Sunquakes are seismic emissions visible on the solar surface, associated with some solar flares. Although discovered in 1998, they have only recently become a more commonly detected phenomenon. Despite the availability of several manual detection guidelines, to our knowledge, the astrophysical data produced for sunquakes is new to the field of Machine Learning. Detecting sunquakes is a daunting task for human operators and this work aims to ease and, if possible, to improve their detection. Thus, we introduce a dataset constructed from acoustic egression-power maps of solar active regions obtained for Solar Cycles 23 and 24 using the holography method. We then present a pedagogical approach to the application of machine learning representation methods for sunquake detection using AutoEncoders, Contrastive Learning, Object Detection and recurrent techniques, which we enhance by introducing several custom domain-specific data augmentation transformations. We address the main challenges of the automated sunquake detection task, namely the very high noise patterns in and outside the active region shadow and the extreme class imbalance given by the limited number of frames that present sunquake signatures. With our trained models, we find temporal and spatial locations of peculiar acoustic emission and qualitatively associate them to eruptive and high energy emission. While noting that these models are still in a prototype stage and there is much room for improvement in metrics and bias levels, we hypothesize that their agreement on example use cases has the potential to enable detection of weak solar acoustic manifestations.
translated by 谷歌翻译
冠状质量弹出(CME)是最地理化的空间天气现象,与大型地磁风暴有关,有可能引起电信,卫星网络中断,电网损失和故障的干扰。因此,考虑到这些风暴对人类活动的潜在影响,对CME的地理效果的准确预测至关重要。这项工作着重于在接近太阳CME的白光冠状动脉数据集中训练的不同机器学习方法,以估计这种新爆发的弹出是否有可能诱导地磁活动。我们使用逻辑回归,k-nearest邻居,支持向量机,向前的人工神经网络以及整体模型开发了二进制分类模型。目前,我们限制了我们的预测专门使用太阳能发作参数,以确保延长警告时间。我们讨论了这项任务的主要挑战,即我们数据集中的地理填充和无效事件的数量以及它们的众多相似之处以及可用变量数量有限的极端失衡。我们表明,即使在这种情况下,这些模型也可以达到足够的命中率。
translated by 谷歌翻译
Traditionally, robots are regarded as universal motion generation machines. They are designed mainly by kinematics considerations while the desired dynamics is imposed by strong actuators and high-rate control loops. As an alternative, one can first consider the robot's intrinsic dynamics and optimize it in accordance with the desired tasks. Therefore, one needs to better understand intrinsic, uncontrolled dynamics of robotic systems. In this paper we focus on periodic orbits, as fundamental dynamic properties with many practical applications. Algebraic topology and differential geometry provide some fundamental statements about existence of periodic orbits. As an example, we present periodic orbits of the simplest multi-body system: the double-pendulum in gravity. This simple system already displays a rich variety of periodic orbits. We classify these into three classes: toroidal orbits, disk orbits and nonlinear normal modes. Some of these we found by geometrical insights and some by numerical simulation and sampling.
translated by 谷歌翻译
Collaborative autonomous multi-agent systems covering a specified area have many potential applications, such as UAV search and rescue, forest fire fighting, and real-time high-resolution monitoring. Traditional approaches for such coverage problems involve designing a model-based control policy based on sensor data. However, designing model-based controllers is challenging, and the state-of-the-art classical control policy still exhibits a large degree of suboptimality. In this paper, we present a reinforcement learning (RL) approach for the multi-agent coverage problem involving agents with second-order dynamics. Our approach is based on the Multi-Agent Proximal Policy Optimization Algorithm (MAPPO). To improve the stability of the learning-based policy and efficiency of exploration, we utilize an imitation loss based on the state-of-the-art classical control policy. Our trained policy significantly outperforms the state-of-the-art. Our proposed network architecture includes incorporation of self attention, which allows a single-shot domain transfer of the trained policy to a large variety of domain shapes and number of agents. We demonstrate our proposed method in a variety of simulated experiments.
