The potential for complex systems to exhibit tipping points in which an equilibrium state undergoes a sudden and often irreversible shift is well established, but prediction of these events using standard forecast modeling techniques is quite difficult. This has led to the development of an alternative suite of methods that seek to identify signatures of critical phenomena in data, which are expected to occur in advance of many classes of dynamical bifurcation. Crucially, the manifestations of these critical phenomena are generic across a variety of systems, meaning that data-intensive deep learning methods can be trained on (abundant) synthetic data and plausibly prove effective when transferred to (more limited) empirical data sets. This paper provides a proof of concept for this approach as applied to lattice phase transitions: a deep neural network trained exclusively on 2D Ising model phase transitions is tested on a number of real and simulated climate systems with considerable success. Its accuracy frequently surpasses that of conventional statistical indicators, with performance shown to be consistently improved by the inclusion of spatial indicators. Tools such as this may offer valuable insight into climate tipping events, as remote sensing measurements provide increasingly abundant data on complex geospatially-resolved Earth systems.
translated by 谷歌翻译
A fundamental challenge to providing edge-AI services is the need for a machine learning (ML) model that achieves personalization (i.e., to individual clients) and generalization (i.e., to unseen data) properties concurrently. Existing techniques in federated learning (FL) have encountered a steep tradeoff between these objectives and impose large computational requirements on edge devices during training and inference. In this paper, we propose SplitGP, a new split learning solution that can simultaneously capture generalization and personalization capabilities for efficient inference across resource-constrained clients (e.g., mobile/IoT devices). Our key idea is to split the full ML model into client-side and server-side components, and impose different roles to them: the client-side model is trained to have strong personalization capability optimized to each client's main task, while the server-side model is trained to have strong generalization capability for handling all clients' out-of-distribution tasks. We analytically characterize the convergence behavior of SplitGP, revealing that all client models approach stationary points asymptotically. Further, we analyze the inference time in SplitGP and provide bounds for determining model split ratios. Experimental results show that SplitGP outperforms existing baselines by wide margins in inference time and test accuracy for varying amounts of out-of-distribution samples.
translated by 谷歌翻译
This white paper lays out a vision of research and development in the field of artificial intelligence for the next decade (and beyond). Its denouement is a cyber-physical ecosystem of natural and synthetic sense-making, in which humans are integral participants$\unicode{x2014}$what we call ''shared intelligence''. This vision is premised on active inference, a formulation of adaptive behavior that can be read as a physics of intelligence, and which inherits from the physics of self-organization. In this context, we understand intelligence as the capacity to accumulate evidence for a generative model of one's sensed world$\unicode{x2014}$also known as self-evidencing. Formally, this corresponds to maximizing (Bayesian) model evidence, via belief updating over several scales: i.e., inference, learning, and model selection. Operationally, this self-evidencing can be realized via (variational) message passing or belief