基于机器学习和其他AI技术的数据驱动模型(DDM)在越来越多的自主系统的感知中起着重要作用。由于仅基于用于培训的数据而仅对其行为进行隐式定义,因此DDM输出可能会出现不确定性。这对通过DDMS实现安全 - 关键感知任务的挑战提出了挑战。解决这一挑战的一种有希望的方法是估计操作过程中当前情况的不确定性,并相应地调整系统行为。在先前的工作中,我们专注于对不确定性的运行时估计,并讨论了处理不确定性估计的方法。在本文中,我们提出了处理不确定性的其他架构模式。此外,我们在定性和定量上对安全性和性能提高进行了定量评估。对于定量评估,我们考虑了一个用于车辆排的距离控制器,其中通过考虑在不同的操作情况下可以降低距离的距离来衡量性能增长。我们得出的结论是,考虑驾驶状况的上下文信息的考虑使得有可能或多或少地接受不确定性,具体取决于情况的固有风险,从而导致绩效提高。
translated by 谷歌翻译
Graph neural networks have recently achieved great successes in predicting quantum mechanical properties of molecules. These models represent a molecule as a graph using only the distance between atoms (nodes). They do not, however, consider the spatial direction from one atom to another, despite directional information playing a central role in empirical potentials for molecules, e.g. in angular potentials. To alleviate this limitation we propose directional message passing, in which we embed the messages passed between atoms instead of the atoms themselves. Each message is associated with a direction in coordinate space. These directional message embeddings are rotationally equivariant since the associated directions rotate with the molecule. We propose a message passing scheme analogous to belief propagation, which uses the directional information by transforming messages based on the angle between them. Additionally, we use spherical Bessel functions and spherical harmonics to construct theoretically well-founded, orthogonal representations that achieve better performance than the currently prevalent Gaussian radial basis representations while using fewer than 1 /4 of the parameters. We leverage these innovations to construct the directional message passing neural network (DimeNet). DimeNet outperforms previous GNNs on average by 76 % on MD17 and by 31 % on QM9. Our implementation is available online. 1
translated by 谷歌翻译
With increasing number of crowdsourced private automatic weather stations (called TPAWS) established to fill the gap of official network and obtain local weather information for various purposes, the data quality is a major concern in promoting their usage. Proper quality control and assessment are necessary to reach mutual agreement on the TPAWS observations. To derive near real-time assessment for operational system, we propose a simple, scalable and interpretable framework based on AI/Stats/ML models. The framework constructs separate models for individual data from official sources and then provides the final assessment by fusing the individual models. The performance of our proposed framework is evaluated by synthetic data and demonstrated by applying it to a re-al TPAWS network.
translated by 谷歌翻译
We apply Physics Informed Neural Networks (PINNs) to the problem of wildfire fire-front modelling. The PINN is an approach that integrates a differential equation into the optimisation loss function of a neural network to guide the neural network to learn the physics of a problem. We apply the PINN to the level-set equation, which is a Hamilton-Jacobi partial differential equation that models a fire-front with the zero-level set. This results in a PINN that simulates a fire-front as it propagates through a spatio-temporal domain. We demonstrate the agility of the PINN to learn physical properties of a fire under extreme changes in external conditions (such as wind) and show that this approach encourages continuity of the PINN's solution across time. Furthermore, we demonstrate how data assimilation and uncertainty quantification can be incorporated into the PINN in the wildfire context. This is significant contribution to wildfire modelling as the level-set method -- which is a standard solver to the level-set equation -- does not naturally provide this capability.
translated by 谷歌翻译
With an ever-growing number of new publications each day, scientific writing poses an interesting domain for authorship analysis of both single-author and multi-author documents. Unfortunately, most existing corpora lack either material from the science domain or the required metadata. Hence, we present SMAuC, a new metadata-rich corpus designed specifically for authorship analysis in scientific writing. With more than three million publications from various scientific disciplines, SMAuC is the largest openly available corpus for authorship analysis to date. It combines a wide and diverse range of scientific texts from the humanities and natural sciences with rich and curated metadata, including unique and carefully disambiguated author IDs. We hope SMAuC will contribute significantly to advancing the field of authorship analysis in the science domain.
