A gossip protocol is a procedure for sharing secrets in a network. The basic action in a gossip protocol is a pairwise message exchange (telephone call) wherein the calling agents exchange all the secrets they know. An agent who knows all secrets is an expert. The usual termination condition is that all agents are experts. Instead, we explore protocols wherein the termination condition is that all agents know that all agents are experts. We call such agents super experts. We also investigate gossip protocols that are common knowledge among the agents. Additionally, we model that agents who are super experts do not make and do not answer calls, and that this is common knowledge. We investigate conditions under which protocols terminate, both in the synchronous case, where there is a global clock, and in the asynchronous case, where there is not. We show that a commonly known protocol with engaged agents may terminate faster than the same commonly known protocol without engaged agents.
translated by 谷歌翻译
This paper expounds the design and control of a new Variable Stiffness Series Elastic Actuator (VSSEA). It is established by employing a modular mechanical design approach that allows us to effectively optimise the stiffness modulation characteristics and power density of the actuator. The proposed VSSEA possesses the following features: i) no limitation in the work-range of output link, ii) a wide range of stiffness modulation (~20Nm/rad to ~1KNm/rad), iii) low-energy-cost stiffness modulation at equilibrium and non-equilibrium positions, iv) compact design and high torque density (~36Nm/kg), and v) high-speed stiffness modulation (~3000Nm/rad/s). Such features can help boost the safety and performance of many advanced robotic systems, e.g., a cobot that physically interacts with unstructured environments and an exoskeleton that provides physical assistance to human users. These features can also enable us to utilise variable stiffness property to attain various regulation and trajectory tracking control tasks only by employing conventional controllers, eliminating the need for synthesising complex motion control systems in compliant actuation. To this end, it is experimentally demonstrated that the proposed VSSEA is capable of precisely tracking desired position and force control references through the use of conventional Proportional-Integral-Derivative (PID) controllers.
translated by 谷歌翻译
In this paper we look into the conjecture of Entezari et al. (2021) which states that if the permutation invariance of neural networks is taken into account, then there is likely no loss barrier to the linear interpolation between SGD solutions. First, we observe that neuron alignment methods alone are insufficient to establish low-barrier linear connectivity between SGD solutions due to a phenomenon we call variance collapse: interpolated deep networks suffer a collapse in the variance of their activations, causing poor performance. Next, we propose REPAIR (REnormalizing Permuted Activations for Interpolation Repair) which mitigates variance collapse by rescaling the preactivations of such interpolated networks. We explore the interaction between our method and the choice of normalization layer, network width, and depth, and demonstrate that using REPAIR on top of neuron alignment methods leads to 60%-100% relative barrier reduction across a wide variety of architecture families and tasks. In particular, we report a 74% barrier reduction for ResNet50 on ImageNet and 90% barrier reduction for ResNet18 on CIFAR10.