translated by 谷歌翻译
持续学习系统将知识从先前看到的任务转移以最大程度地提高新任务的能力是该领域的重大挑战,从而限制了持续学习解决方案对现实情况的适用性。因此,本研究旨在扩大我们在不断加强学习的特定情况下对转移及其驱动力的理解。我们采用SAC作为基础RL算法和持续的世界作为连续控制任务的套件。我们系统地研究SAC(演员和评论家,勘探和数据)的不同组成部分如何影响转移功效,并提供有关各种建模选项的建议。在最近的连续世界基准中评估了最佳的选择,即称为clonex-sac。 Clonex-SAC获得了87%的最终成功率,而Packnet的80%是基准中的最佳方法。此外,根据连续世界提供的指标,转移从0.18增至0.54。
translated by 谷歌翻译
腿部运动中的弹簧基于弹簧的执行器可提供能量效率和提高的性能,但增加了控制器设计的难度。尽管以前的作品集中在广泛的建模和模拟上,以找到此类系统的最佳控制器,但我们建议直接在真实机器人上学习无模型控制器。在我们的方法中,步态首先是由中央模式发电机(CPG)合成的,其参数被优化以快速获得可实现有效运动的开环控制器。然后,为了使该控制器更强大并进一步提高性能,我们使用强化学习来关闭循环,以在CPG之上学习纠正措施。我们评估了DLR弹性四足动物BERT中提出的方法。我们在学习小跑和前进步态方面的结果表明,对弹簧执行动力学的开发自然而然地从对动态运动的优化中出现,尽管没有模型,但仍会产生高性能的运动。整个过程在真正的机器人上不超过1.5小时,并导致自然步态。
translated by 谷歌翻译
机器学习渗透到许多行业,这为公司带来了新的利益来源。然而,在人寿保险行业中,机器学习在实践中并未被广泛使用,因为在过去几年中,统计模型表明了它们的风险评估效率。因此,保险公司可能面临评估人工智能价值的困难。随着时间的流逝,专注于人寿保险行业的修改突出了将机器学习用于保险公司的利益以及通过释放数据价值带来的利益。本文回顾了传统的生存建模方法论,并通过机器学习技术扩展了它们。它指出了与常规机器学习模型的差异,并强调了特定实现在与机器学习模型家族中面对审查数据的重要性。在本文的补充中,已经开发了Python库。已经调整了不同的开源机器学习算法,以适应人寿保险数据的特殊性,即检查和截断。此类模型可以轻松地从该SCOR库中应用,以准确地模拟人寿保险风险。
translated by 谷歌翻译
人类从不同地点和时间的事件的发生中学习,以预测类似的事件轨迹。我们将松散的分离时间(LDT)现象定义为两个或多个事件,这些事件可能在不同的地方和不同的时间表中发生,但在事件的性质和位置的属性上共享相似之处。在这项工作中,我们改善了重复的神经网络(RNN)的使用,特别是短期内存(LSTM)网络,以启用为LDT生成更好的时间表预测的AI解决方案。我们根据趋势使用时间表之间的相似性度量,并引入代表这些趋势的嵌入。嵌入代表事件的属性,该属性与LSTM结构相结合,可以聚集以识别类似的时间不对然后的事件。在本文中,我们探讨了从与LSTM建模的地球物理和人口统计学现象有关的时间不变数据中播种多元LSTM的方法。我们将这些方法应用于从COVID-19检测到的感染和死亡病例中得出的时间表数据。我们使用公开可用的社会经济数据来播种LSTM模型,创建嵌入,以确定这种播种是否改善了病例预测。这些LSTM产生的嵌入量被聚集,以识别预测不断发展的时间表的最佳匹配候选者。采用这种方法,我们显示了美国县一级疾病传播的10天移动平均预测的改善。
translated by 谷歌翻译
手动检查粪便涂片样品以鉴定寄生卵的存在非常耗时,只能由专家进行。因此,需要自动化系统来解决此问题,因为它可以与严重的肠道寄生虫感染有关。本文回顾了微观图像中关于寄生卵检测和分类的ICIP 2022挑战。我们描述了此应用程序的新数据集,该数据集是同类数据集的最大数据集。参与者在挑战中使用的方法及其结果及其结果进行了汇总和讨论。
translated by 谷歌翻译
深度神经网络是当今离线增强学习中最常用的功能近似值。先前的工作表明,接受TD学习和梯度下降训练的神经网可以表现出隐式正则化,可以通过这些网络的参数化不足来表征。具体而言,已经观察到在训练期间,倒数第二个特征层的排名(也称为\ textit {有效等级})急剧崩溃。反过来,这种崩溃被认为是为了降低模型在学习后期进一步适应的能力,从而导致最终表现降低。有效等级和绩效之间的这种关联使离线RL的有效等级引人注目,主要用于离线政策评估。在这项工作中,我们对三个离线RL数据集的有效等级与绩效之间的关系进行了仔细的实证研究:Bsuite,Atari和DeepMind Lab。我们观察到,直接关联仅存在于受限的设置中,并且在更广泛的超参数扫描中消失。此外,我们从经验上确定了三个学习的阶段,这些阶段解释了隐式正则化对学习动力学的影响,并发现单独进行引导不足以解释有效等级的崩溃。此外,我们表明其他几个因素可能会混淆有效的等级与绩效之间的关系,并得出结论,在简单假设下研究这种关联可能会产生高度误导。
translated by 谷歌翻译