Disentanglement of constituent factors of a sensory signal is central to perception and cognition and hence is a critical task for future artificial intelligence systems. In this paper, we present a compute engine capable of efficiently factorizing holographic perceptual representations by exploiting the computation-in-superposition capability of brain-inspired hyperdimensional computing and the intrinsic stochasticity associated with analog in-memory computing based on nanoscale memristive devices. Such an iterative in-memory factorizer is shown to solve at least five orders of magnitude larger problems that cannot be solved otherwise, while also significantly lowering the computational time and space complexity. We present a large-scale experimental demonstration of the factorizer by employing two in-memory compute chips based on phase-change memristive devices. The dominant matrix-vector multiply operations are executed at O(1) thus reducing the computational time complexity to merely the number of iterations. Moreover, we experimentally demonstrate the ability to factorize visual perceptual representations reliably and efficiently.

现代高性能计算（HPC）系统的复杂性日益增加，需要引入自动化和数据驱动的方法，以支持系统管理员为增加系统可用性的努力。异常检测是改善可用性不可或缺的一部分，因为它减轻了系统管理员的负担，并减少了异常和解决方案之间的时间。但是，对当前的最新检测方法进行了监督和半监督，因此它们需要具有异常的人体标签数据集 - 在生产HPC系统中收集通常是不切实际的。基于聚类的无监督异常检测方法，旨在减轻准确的异常数据的需求，到目前为止的性能差。在这项工作中，我们通过提出RUAD来克服这些局限性，RUAD是一种新型的无监督异常检测模型。 Ruad比当前的半监督和无监督的SOA方法取得了更好的结果。这是通过考虑数据中的时间依赖性以及在模型体系结构中包括长短期限内存单元的实现。提出的方法是根据tier-0系统（带有980个节点的Cineca的Marconi100的完整历史）评估的。 RUAD在半监督训练中达到曲线（AUC）下的区域（AUC）为0.763，在无监督的训练中达到了0.767的AUC，这改进了SOA方法，在半监督训练中达到0.747的AUC，无需训练的AUC和0.734的AUC在无处不在的AUC中提高了AUC。训练。它还大大优于基于聚类的当前SOA无监督的异常检测方法，其AUC为0.548。

纳米大小的无人机具有探索未知和复杂环境的巨大潜力。它们的尺寸很小，使它们敏捷且安全地靠近人类，并使他们能够穿过狭窄的空间。但是，它们的尺寸很小和有效载荷限制了板载计算和传感的可能性，从而使完全自主的飞行极具挑战性。迈向完全自主权的第一步是可靠的避免障碍，这在通用的室内环境中被证明在技术上具有挑战性。当前的方法利用基于视觉或一维传感器来支持纳米无人机感知算法。这项工作为基于新颖的毫米尺寸64像素多区域飞行时间（TOF）传感器和通用的无模型控制策略提供了轻巧的避免障碍系统。报告的现场测试基于Crazyflie 2.1，该测试由定制的多区TOF甲板扩展，总质量为35克。该算法仅使用0.3％的车载处理能力（210US执行时间），帧速率为15fps，为许多未来应用提供了绝佳的基础。运行提出的感知系统（包括抬起和操作传感器）所需的总无人机功率不到10％。在通用且以前未开发的室内环境中，提出的自动纳米大小无人机以0.5m/s的速度达到100％可靠性。所提出的系统释放出具有广泛数据集的开源，包括TOF和灰度摄像头数据，并与运动捕获中的无人机位置地面真相结合在一起。

从几个培训示例中不断学习新课程，而不忘记以前的旧课程需要一个灵活的体系结构，而不可避免地会增加部分存储，其中可以逐步存储并有效地检索新的示例和类。一个可行的架构解决方案是将固定的深神经网络紧密融合到动态发展的明确记忆（EM）。作为该体系结构的核心，我们提出了一个EM单元，该单元在持续学习操作过程中利用节能中的内存计算（IMC）核心。我们首次证明了EM单元如何使用基于IMC Core上的操作（PCM）上的IMC核心操作，在推理期间进行了多个训练示例，扩展以适应看不见的类并进行相似性搜索。具体而言，通过PCM设备的原位进行性结晶实现了一些编码训练示例的物理叠加。与不断学习的最新完整精确基线软件模型相比，IMC核心上达到的分类精度在1.28％ - 2.5％范围内保持在2.5％之内。在60个旧课程的顶部，新颖的课程（每班只有五个示例）。

量化广泛用于云和边缘系统，以减少深层神经网络的记忆占用，潜伏期和能耗。特别是，混合精液量化，即，在网络的不同部分中使用不同的位宽度，已被证明可以提供出色的效率提高，尤其是通过自动化神经体系结构确定的优化的位宽度分配，尤其是通过自动化的位宽度分配（NAS）工具。最先进的混合精液在层面上，即，它对每个网络层的权重和激活张量使用不同的位宽度。在这项工作中，我们扩大了搜索空间，提出了一种新颖的NA，该NAS独立选择每个重量张量通道的位宽度。这为工具提供了额外的灵活性，即仅针对与最有用的功能相关的权重分配更高的精度。在MLPERF微小的基准套件上进行测试，我们获得了精确度大小与精度与能量空间的帕累托最佳模型的丰富集合。当部署在MPIC RISC-V边缘处理器上时，我们的网络将记忆和能量分别减少了63％和27％，而与层的方法相比，以相同的精度为单位。

