基于硬件的加速度是促进许多计算密集型数学操作的广泛尝试。本文提出了一个基于FPGA的体系结构来加速卷积操作 - 在许多卷积神经网络模型中出现的复杂且昂贵的计算步骤。我们将设计定为标准卷积操作,打算以边缘-AI解决方案启动产品。该项目的目的是产生一个可以一次处理卷积层的FPGA IP核心。系统开发人员可以使用Verilog HDL作为体系结构的主要设计语言来部署IP核心。实验结果表明,我们在简单的边缘计算FPGA板上合成的单个计算核心可以提供0.224 GOPS。当董事会充分利用时,可以实现4.48 GOP。
translated by 谷歌翻译
Adversarial machine learning has been both a major concern and a hot topic recently, especially with the ubiquitous use of deep neural networks in the current landscape. Adversarial attacks and defenses are usually likened to a cat-and-mouse game in which defenders and attackers evolve over the time. On one hand, the goal is to develop strong and robust deep networks that are resistant to malicious actors. On the other hand, in order to achieve that, we need to devise even stronger adversarial attacks to challenge these defense models. Most of existing attacks employs a single $\ell_p$ distance (commonly, $p\in\{1,2,\infty\}$) to define the concept of closeness and performs steepest gradient ascent w.r.t. this $p$-norm to update all pixels in an adversarial example in the same way. These $\ell_p$ attacks each has its own pros and cons; and there is no single attack that can successfully break through defense models that are robust against multiple $\ell_p$ norms simultaneously. Motivated by these observations, we come up with a natural approach: combining various $\ell_p$ gradient projections on a pixel level to achieve a joint adversarial perturbation. Specifically, we learn how to perturb each pixel to maximize the attack performance, while maintaining the overall visual imperceptibility of adversarial examples. Finally, through various experiments with standardized benchmarks, we show that our method outperforms most current strong attacks across state-of-the-art defense mechanisms, while retaining its ability to remain clean visually.
translated by 谷歌翻译
The dynamics of a turbulent flow tend to occupy only a portion of the phase space at a statistically stationary regime. From a dynamical systems point of view, this portion is the attractor. The knowledge of the turbulent attractor is useful for two purposes, at least: (i) We can gain physical insight into turbulence (what is the shape and geometry of the attractor?), and (ii) it provides the minimal number of degrees of freedom to accurately describe the turbulent dynamics. Autoencoders enable the computation of an optimal latent space, which is a low-order representation of the dynamics. If properly trained and correctly designed, autoencoders can learn an approximation of the turbulent attractor, as shown by Doan, Racca and Magri (2022). In this paper, we theoretically interpret the transformations of an autoencoder. First, we remark that the latent space is a curved manifold with curvilinear coordinates, which can be analyzed with simple tools from Riemann geometry. Second, we characterize the geometrical properties of the latent space. We mathematically derive the metric tensor, which provides a mathematical description of the manifold. Third, we propose a method -- proper latent decomposition (PLD) -- that generalizes proper orthogonal decomposition of turbulent flows on the autoencoder latent space. This decomposition finds the dominant directions in the curved latent space. This theoretical work opens up computational opportunities for interpreting autoencoders and creating reduced-order models of turbulent flows.
translated by 谷歌翻译
Scene Graph Generation (SGG) serves a comprehensive representation of the images for human understanding as well as visual understanding tasks. Due to the long tail bias problem of the object and predicate labels in the available annotated data, the scene graph generated from current methodologies can be biased toward common, non-informative relationship labels. Relationship can sometimes be non-mutually exclusive, which can be described from multiple perspectives like geometrical relationships or semantic relationships, making it even more challenging to predict the most suitable relationship label. In this work, we proposed the SG-Shuffle pipeline for scene graph generation with 3 components: 1) Parallel Transformer Encoder, which learns to predict object relationships in a more exclusive manner by grouping relationship labels into groups of similar purpose; 2) Shuffle Transformer, which learns to select the final relationship labels from the category-specific feature generated in the previous step; and 3) Weighted CE loss, used to alleviate the training bias caused by the imbalanced dataset.