propagation on a factor graph. Crucially, active inference foregrounds an existential imperative of intelligent systems; namely, curiosity or the resolution of uncertainty. This same imperative underwrites belief sharing in ensembles of agents, in which certain aspects (i.e., factors) of each agent's generative world model provide a common ground or frame of reference. Active inference plays a foundational role in this ecology of belief sharing$\unicode{x2014}$leading to a formal account of collective intelligence that rests on shared narratives and goals. We also consider the kinds of communication protocols that must be developed to enable such an ecosystem of intelligences and motivate the development of a shared hyper-spatial modeling language and transaction protocol, as a first$\unicode{x2014}$and key$\unicode{x2014}$step towards such an ecology.
translated by 谷歌翻译
本文考虑通过模型量化提高联邦学习(FL)的无线通信和计算效率。在提出的Bitwidth FL方案中,Edge设备将其本地FL模型参数的量化版本训练并传输到协调服务器,从而将它们汇总为量化的全局模型并同步设备。目的是共同确定用于本地FL模型量化的位宽度以及每次迭代中参与FL训练的设备集。该问题被视为一个优化问题,其目标是在每卷工具采样预算和延迟要求下最大程度地减少量化FL的训练损失。为了得出解决方案,进行分析表征,以显示有限的无线资源和诱导的量化误差如何影响所提出的FL方法的性能。分析结果表明,两个连续迭代之间的FL训练损失的改善取决于设备的选择和量化方案以及所学模型固有的几个参数。给定基于线性回归的这些模型属性的估计值,可以证明FL训练过程可以描述为马尔可夫决策过程(MDP),然后提出了基于模型的增强学习(RL)方法来优化动作的方法选择迭代。与无模型RL相比,这种基于模型的RL方法利用FL训练过程的派生数学表征来发现有效的设备选择和量化方案,而无需强加其他设备通信开销。仿真结果表明,与模型无RL方法和标准FL方法相比,提出的FL算法可以减少29%和63%的收敛时间。
translated by 谷歌翻译
逆运动学(IK)系统通常相对于其输入特征很僵硬,因此需要将用户干预适应新骨架。在本文中,我们旨在创建一个适用于各种人类形态的灵活的,学到的IK求解器。我们扩展了最先进的机器学习IK求解器,以在众所周知的皮肤多人线性模型(SMPL)上运行。我们称我们的模型SMPL-IK,并表明当集成到实时3D软件中时,该扩展系统为定义新型AI-Asissist Animation Workfrows提供了机会。例如,通过允许用户在摆姿势的同时修改性别和身体形状,可以使姿势创作更加灵活。此外,当使用现有姿势估计算法链接时,SMPL-IK通过允许用户从2D图像引导3D场景来加速摆姿势,同时允许进一步编辑。最后,我们提出了一种新颖的SMPL形状反转机制(SMPL-SI),将任意类人形特征映射到SMPL空间,使艺术家能够在自定义字符上利用SMPL-IK。除了显示拟议工具的定性演示外,我们还介绍了H36M和Amass数据集上的定量SMPL-IK基准。
translated by 谷歌翻译
联合学习(FL)被认为是分布式机器学习(ML)最有前途的解决方案之一。在当前的大多数文献中,FL已被研究用于监督的ML任务,其中边缘设备收集标记的数据。然而,在许多应用中,假设存在跨设备标记的数据是不切实际的。为此,我们开发了一种新颖的方法论,合作联合无监督的对比度学习(CF-CL),用于使用未标记的数据集的跨越边缘设备的FL。 CF-CL采用本地设备合作,其中通过设备到设备(D2D)通信在设备之间进行数据交换,以避免由非独立且相同分布式(非I.I.I.I.D。)本地数据集引起的本地模型偏差。 CF-CL引入了针对无监督的FL设置量身定制的推动力智能数据共享机制,在该设置中,每个设备将其本地数据点的子集推向其邻居,作为保留数据点,并从其邻居中提取一组数据点,并通过其进行采样概率重要性抽样技术。我们证明,CF-CL导致(i)跨设备的无监督的潜在空间对齐,(ii)更快的全局收敛,允许较低的全局模型聚合; (iii)在极端非i.i.d中有效。跨设备的数据设置。
translated by 谷歌翻译
本文介绍了BRL/PISA/IIT(BPI)SOFTHAND:单个执行器驱动的,低成本,3D打印,肌腱驱动的机器人手,可用于执行一系列掌握任务。基于PISA/IIT SOFTHAND的自适应协同作用,我们设计了一种新的关节系统和肌腱路由,以促进软化和适应性的协同作用,这有助于我们平衡手的耐用性,负担能力和握住手的性能。这项工作的重点在于该杂种的设计,仿真,协同作用和抓握测试。新颖的小块是根据连锁,齿轮对和几何约束机制设计和印刷的,可以应用于大多数肌腱驱动的机器人手。我们表明,机器人手可以成功地掌握和提起各种目标对象并适应复杂的几何形状,从而反映了软化和适应性协同的成功采用。我们打算为手的设计开放源,以便可以在家用3D打印机上廉价地构建。有关更多详细信息:https://sites.google.com/view/bpi-softhandtactile-group-bri/brlpisaiit-softhand-design
translated by 谷歌翻译
人们如何积极学习学习?也就是说,人们如何以及何时选择促进长期学习和选择更有益的行动的行动?我们在积极的因果学习领域中探索这些问题。我们提出了一个层次的贝叶斯模型,该模型通过预测人们不仅追求有关因果关系的信息,而且还涉及因果关系的信息,$ \ unicode {x2014} $摘要信念关于因果关系的抽象信念,这些关系跨越了多种情况,并约束了我们如何约束我们如何限制了我们如何限制我们的因果关系。在每种情况下学习细节。在具有14个受试者间操作的两个主动“泡沫检测器”实验中,我们的模型受到参与者行为的定性趋势和基于个体差异的模型比较的支持。我们的结果表明,当在积极的因果学习问题之间存在抽象相似之处时,人们很容易就这些相似性学习和转移过度的疏忽。此外,人们利用这些夸张的人来促进长期的积极学习。
translated by 谷歌翻译
难以理解的AI系统很难信任,尤其是当它们在自动驾驶(例如自动驾驶)等安全环境中运行时。因此,有必要建立透明且可查询的系统以提高信任水平。我们提出了一种基于现有的称为IGP2的现有白盒系统的自动驾驶汽车运动计划和预测的透明,以人为中心的解释生成方法。我们的方法将贝叶斯网络与无上下文生成规则相结合,并可以为自动驾驶汽车的高级驾驶行为提供因果自然语言解释。对模拟方案的初步测试表明,我们的方法捕获了自动驾驶汽车行动背后的原因,并产生了具有不同复杂性的可理解解释。
translated by 谷歌翻译
尽管电子健康记录是生物医学研究的丰富数据来源,但这些系统并未在医疗环境中统一地实施,并且由于医疗保健碎片化和孤立的电子健康记录之间缺乏互操作性,可能缺少大量数据。考虑到缺少数据的案例的删除可能会在随后的分析中引起严重的偏见,因此,一些作者更喜欢采用多重插补策略来恢复缺失的信息。不幸的是,尽管几项文献作品已经通过使用现在可以自由研究的任何不同的多个归档算法记录了有希望的结果,但尚无共识,MI算法效果最好。除了选择MI策略之外,归纳算法及其应用程序设置的选择也至关重要且具有挑战性。在本文中,受鲁宾和范布伦的开创性作品的启发,我们提出了一个方法学框架,可以应用于评估和比较多种多个插补技术,旨在选择用于计算临床研究工作中最有效的推断。我们的框架已被应用于验证和扩展较大的队列,这是我们在先前的文献研究中提出的结果,我们在其中评估了关键患者的描述符和Covid-19的影响在2型糖尿病患者中的影响,其数据为2型糖尿病,其数据为2型糖尿病由国家共同队列合作飞地提供。
translated by 谷歌翻译