内核放牧算法用于在复制的内核希尔伯特空间（RKHS）中构建正交规则。虽然该方法的算法的计算效率和输出正交公式的稳定性是该方法的优点，但与其他正交方法相比，给定数量的节点的集成误差的收敛速度很慢。在本文中，我们提出了一种经过修改的内核放牧算法，该算法在先前的研究中引入了框架，并旨在获得更稀疏的解决方案，同时保留标准仁放牧的优势。在提出的算法中，负梯度通过几个顶点方向近似，并且通过在每次迭代中的近似下降方向移动来更新当前的解决方案。我们表明，集成误差的收敛速度是由负梯度和近似梯度之间角度的余弦决定的。基于此，我们提出了新的梯度近似算法并理论上分析它们，包括通过收敛分析。在数值实验中，我们从节点的稀疏性和计算效率方面证实了所提出的算法的有效性。此外，我们提供了具有完全校对权重的内核正交规则的新理论分析，该规则比以前的研究更快地实现了收敛速度。

Text-to-text generation models have increasingly become the go-to solution for a wide variety of sequence labeling tasks (e.g., entity extraction and dialog slot filling). While most research has focused on the labeling accuracy, a key aspect -- of vital practical importance -- has slipped through the cracks: understanding model confidence. More specifically, we lack a principled understanding of how to reliably gauge the confidence of a model in its predictions for each labeled span. This paper aims to provide some empirical insights on estimating model confidence for generative sequence labeling. Most notably, we find that simply using the decoder's output probabilities is not the best in realizing well-calibrated confidence estimates. As verified over six public datasets of different tasks, we show that our proposed approach -- which leverages statistics from top-$k$ predictions by a beam search -- significantly reduces calibration errors of the predictions of a generative sequence labeling model.

This study proposed a novel robotic gripper that can achieve grasping and infinite wrist twisting motions using a single actuator. The gripper is equipped with a differential gear mechanism that allows switching between the grasping and twisting motions according to the magnitude of the tip force applied to the finger. The grasping motion is activated when the tip force is below a set value, and the wrist twisting motion is activated when the tip force exceeds this value. "Twist grasping," a special grasping mode that allows the wrapping of a flexible thin object around the fingers of the gripper, can be achieved by the twisting motion. Twist grasping is effective for handling objects with flexible thin parts, such as laminated packaging pouches, that are difficult to grasp using conventional antipodal grasping. In this study, the gripper design is presented, and twist grasping is analyzed. The gripper performance is experimentally validated.

Robotic hands with soft surfaces can perform stable grasping, but the high friction of the soft surfaces makes it difficult to release objects, or to perform operations that require sliding. To solve this issue, we previously developed a contact area variable surface (CAVS), whose friction changed according to the load. However, only our fundamental results were previously presented, with detailed analyses not provided. In this study, we first investigated the CAVS friction anisotropy, and demonstrated that the longitudinal direction exhibited a larger ratio of friction change. Next, we proposed a sensible CAVS, capable of providing a variable-friction mechanism, and tested its sensing and control systems in operations requiring switching between sliding and stable-grasping modes. Friction sensing was performed using an embedded camera, and we developed a gripper using the sensible CAVS, considering the CAVS friction anisotropy. In CAVS, the low-friction mode corresponds to a small grasping force, while the high-friction mode corresponds to a greater grasping force. Therefore, by controlling only the friction mode, the gripper mode can be set to either the sliding or stable-grasping mode. Based on this feature, a methodology for controlling the contact mode was constructed. We demonstrated a manipulation involving sliding and stable grasping, and thus verified the efficacy of the developed sensible CAVS.

This letter proposes a novel single-fingered reconfigurable robotic gripper for grasping objects in narrow working spaces. The finger of the developed gripper realizes two configurations, namely, the insertion and grasping modes, using only a single motor. In the insertion mode, the finger assumes a thin shape such that it can insert its tip into a narrow space. The grasping mode of the finger is activated through a folding mechanism. Mode switching can be achieved in two ways: switching the mode actively by a motor, or combining passive rotation of the fingertip through contact with the support surface and active motorized construction of the claw. The latter approach is effective when it is unclear how much finger insertion is required for a specific task. The structure provides a simple control scheme. The performance of the proposed robotic gripper design and control methodology was experimentally evaluated. The minimum width of the insertion space required to grasp an object is 4 mm (1 mm, when using a strategy).

