In the Priority $k$-Center problem, the input consists of a metric space $(X,d)$, an integer $k$, and for each point $v \in X$ a priority radius $r(v)$. The goal is to choose $k$-centers $S \subseteq X$ to minimize $\max_{v \in X} \frac{1}{r(v)} d(v,S)$. If all $r(v)$'s are uniform, one obtains the $k$-Center problem. Plesn\'ik [Plesn\'ik, Disc. Appl. Math. 1987] introduced the Priority $k$-Center problem and gave a $2$-approximation algorithm matching the best possible algorithm for $k$-Center. We show how the problem is related to two different notions of fair clustering [Harris et al., NeurIPS 2018; Jung et al., FORC 2020]. Motivated by these developments we revisit the problem and, in our main technical contribution, develop a framework that yields constant factor approximation algorithms for Priority $k$-Center with outliers. Our framework extends to generalizations of Priority $k$-Center to matroid and knapsack constraints, and as a corollary, also yields algorithms with fairness guarantees in the lottery model of Harris et al [Harris et al, JMLR 2019].
translated by 谷歌翻译
The increasing number of surveillance cameras and security concerns have made automatic violent activity detection from surveillance footage an active area for research. Modern deep learning methods have achieved good accuracy in violence detection and proved to be successful because of their applicability in intelligent surveillance systems. However, the models are computationally expensive and large in size because of their inefficient methods for feature extraction. This work presents a novel architecture for violence detection called Two-stream Multi-dimensional Convolutional Network (2s-MDCN), which uses RGB frames and optical flow to detect violence. Our proposed method extracts temporal and spatial information independently by 1D, 2D, and 3D convolutions. Despite combining multi-dimensional convolutional networks, our models are lightweight and efficient due to reduced channel capacity, yet they learn to extract meaningful spatial and temporal information. Additionally, combining RGB frames and optical flow yields 2.2% more accuracy than a single RGB stream. Regardless of having less complexity, our models obtained state-of-the-art accuracy of 89.7% on the largest violence detection benchmark dataset.
translated by 谷歌翻译
综合光子神经网络(IPNN)成为常规电子AI加速器的有前途的后继者,因为它们在计算速度和能源效率方面提供了实质性的提高。特别是,相干IPNN使用Mach-Zehnder干涉仪(MZIS)的阵列进行单位转换来执行节能矩阵矢量乘法。然而,IPNN中的基本MZI设备易受光刻变化和热串扰引起的不确定性,并且由于不均匀的MZI插入损失和量化错误而导致不确定的不确定性,这是由于调谐相角的编码较低而导致的。在本文中,我们首次使用自下而上的方法系统地表征了IPNN中这种不确定性和不确定性(共同称为缺陷)的影响。我们表明,它们对IPNN准确性的影响可能会根据受影响组件的调谐参数(例如相角),其物理位置以及缺陷的性质和分布而差异很大。为了提高可靠性措施,我们确定了关键的IPNN构件,在不完美之下,这些基础可能导致分类准确性的灾难性降解。我们表明,在多个同时缺陷下,即使不完美参数限制在较小的范围内,IPNN推断精度也可能会降低46%。我们的结果还表明,推论精度对影响IPNN输入层旁边的线性层中MZI的缺陷敏感。
translated by 谷歌翻译
基于奇异值分解的相干集成光子神经网络(SC-IPNN)具有大的占地面积,遭受高静态功耗进行训练和推理,并且不能使用传统的DNN修剪技术进行修剪。我们利用彩票假设提出了一种用于SC-IPN的第一种硬件感知修剪方法,通过最小化重量参数的数量来缓解这些挑战。我们修剪基于多层的Perceptron的SC-IPN,并显示高达89%的相位角,其对应于SC-IPNN中的重量参数,可以在减少时具有可忽略的精度损失(小于5%)。静电功耗高达86%。
translated by 谷歌翻译
纵向脑磁共振成像(MRI)含有病理扫描的登记是由于组织外观变化而挑战,仍然是未解决的问题。本文介绍了第一脑肿瘤序列登记(Brats-Reg)挑战,重点是估计诊断患有脑弥漫性胶质瘤的同一患者的术前和后续扫描之间的对应关系。 Brats-Reg挑战打算建立可变形登记算法的公共基准环境。关联的数据集包括根据公共解剖模板,为每个扫描的大小和分辨率策划的DE识别的多机构多参数MRI(MPMRI)数据。临床专家在扫描内产生了广泛的标志标记点,描述了跨时域的不同解剖位置。培训数据以及这些地面真相注释将被释放给参与者来设计和开发他们的注册算法,而组织者将扣留验证和测试数据的注释,并用于评估参与者的集装箱化算法。每个所提交的算法都将使用几个度量来定量评估,例如中位绝对误差(MAE),鲁棒性和雅可比的决定因素。
translated by 谷歌翻译
我们提出了一种用于相干光子神经网络的新型硬件感知幅度修剪技术。该技术可以将99.45%的网络参数进行99.45%,并将静态功耗降低98.23%,精度损失可忽略不计。
translated by 谷歌翻译
传统上,自动语音识别的研究重点是对音频表示的本地首选编码,以预测话语中的语音。不幸的是,依靠此类超本地信息的方法往往容易受到本地级腐败(例如音频框架掉落或大声的噪音)和全球级别的噪音(例如环境噪音或背景噪音)在训练期间看到。在这项工作中,我们介绍了一种新颖的方法,该方法利用了基于掩盖语言建模的自我监督的学习技术来计算对话语发生的环境的全球多模式编码。然后,我们使用一个新的深融合框架将这种全局上下文集成到传统的ASR方法中,并证明所得的方法可以在LibrisPeech上胜过高达7%的基线方法;内部数据集的收益范围从6%(较大型号)到45%(在较小的型号上)。
translated by 谷歌翻译