关键字斑点（kWs）是一个重要的功能，使我们的周围环境中许多无处不在的智能设备进行交互，可以通过唤醒词或直接作为人机界面激活它们。对于许多应用程序，KWS是我们与设备交互的进入点，因此，始终是ON工作负载。许多智能设备都是移动的，并且它们的电池寿命受到持续运行的服务受到严重影响。因此，KWS和类似的始终如一的服务是在优化整体功耗时重点。这项工作解决了低成本微控制器单元（MCU）的KWS节能。我们将模拟二元特征提取与二元神经网络相结合。通过用拟议的模拟前端取代数字预处理，我们表明数据采集和预处理所需的能量可以减少29倍，将其份额从主导的85％的份额削减到仅为我们的整体能源消耗的16％参考KWS应用程序。语音命令数据集的实验评估显示，所提出的系统分别优于最先进的准确性和能效，在10级数据集中分别在10级数据集上达到1％和4.3倍，同时提供令人信服的精度 - 能源折衷包括71倍能量减少2％的精度下降。

在小型电池约束的物流设备上部署现代TinyML任务需要高计算能效。使用非易失性存储器（NVM）的模拟内存计算（IMC）承诺在深神经网络（DNN）推理中的主要效率提高，并用作DNN权重的片上存储器存储器。然而，在系统级别尚未完全理解IMC的功能灵活性限制及其对性能，能量和面积效率的影响。为了目标实际的端到端的IOT应用程序，IMC阵列必须括在异构可编程系统中，引入我们旨在解决这项工作的新系统级挑战。我们介绍了一个非均相紧密的聚类架构，整合了8个RISC-V核心，内存计算加速器（IMA）和数字加速器。我们在高度异构的工作负载上基准测试，例如来自MobileNetv2的瓶颈层，显示出11.5倍的性能和9.5倍的能效改进，而在核心上高度优化并行执行相比。此外，我们通过将我们的异构架构缩放到多阵列加速器，探讨了在IMC阵列资源方面对全移动级DNN（MobileNetv2）的端到端推断的要求。我们的结果表明，我们的解决方案在MobileNetv2的端到端推断上，在执行延迟方面比现有的可编程架构更好，比最先进的异构解决方案更好的数量级集成内存计算模拟核心。

Graph Neural Networks (GNNs) achieve state-of-the-art performance on graph-structured data across numerous domains. Their underlying ability to represent nodes as summaries of their vicinities has proven effective for homophilous graphs in particular, in which same-type nodes tend to connect. On heterophilous graphs, in which different-type nodes are likely connected, GNNs perform less consistently, as neighborhood information might be less representative or even misleading. On the other hand, GNN performance is not inferior on all heterophilous graphs, and there is a lack of understanding of what other graph properties affect GNN performance. In this work, we highlight the limitations of the widely used homophily ratio and the recent Cross-Class Neighborhood Similarity (CCNS) metric in estimating GNN performance. To overcome these limitations, we introduce 2-hop Neighbor Class Similarity (2NCS), a new quantitative graph structural property that correlates with GNN performance more strongly and consistently than alternative metrics. 2NCS considers two-hop neighborhoods as a theoretically derived consequence of the two-step label propagation process governing GCN's training-inference process. Experiments on one synthetic and eight real-world graph datasets confirm consistent improvements over existing metrics in estimating the accuracy of GCN- and GAT-based architectures on the node classification task.

Neuromorphic systems require user-friendly software to support the design and optimization of experiments. In this work, we address this need by presenting our development of a machine learning-based modeling framework for the BrainScaleS-2 neuromorphic system. This work represents an improvement over previous efforts, which either focused on the matrix-multiplication mode of BrainScaleS-2 or lacked full automation. Our framework, called hxtorch.snn, enables the hardware-in-the-loop training of spiking neural networks within PyTorch, including support for auto differentiation in a fully-automated hardware experiment workflow. In addition, hxtorch.snn facilitates seamless transitions between emulating on hardware and simulating in software. We demonstrate the capabilities of hxtorch.snn on a classification task using the Yin-Yang dataset employing a gradient-based approach with surrogate gradients and densely sampled membrane observations from the BrainScaleS-2 hardware system.

Generalisation to unseen contexts remains a challenge for embodied navigation agents. In the context of semantic audio-visual navigation (SAVi) tasks, the notion of generalisation should include both generalising to unseen indoor visual scenes as well as generalising to unheard sounding objects. However, previous SAVi task definitions do not include evaluation conditions on truly novel sounding objects, resorting instead to evaluating agents on unheard sound clips of known objects; meanwhile, previous SAVi methods do not include explicit mechanisms for incorporating domain knowledge about object and region semantics. These weaknesses limit the development and assessment of models' abilities to generalise their learned experience. In this work, we introduce the use of knowledge-driven scene priors in the semantic audio-visual embodied navigation task: we combine semantic information from our novel knowledge graph that encodes object-region relations, spatial knowledge from dual Graph Encoder Networks, and background knowledge from a series of pre-training tasks -- all within a reinforcement learning framework for audio-visual navigation. We also define a new audio-visual navigation sub-task, where agents are evaluated on novel sounding objects, as opposed to unheard clips of known objects. We show improvements over strong baselines in generalisation to unseen regions and novel sounding objects, within the Habitat-Matterport3D simulation environment, under the SoundSpaces task.