translated by 谷歌翻译
无线传感器网络由随机分布的传感器节点组成,用于监视目标或感兴趣的区域。由于每个传感器的电池容量有限,因此维持连续监视的网络是一个挑战。无线电源传输技术正在作为可靠的解决方案,用于通过部署移动充电器(MC)为传感器充电传感器。但是,由于网络中出现不确定性,为MC设计最佳的充电路径是具有挑战性的。由于网络拓扑的不可预测的变化,例如节点故障,传感器的能耗率可能会显着波动。这些变化也导致每个传感器的重要性变化,在现有作品中通常被认为是相同的。我们在本文中提出了一种使用深度强化学习(DRL)方法提出新颖的自适应充电方案,以解决这些挑战。具体来说,我们赋予MC采用充电策略,该策略确定了下一个在网络当前状态上充电条件的传感器。然后,我们使用深层神经网络来参数这项收费策略,该策略将通过强化学习技术进行培训。我们的模型可以适应网络拓扑的自发变化。经验结果表明,所提出的算法的表现优于现有的按需算法的大幅度边缘。
translated by 谷歌翻译
自Bert(Devlin等,2018)以来,学习上下文化的单词嵌入一直是NLP中的事实上的标准。然而,学习上下文化短语嵌入的进展受到缺乏人类通知的语句基准基准的阻碍。为了填补这一空白,我们提出了PIC- 〜28K名词短语的数据集伴随着它们的上下文Wikipedia页面,以及一套三个任务,这些任务增加了评估短语嵌入质量的难度。我们发现,在我们的数据集中进行的培训提高了排名模型的准确性,并明显地将问题答案(QA)模型推向了近人类的准确性,而在语义搜索上,鉴于询问短语和段落,在语义搜索上是95%的精确匹配(EM)。有趣的是,我们发现这种令人印象深刻的性能的证据是因为质量检查模型学会了更好地捕获短语的共同含义,而不管其实际背景如何。也就是说,在我们的短语中歧义歧义(PSD)任务上,SOTA模型的精度大大下降(60%EM),在两个不同情况下未能区分相同短语的两种不同感觉。在我们的3任任务基准测试中的进一步结果表明,学习上下文化的短语嵌入仍然是一个有趣的开放挑战。
translated by 谷歌翻译
本文旨在解决多个对象跟踪(MOT),这是计算机视觉中的一个重要问题,但由于许多实际问题,尤其是阻塞,因此仍然具有挑战性。确实,我们提出了一种新的实时深度透视图 - 了解多个对象跟踪(DP-MOT)方法,以解决MOT中的闭塞问题。首先提出了一个简单但有效的主题深度估计(SODE),以在2D场景中自动以无监督的方式自动订购检测到的受试者的深度位置。使用SODE的输出,提出了一个新的活动伪3D KALMAN滤波器,即具有动态控制变量的Kalman滤波器的简单但有效的扩展,以动态更新对象的运动。此外,在数据关联步骤中提出了一种新的高阶关联方法,以合并检测到的对象之间的一阶和二阶关系。与标准MOT基准的最新MOT方法相比,提出的方法始终达到最先进的性能。
translated by 谷歌翻译
算法追索权旨在推荐提供丰富的反馈,以推翻不利的机器学习决策。我们在本文中介绍了贝叶斯追索权,这是一种模型不足的追索权,可最大程度地减少后验概率比值比。此外,我们介绍了其最小的稳健对应物,目的是对抗机器学习模型参数的未来变化。强大的对应物明确考虑了使用最佳传输(Wasserstein)距离规定的高斯混合物中数据的扰动。我们表明,可以将最终的最差目标函数分解为求解一系列二维优化子问题,因此,最小值追索问题发现问题可用于梯度下降算法。与现有的生成健壮的回流的方法相反,可靠的贝叶斯追索不需要线性近似步骤。数值实验证明了我们提出的稳健贝叶斯追索权面临模型转移的有效性。我们的代码可在https://github.com/vinairesearch/robust-bayesian-recourse上找到。
translated by 谷歌翻译
域适应(DA)从严格的理论作品中获益,研究其富有识别特征和各个方面,例如学习领域 - 不变的表示及其权衡。然而,由于多个源域的参与和训练期间目标域的潜在不可用的域,因此似乎不是这种源DA和域泛化(DG)设置的情况非常复杂和复杂。在本文中,我们为目标一般损失开发了新的上限,吸引我们来定义两种域名不变的表示。我们进一步研究了利弊以及执行学习每个领域不变的表示的权衡。最后,我们进行实验检查这些陈述的权衡,以便在实践中提供有关如何使用它们的实践提示,并探索我们发达理论的其他有趣性质。
translated by 谷歌翻译
本文解决了一个称为“条件流形学习”的问题,该问题旨在学习高维数据的低维歧管嵌入高维数据,在辅助歧管信息上调节。该辅助歧管信息来自可控或可测量的条件,这些条件是许多科学和工程应用中的普遍存在。提出了一类关于该问题的广泛解决方案,提出了条件多维缩放(包括条件ISOMAP变体)。介绍了SMACOF算法的条件版本,以优化条件多维缩放的目标函数。
translated by 谷歌翻译