translated by 谷歌翻译
在本文中,研究了无线网络的联合学习(FL)。在每个通信回合中,选择一部分设备以有限的时间和能量参与聚合。为了最大程度地减少收敛时间,在基于Stackelberg游戏的框架中共同考虑了全球损失和延迟。具体而言,在Leader级别上,将基于信息的设备选择(AOI)选择为全球损失最小化问题,而子渠道分配,计算资源分配和功率分配在追随者级别被视为延迟最小化问题。通过将追随者级别的问题分为两个子问题,追随者的最佳响应是通过基于单调优化的资源分配算法和基于匹配的子渠道分配算法获得的。通过得出收敛速率的上限,重新制定了领导者级别的问题,然后提出了基于列表的设备选择算法来实现Stackelberg平衡。仿真结果表明,所提出的设备选择方案在全球损失方面优于其他方案,而开发的算法可以显着降低计算和通信的时间消耗。
translated by 谷歌翻译
这项研究深入研究了机器人支持的翻转课程的可行性,以阅读理解。在16项课程中,比较了444名学生的阅读理解和工作空间表现,并进行了商业化和自我生成的机器人的班级。结果表明,翻转的课程为医学目的的英语中学教育带来了良好的教学学习氛围(EMP)阅读理解,并采用主动方法来进行工作空间表现。在同时,混合效应模型表明,学生参与自我生成的机器人支持的翻转班级的效果大小(+17.6 \%)比商业机器人机器人支持的翻转类别更大。分析产生了EMP阅读理解和工作空间表现的五个促成主持人:阅读能力,态度,实践方式以及学生和教师的角色。
translated by 谷歌翻译
我们研究了不同修剪技术对具有对比损失功能的深神经网络所学的表示的影响。我们的工作发现,相对于经过传统的跨透明损失训练的模型,在高稀疏度水平上,对比度学习的示例数量更高。为了理解这种明显的差异,我们使用派(Hooker等,2019),Q-Score(Kalibhat等,2022)和PD-Score(Baldock等,2021)等指标(Hooker等,2019),测量修剪对学习的表示质量的影响。我们的分析表明,修剪方法实施的时间表很重要。我们发现,当在训练阶段早期引入修剪时,稀疏性对学习表示的质量的负面影响最高。
translated by 谷歌翻译
本文研究了静态稀疏对训练有素网络对扰动,数据腐败和对抗性示例的鲁棒性的影响。我们表明,通过增加网络宽度和深度,同时保持网络容量固定,稀疏网络始终匹配,并且通常优于其最初密集的版本,从而达到了一定的稀疏性。由于网络层之间的连通性松动而导致非常高的稀疏性同时下降。我们的发现表明,文献中观察到的网络压缩引起的快速鲁棒性下降是由于网络容量降低而不是稀疏性。
translated by 谷歌翻译
最近,修剪深度神经网络(DNNS)因提高准确性和泛化功率,降低网络规模以及提高专业硬件的推理速度而受到了很多关注。尽管修剪主要在计算机视觉任务上进行了测试,但几乎没有探索其在医学图像分析中的应用。这项工作调查了众所周知的修剪技术,即层和网络范围的修剪,对组织学图像中细胞核实例分割性能的影响。我们利用的实例分割模型由两个主要分支组成:(1)语义分割分支,以及(2)深层回归分支。我们研究了修剪对两个分支的性能的影响分别对两个分支的性能以及最终的核实例分割结果。在两个公开可用数据集上进行了评估,我们的结果表明,层修剪的性能比在较小的压缩比(CRS)的网络修剪方面稍好,而对于大型CRS,网络范围的修剪会产生出色的性能。对于语义分割,深度回归和最终实例分割,可以通过层的修剪来修剪93.75%,95%和80%的模型权重,而相应模型的性能降低了2%。
translated by 谷歌翻译
尽管准确的预测,但葡萄糖水平预测的数据驱动模型通常不会提供有意义的见解。然而,在医学中的背景理解至关重要,特别是糖尿病管理。在本文中,我们介绍了HAT-NET:一个混合模型,从生理模型中蒸馏到深度神经网络中的知识。它模拟葡萄糖,胰岛素和碳水化合物的扩散,通过具有由颂歌专家模型限制的经常性注意网络定制的生物启发深度学习架构。我们申请患有2型糖尿病患者的葡萄糖水平预测。它实现了竞争性表演,同时提供胰岛素和碳水化合物随时间扩散的合理测量。
translated by 谷歌翻译
环理论说明,环是代数结构,其中可以在元素添加和乘法之间进行两个二元操作。二值化是一种图像处理的方法,其中像素内的值减小到从零到一个的比例,零表示最不存在的光,一个表示最大的光。目前,超声图在扫描充血性心力衰竭中实施。然而,代表疾病的着名的花花公子兔子符号因周围的器官和较低的质量图像制作而越来越难以隔离。本文介绍了OTSU阈值处理方法,并结合了新的元素,以考虑不同的图像特征,意味着更好地在超声图像中隔离充血性心力衰竭指标。
translated by 谷歌翻译