖峰神经网络（SNN）和神经胸工程领域带来了如何接近机器学习（ML）和计算机视觉（CV）问题的范式转变。这种范式转变来自基于事件的传感和处理的适应。基于事件的视觉传感器允许生产与场景动态相关的稀疏和异步事件。不仅允许捕获空间信息但是要捕获的时间信息的高保真度。同时避免常规高帧速率接近的额外开销和冗余。然而，随着该范式的这种变化，来自传统CV和ML的许多技术不适用于基于事件的空间视觉流。作为如此有限数量的识别，存在检测和分割方法。在本文中，我们介绍了一种新的方法，可以使用仅使用训练的尖峰卷积神经网络的峰值时间依赖性可塑性的重量来执行实例分割。这利用网络的内部特征表示的空间和时间方面添加了这种新的辨别能力。我们通过成功转换为面部识别和实例分段网络成功转换单级无监督网络来突出新功能。

学术研究和金融业最近引起了机器学习算法，因为他们的权力解决了复杂的学习任务。然而，在公司的默认预测领域，缺乏可解释性阻止了广泛采用了黑箱类型的模型。为了克服这一缺点并保持黑盒的高性能，本文依赖于模型 - 无症方法。累计的本地效果和福芙值用于塑造预测因子对默认可能性的影响，并根据其对模型结果的贡献进行排名。与三种标准判别模型相比，通过两个机器学习算法（极端梯度升压和前馈神经网络）实现了预测。结果表明，我们对意大利中小企业制造业的分析通过极端梯度提升算法从整体最高分类功率的优势，而不放弃丰富的解释框架。

Reinforcement Learning (RL) is currently one of the most commonly used techniques for traffic signal control (TSC), which can adaptively adjusted traffic signal phase and duration according to real-time traffic data. However, a fully centralized RL approach is beset with difficulties in a multi-network scenario because of exponential growth in state-action space with increasing intersections. Multi-agent reinforcement learning (MARL) can overcome the high-dimension problem by employing the global control of each local RL agent, but it also brings new challenges, such as the failure of convergence caused by the non-stationary Markov Decision Process (MDP). In this paper, we introduce an off-policy nash deep Q-Network (OPNDQN) algorithm, which mitigates the weakness of both fully centralized and MARL approaches. The OPNDQN algorithm solves the problem that traditional algorithms cannot be used in large state-action space traffic models by utilizing a fictitious game approach at each iteration to find the nash equilibrium among neighboring intersections, from which no intersection has incentive to unilaterally deviate. One of main advantages of OPNDQN is to mitigate the non-stationarity of multi-agent Markov process because it considers the mutual influence among neighboring intersections by sharing their actions. On the other hand, for training a large traffic network, the convergence rate of OPNDQN is higher than that of existing MARL approaches because it does not incorporate all state information of each agent. We conduct an extensive experiments by using Simulation of Urban MObility simulator (SUMO), and show the dominant superiority of OPNDQN over several existing MARL approaches in terms of average queue length, episode training reward and average waiting time.

The visual dimension of cities has been a fundamental subject in urban studies, since the pioneering work of scholars such as Sitte, Lynch, Arnheim, and Jacobs. Several decades later, big data and artificial intelligence (AI) are revolutionizing how people move, sense, and interact with cities. This paper reviews the literature on the appearance and function of cities to illustrate how visual information has been used to understand them. A conceptual framework, Urban Visual Intelligence, is introduced to systematically elaborate on how new image data sources and AI techniques are reshaping the way researchers perceive and measure cities, enabling the study of the physical environment and its interactions with socioeconomic environments at various scales. The paper argues that these new approaches enable researchers to revisit the classic urban theories and themes, and potentially help cities create environments that are more in line with human behaviors and aspirations in the digital age.

Representing and synthesizing novel views in real-world dynamic scenes from casual monocular videos is a long-standing problem. Existing solutions typically approach dynamic scenes by applying geometry techniques or utilizing temporal information between several adjacent frames without considering the underlying background distribution in the entire scene or the transmittance over the ray dimension, limiting their performance on static and occlusion areas. Our approach $\textbf{D}$istribution-$\textbf{D}$riven neural radiance fields offers high-quality view synthesis and a 3D solution to $\textbf{D}$etach the background from the entire $\textbf{D}$ynamic scene, which is called $\text{D}^4$NeRF. Specifically, it employs a neural representation to capture the scene distribution in the static background and a 6D-input NeRF to represent dynamic objects, respectively. Each ray sample is given an additional occlusion weight to indicate the transmittance lying in the static and dynamic components. We evaluate $\text{D}^4$NeRF on public dynamic scenes and our urban driving scenes acquired from an autonomous-driving dataset. Extensive experiments demonstrate that our approach outperforms previous methods in rendering texture details and motion areas while also producing a clean static background. Our code will be released at https://github.com/Luciferbobo/D4NeRF.