顺序标记是一项基本的NLP任务，构成了许多应用程序的骨干。对SEQ2SEQ模型的监督学习（如T5）在这些问题上取得了巨大的成功。但是，这些模型的培训目标与我们在实际应用中关心的指标和Desiderata之间存在显着脱节。例如，实用的序列标记应用程序可能需要优化某些Precision-Recall折衷（TOP-K预测），这与最大化金标记序列的可能性的标准目标完全不同。因此，为了弥合这一差距，我们提出了Groot，这是一个简单而有效的框架，用于生成文本序列的奖励优化。 Groot通过训练生成的顺序标记模型来工作，以将解码器输出分布与（Black-Box）奖励函数的输出分布相匹配。使用迭代培训制度，我们首先生成预测候选者，然后纠正其中的错误，最后对比这些候选者（基于其奖励价值）。正如通过四个公共基准测试的广泛实验所证明的那样，Groot显着改善了所有奖励指标。此外，Groot还导致了整体解码器分布的改善，这是由顶级$ K $候选者的质量提高所证明的。

小型模块化反应堆的概念改变了解决未来能源危机的前景。考虑到其较低的投资要求，模块化，设计简单性和增强的安全功能，这种新的反应堆技术非常有希望。人工智能驱动的多尺度建模（中子，热液压，燃料性能等）在小型模块化反应堆的研究中纳入了数字双胞胎和相关的不确定性。在这项工作中，进行了一项关于耐亡燃料的多尺度建模的全面研究。探索了这些燃料在轻水的小型模块化反应堆中的应用。本章还重点介绍了机器学习和人工智能在设计优化，控制和监视小型模块反应器中的应用。最后，简要评估了有关人工智能在高燃烧复合事故耐受燃料的发展中的研究差距。还讨论了实现这些差距的必要行动。

利用预训练语言模型的抽象摘要系统在基准数据集上取得了卓越的结果。但是，此类模型已被证明更容易幻觉，这些事实对输入背景不忠。在本文中，我们提出了一种通过实体覆盖范围控制（ECC）来补救实体级外部幻觉的方法。我们首先计算实体覆盖范围的精度，并为每个培训示例提供相应的控制代码，该示例隐含地指导该模型在训练阶段识别忠实的内容。我们通过从Wikipedia提取的大但嘈杂的数据中进行中间调整进一步扩展了我们的方法，以解锁零击摘要。我们表明，根据我们对三个基准数据集XSUM，PubMed和Samsum的实验结果，根据我们在监督的微调和零射击设置中，可以在监督微调和零摄像设置中更加忠实和显着的抽象性汇总。

婴儿对一般运动（GM）的评估是早期诊断神经发育障碍的有用工具。但是，其在临床实践中的评估依赖于专家的视觉检查，并且热切期待自动解决方案。最近，基于视频的GMS分类引起了人们的注意，但是这种方法将受到无关信息的强烈影响，例如视频中的背景混乱。此外，为了可靠性，有必要在GMS期间正确提取婴儿的时空特征。在这项研究中，我们提出了一种自动GMS分类方法，该方法由预处理网络组成，该网络从GMS视频中删除不必要的背景信息并调整婴儿的身体位置以及基于两流结构的后续运动分类网络。提出的方法可以有效地提取GMS分类的基本时空特征，同时防止过度拟合与不同记录环境无关的信息。我们使用从100名婴儿获得的视频验证了提出的方法。实验结果表明，所提出的方法的表现优于几个基线模型和现有方法。

预计机器人将取代诸如家务之类的琐碎任务。其中一些任务包括执行的无毛线操作，而无需抓住对象。非忧虑的操作非常困难，因为它需要考虑环境和对象的动态。因此，模仿复杂行为需要大量的人类示范。在这项研究中，提出了一种自我监督的学习，该学习认为动态以实现可变速度进行非骚扰操作。所提出的方法仅收集自主操作期间获得的成功动作数据。通过微调成功的数据，机器人可以学习自身，环境和对象之间的动态。我们尝试使用对24个人类收集的培训数据训练的神经网络模型来挖掘和运输煎饼的任务。所提出的方法将成功率从40.2％提高到85.7％，并成功完成了其他物体的任务超过75％。