在本文中,我们在拓扑数据分析和几何深度学习之间建立了一个桥梁,调整了群体模棱两可的非企业运算符(Geneos)的拓扑理论,以在所有图表的空间上作用于在顶点或边缘加权的所有图。这是通过展示Geneo的一般概念可以用于转换图形并提供有关其结构的信息来完成的。这就需要引入广义定义和广义定义措施的新概念以及这些概念使我们能够在图之间构建基因的数学证据。实验部分结束了本文,说明了我们的操作员可能使用从图形中提取信息。本文是一系列研究线的一部分,该研究致力于为几何深度学习开发基因诺的组成和几何理论。
translated by 谷歌翻译
Artificial intelligence (AI) in its various forms finds more and more its way into complex distributed systems. For instance, it is used locally, as part of a sensor system, on the edge for low-latency high-performance inference, or in the cloud, e.g. for data mining. Modern complex systems, such as connected vehicles, are often part of an Internet of Things (IoT). To manage complexity, architectures are described with architecture frameworks, which are composed of a number of architectural views connected through correspondence rules. Despite some attempts, the definition of a mathematical foundation for architecture frameworks that are suitable for the development of distributed AI systems still requires investigation and study. In this paper, we propose to extend the state of the art on architecture framework by providing a mathematical model for system architectures, which is scalable and supports co-evolution of different aspects for example of an AI system. Based on Design Science Research, this study starts by identifying the challenges with architectural frameworks. Then, we derive from the identified challenges four rules and we formulate them by exploiting concepts from category theory. We show how compositional thinking can provide rules for the creation and management of architectural frameworks for complex systems, for example distributed systems with AI. The aim of the paper is not to provide viewpoints or architecture models specific to AI systems, but instead to provide guidelines based on a mathematical formulation on how a consistent framework can be built up with existing, or newly created, viewpoints. To put in practice and test the approach, the identified and formulated rules are applied to derive an architectural framework for the EU Horizon 2020 project ``Very efficient deep learning in the IoT" (VEDLIoT) in the form of a case study.
translated by 谷歌翻译
变形金刚目前是自然语言理解(NLU)任务的最新技术,容易产生未校准的预测或极端概率,从而根据其输出相对困难而做出不同的决策过程。在本文中,我们建议构建几个电感Venn - 持续预测因子(IVAP),这些预测因子(IVAP)可以根据预先训练的变压器的选择在最小的假设下可以很好地校准。我们在一组不同的NLU任务上测试了它们的性能,并表明它们能够产生均匀分布在[0,1]间隔的概率预测的良好概率预测,同时均保留了原始模型的预测准确性。
translated by 谷歌翻译
从文本中提取过程是过程发现的重要任务,近年来已经开发了各种方法。但是,与其他信息提取任务相反,缺乏商业流程描述的金标准库,这些文献对所有感兴趣的实体和关系仔细注释。因此,目前很难以客观的方式比较通过提取方法获得的结果,而缺乏带注释的文本也阻止了数据驱动的信息提取方法的应用,这是自然语言处理领域的典型特征。因此,为了弥合这一差距,我们介绍了PET数据集,这是用活动,网关,参与者和流程信息注释的业务流程描述的第一个语料库。我们介绍了我们的新资源,包括各种基线,以基准从文本中提取业务流程的困难和挑战。可以通过huggingface.co/datasets/patriziobellan/pet访问宠物
translated by 谷歌翻译
在本作的工作中,提出了两种基于机器学习的有限变形的本质型模型。使用输入凸神经网络,该模型是过度塑化的,各向异性的并且实现了多种凸起条件,这意味着椭圆形,因此确保了材料稳定性。第一本构模型基于一组多晶硅,各向异性和目标不变。第二种方法在变形梯度,其辅助因子和决定簇方面配制,使用组对称性来满足材料对称条件,以及数据增强以满足客观性大致。数据集的扩展为数据增强方法是基于机械考虑,不需要额外的实验或模拟数据。该模型具有高度具有挑战性的立方晶格超材料的模拟数据,包括有限变形和格子稳定性。基于在实验研究中通常应用的变形,使用适量的校准数据。虽然基于不变的模型显示了几种变形模式的缺点,但是仅基于变形梯度的模型能够非常好地再现和预测有效的材料行为,并且表现出优异的泛化能力。此外,使用分析多晶硅电位产生横向各向同性数据校准模型。在这种情况下,两种模型都表现出优异的结果,展示了PolyConvex神经网络本构模型对其他对称组的直接适用性。
translated by 谷歌翻译