由于Pandemics和远程工作环境的优势,远程审查和求职面试获得了普及,并变得不可或缺。大多数公司和学术机构利用这些系统为他们的招聘流程以及在线考试。然而,远程检查系统的一个关键问题是在可靠的环境中进行考试。在这项工作中,我们展示了一个作弊分析管道,用于在线访谈和考试。该系统仅需要候选人的视频,在考试期间记录。然后采用作弊检测管道来检测另一个人,电子设备使用和候选缺席状态。管道由面部检测,面部识别,对象检测和面部跟踪算法组成。为了评估管道的性能,我们收集了私人视频数据集。视频数据集包括作弊活动和清洁视频。最终,我们的管道提供了一种有效和快速的指导,可以在在线面试和考试视频中检测和分析作弊活动。
translated by 谷歌翻译
Rearrangement puzzles are variations of rearrangement problems in which the elements of a problem are potentially logically linked together. To efficiently solve such puzzles, we develop a motion planning approach based on a new state space that is logically factored, integrating the capabilities of the robot through factors of simultaneously manipulatable joints of an object. Based on this factored state space, we propose less-actions RRT (LA-RRT), a planner which optimizes for a low number of actions to solve a puzzle. At the core of our approach lies a new path defragmentation method, which rearranges and optimizes consecutive edges to minimize action cost. We solve six rearrangement scenarios with a Fetch robot, involving planar table puzzles and an escape room scenario. LA-RRT significantly outperforms the next best asymptotically-optimal planner by 4.01 to 6.58 times improvement in final action cost.
translated by 谷歌翻译
Development of guidance, navigation and control frameworks/algorithms for swarms attracted significant attention in recent years. That being said, algorithms for planning swarm allocations/trajectories for engaging with enemy swarms is largely an understudied problem. Although small-scale scenarios can be addressed with tools from differential game theory, existing approaches fail to scale for large-scale multi-agent pursuit evasion (PE) scenarios. In this work, we propose a reinforcement learning (RL) based framework to decompose to large-scale swarm engagement problems into a number of independent multi-agent pursuit-evasion games. We simulate a variety of multi-agent PE scenarios, where finite time capture is guaranteed under certain conditions. The calculated PE statistics are provided as a reward signal to the high level allocation layer, which uses an RL algorithm to allocate controlled swarm units to eliminate enemy swarm units with maximum efficiency. We verify our approach in large-scale swarm-to-swarm engagement simulations.
translated by 谷歌翻译
Advances in reinforcement learning (RL) often rely on massive compute resources and remain notoriously sample inefficient. In contrast, the human brain is able to efficiently learn effective control strategies using limited resources. This raises the question whether insights from neuroscience can be used to improve current RL methods. Predictive processing is a popular theoretical framework which maintains that the human brain is actively seeking to minimize surprise. We show that recurrent neural networks which predict their own sensory states can be leveraged to minimise surprise, yielding substantial gains in cumulative reward. Specifically, we present the Predictive Processing Proximal Policy Optimization (P4O) agent; an actor-critic reinforcement learning agent that applies predictive processing to a recurrent variant of the PPO algorithm by integrating a world model in its hidden state. P4O significantly outperforms a baseline recurrent variant of the PPO algorithm on multiple Atari games using a single GPU. It also outperforms other state-of-the-art agents given the same wall-clock time and exceeds human gamer performance on multiple games including Seaquest, which is a particularly challenging environment in the Atari domain. Altogether, our work underscores how insights from the field of neuroscience may support the development of more capable and efficient artificial agents.