translated by 谷歌翻译
我们提出了一种新的方法,可以在复杂模型(例如贝叶斯神经网络)中执行近似贝叶斯推断。该方法比马尔可夫链蒙特卡洛更可扩展到大数据,它具有比变异推断更具表现力的模型,并且不依赖于对抗训练(或密度比估计)。我们采用了构建两个模型的最新方法:(1)一个主要模型,负责执行回归或分类; (2)一个辅助,表达的(例如隐式)模型,该模型定义了主模型参数上的近似后验分布。但是,我们根据后验预测分布的蒙特卡洛估计值通过梯度下降来优化后验模型的参数 - 这是我们唯一的近似值(除后模型除外)。只需要指定一个可能性,可以采用各种形式,例如损失功能和合成可能性,从而提供无可能的方法的形式。此外,我们制定了该方法,使后样品可以独立于或有条件地取决于主要模型的输入。后一种方法被证明能够增加主要模型的明显复杂性。我们认为这在诸如替代和基于物理的模型之类的应用中很有用。为了促进贝叶斯范式如何提供不仅仅是不确定性量化的方式,我们证明了:不确定性量化,多模式以及具有最新预测的神经网络体系结构的应用。
translated by 谷歌翻译
神经建筑搜索(NAS)已被广泛研究,并已成长为具有重大影响的研究领域。虽然经典的单目标NAS搜索具有最佳性能的体系结构,但多目标NAS考虑了应同时优化的多个目标,例如,将沿验证错误最小化资源使用率。尽管在多目标NAS领域已经取得了长足的进步,但我们认为实际关注的实际优化问题与多目标NAS试图解决的优化问题之间存在一些差异。我们通过将多目标NAS问题作为质量多样性优化(QDO)问题来解决这一差异,并引入了三种质量多样性NAS优化器(其中两个属于多重速度优化器组),以寻求高度多样化但多样化的体系结构对于特定于应用程序特定的利基,例如硬件约束。通过将这些优化器与它们的多目标对应物进行比较,我们证明了质量多样性总体上优于多目标NA在解决方案和效率方面。我们进一步展示了应用程序和未来的NAS研究如何在QDO上蓬勃发展。
translated by 谷歌翻译
比较不同的汽车框架是具有挑战性的,并且经常做错了。我们引入了一个开放且可扩展的基准测试,该基准遵循最佳实践,并在比较自动框架时避免常见错误。我们对71个分类和33项回归任务进行了9个著名的自动框架进行了详尽的比较。通过多面分析,评估模型的准确性,与推理时间的权衡以及框架失败,探索了自动框架之间的差异。我们还使用Bradley-terry树来发现相对自动框架排名不同的任务子集。基准配备了一个开源工具,该工具与许多自动框架集成并自动化经验评估过程端到端:从框架安装和资源分配到深入评估。基准测试使用公共数据集,可以轻松地使用其他Automl框架和任务扩展,并且具有最新结果的网站。
translated by 谷歌翻译
平均网络集合的预测是改善各种基准和kaggle竞争中预测性能和计算的尖端有效方法。但是,深层合奏的Thruntime和培训成本随着整体的规模线性增长,使它们不适合许多应用。平均重量的权重代替预测规定了这种不利性推断,通常应用于模型的中间检查点以降低训练成本。尽管有效,但只有很少的作品可以平均体重的理解和表现。我们描述了重量必须符合体重空间,功能空间和损失的互动的先决条件。此外,我们介绍了新的测试方法(称为Oracle测试),以测量权重之间的功能空间。我们证明了我们的WF战略在艺术分割CNN和变形金刚以及BDD100K和CityScapes等现实世界中的多功能性。我们将WF与类似的操作进行了比较,并显示了我们对预测性能和校准的分布数据术语的优势。
translated by 谷歌翻译
语义场景的理解对于在各种环境中作用的移动代理至关重要。尽管语义细分已经提供了大量信息,但缺少有关单个对象以及一般场景的详细信息,但对于许多现实世界应用程序所必需。但是,分别解决多个任务是昂贵的,并且在移动平台上计算和电池能力有限,无法实时完成。在本文中,我们提出了一种有效的多任务方法,用于RGB-D场景分析〜(EMSANET),该方法同时执行语义和实例分割〜(Panoptic分割),实例方向估计和场景分类。我们表明,所有任务都可以在移动平台上实时使用单个神经网络完成,而不会降低性能 - 相比之下,各个任务能够彼此受益。为了评估我们的多任务方法,我们扩展了常见的RGB-D室内数据集NYUV2和SUNRGB-D的注释,例如分割和方向估计。据我们所知,我们是第一个为NYUV2和SUNRGB-D上的室内场景分析提供如此全面的多任务设置的结果。
translated by 谷歌翻译