translated by 谷歌翻译
在本文中,我们提出了一种针对SGD轨迹的新覆盖技术。该定位提供了一种算法特异性的复杂性,该复杂性通过覆盖数来衡量,与标准均匀覆盖的参数相比,该范围独立于维度的基数,从而导致指数尺寸依赖性。基于这种本地化结构,我们表明,如果目标函数是分段的有限扰动,则用$ p $零件强烈凸出和光滑的功能,即非convex和非平滑词,则概括性误差可以由上限。 $ o(\ sqrt {(\ log n \ log(np))/n})$,其中$ n $是数据示例的数量。特别是,此速率与维度无关,并且不需要尽早停止和衰减的步骤。最后,我们在各种环境中采用这些结果,并为多级线性模型,多级支持向量机和$ k $ - 均值聚类用于硬和软标签设置,并改善已知的最先进的范围,从而改善了已知的最先进的, - 阿尔特费率。
translated by 谷歌翻译
我们为频率域的弹性驱动(S(D)EA)建立了必要的条件,同时在速度产生的阻抗控制(VSIC)下呈现无效阻抗和理想弹簧。我们在闭环控制下引入了S(d)EA的被动物理当量,以帮助建立对被动性界限的直观理解,并突出不同植物参数和控制器增益对系统闭环性能的影响。通过被动物理当量,我们严格地比较了不同植物动力学(例如,SEA和SDEA)以及不同级联的控制器架构(例如P-P和P-PI)对系统性能的影响。我们表明,被动物理等效物为有效的阻抗分析建立了一种自然手段。我们提供了理论结果的实验验证,并评估了VSIC下的S(d)EA的触觉渲染性能。
translated by 谷歌翻译
在本文中,我们研究了一个学习问题,其中预报师仅观察部分信息。通过适当地重新缩放问题,我们在瓦斯坦斯坦空间上启发了一个有限的PDE,它表征了预报员的遗憾的渐近行为。使用验证类型参数,我们表明,可以通过找到此抛物线PDE的合适的平滑子/超溶液来解决获得遗憾界限和有效算法的问题。
translated by 谷歌翻译
了解现代机器学习设置中的概括一直是统计学习理论的主要挑战之一。在这种情况下,近年来见证了各种泛化范围的发展,表明了不同的复杂性概念,例如数据样本和算法输出之间的相互信息,假设空间的可压缩性以及假设空间的分形维度。尽管这些界限从不同角度照亮了手头的问题,但它们建议的复杂性概念似乎似乎无关,从而限制了它们的高级影响。在这项研究中,我们通过速率理论的镜头证明了新的概括界定,并明确地将相互信息,可压缩性和分形维度的概念联系起来。我们的方法包括(i)通过使用源编码概念来定义可压缩性的广义概念,(ii)表明“压缩错误率”可以与预期和高概率相关。我们表明,在“无损压缩”设置中,我们恢复并改善了现有的基于信息的界限,而“有损压缩”方案使我们能够将概括与速率延伸维度联系起来,这是分形维度的特定概念。我们的结果为概括带来了更统一的观点,并打开了几个未来的研究方向。
translated by 谷歌翻译
在GAN的潜在空间中发现有意义的方向来操纵语义属性通常需要大量标记的数据。最近的工作旨在通过利用对比语言图像预训练(CLIP),联合文本图像模型来克服这种限制。在有希望的同时,这些方法需要几个小时的预处理或培训来达到所需的操纵。在本文中,我们展示了Stylemc,一种快速有效的文本驱动图像生成和操纵方法。 Stylemc使用基于剪辑的丢失和身份丢失来通过单个文本提示来操纵图像,而不会显着影响其他属性。与现有工作不同,Stylemc只需要几秒钟的每个文本提示培训,以找到稳定的全局方向,不需要提示工程,可以与任何预先训练的样式模型一起使用。我们展示了我们方法的有效性,并将其与最先进的方法进行比较。我们的代码可以在http://catlab-team.github.io/stylemc找到。
translated by 谷歌翻译
最近,在预训练的GANS的潜在空间中发现可解释的方向已成为一个流行的话题。虽然现有的工作主要是考虑语义图像操纵的指示,我们专注于抽象财产:创造力。我们可以操纵图像或更少的创意吗?我们在最大的基于AI的创造力平台,艺术平台上建立工作,其中用户可以使用预先训练的GaN模型生成图像。我们探索在该平台上生成的图像的潜在维度,并提出了一种用于操纵图像的新框架,使其更具创意。我们的代码和数据集可用于http://github.com/catlab-team/latentcreative。
translated by 谷歌翻译