当可用时,我们继续研究宠物或SPECT等抛光断层凝视的不确定性量化问题。为了解决上述问题,我们将最近提出的非参数后学习技术适应排放断层扫描中泊松型数据的背景。使用这种方法,我们推出了采样算法,这些算法是微不一性的,可扩展的,非常容易实现。此外,我们证明了在小噪声极限中分布产生的样品的条件一致性和紧密性(即,当采集时间趋于无穷大时)并导出必须使用MRI图像的新几何和必要条件。这种情况自然出现在错过的广义泊松模型的可识别性问题的背景下。我们还将我们的方法与贝叶斯马尔可夫链蒙特卡罗采样进行了鲜明对比,基于一个数据增强方案,这在宠物或SPECT的期望最大化算法中非常流行。我们理论上展示了这些数据增强显着增加了马尔可夫链的混合时间。鉴于此,我们的算法似乎在设计复杂性,可扩展性,数值负荷和不确定性评估之间提供合理的权衡。
translated by 谷歌翻译
Static subword tokenization algorithms have been an essential component of recent works on language modeling. However, their static nature results in important flaws that degrade the models' downstream performance and robustness. In this work, we propose MANTa, a Module for Adaptive Neural TokenizAtion. MANTa is a differentiable tokenizer trained end-to-end with the language model. The resulting system offers a trade-off between the expressiveness of byte-level models and the speed of models trained using subword tokenization. In addition, our tokenizer is highly explainable since it produces an explicit segmentation of sequences into blocks. We evaluate our pre-trained model on several English datasets from different domains as well as on synthetic noise. We find that MANTa improves robustness to character perturbations and out-of-domain data. We then show that MANTa performs comparably to other models on the general-domain GLUE benchmark. Finally, we show that it is considerably faster than strictly byte-level models.
translated by 谷歌翻译
本文介绍了在高斯过程回归/克里格替代建模技术中选择/设计内核的算法。我们在临时功能空间中采用内核方法解决方案的设置,即繁殖内核希尔伯特空间(RKHS),以解决在观察到它的观察值的情况下近似定期目标函数的问题,即监督学习。第一类算法是内核流,该算法是在机器学习中的分类中引入的。它可以看作是一个交叉验证过程,因此选择了“最佳”内核,从而最小化了通过删除数据集的某些部分(通常为一半)而产生的准确性损失。第二类算法称为光谱内核脊回归,旨在选择“最佳”核,以便在相关的RKHS中,要近似的函数的范围很小。在Mercer定理框架内,我们就目标函数的主要特征来获得该“最佳”内核的明确结构。从数据中学习内核的两种方法均通过有关合成测试功能的数值示例,以及在湍流建模验证二维机翼的湍流模型验证中的经典测试用例。
translated by 谷歌翻译
生成用户活动是评估安全监控工具的关键能力,以及提高攻击者分析平台的可信度(例如,蜜涅斯)。在本文中,为了产生此活动,我们通过外部代理仪器仪器。该代理结合了基于确定性和深度学习的方法,以适应不同的环境(例如,多个操作系统,软件版本等),同时保持高性能。我们还提出了有条件的文本生成模型,以方便创建对话和文档来加速相干,系统范围的生活场景的定义。
translated by 谷歌翻译
基于平铺,形状和图形运算符,通过其底层图描述了Ludii General Game系统的游戏板,自动检测图形元素,方向和径向序列之间的拓扑关系等重要属性。这种方法允许简单而简洁地描述最能实现的游戏板。
translated by 谷歌翻译
本文介绍了三种不同的播出优化实现,如Monte-Carlo树搜索等游戏播放算法常用。每个优化的实现都仅适用于根据其规则的特定游戏集。Ludii General游戏系统可以根据游戏的描述在其常规游戏描述语言中,是否适用任何优化的实现。经验评估展示了标准实施中的主要加速,其中运行播出的中位结果是快速的播出5.08倍,在Ludii中超过145个不同的游戏,其中一个优化的实现是适用的。
translated by 谷歌翻译
The standard semantics of multi-agent epistemic logic S5 is based on Kripke models whose accessibility relations are reflexive, symmetric and transitive. This one dimensional structure contains implicit higher-dimensional information beyond pairwise interactions, that we formalized as pure simplicial models in a previous work (Information and Computation, 2021). Here we extend the theory to encompass simplicial models that are not necessarily pure. The corresponding class of Kripke models are those where the accessibility relation is symmetric and transitive, but might not be reflexive. Such models correspond to the epistemic logic KB4 . Impure simplicial models arise in situations where two possible worlds may not have the same set of agents. We illustrate it with distributed computing examples of synchronous systems where processes may crash.
translated by 谷歌翻译
强化学习中的信用作业是衡量行动对未来奖励的影响的问题。特别是,这需要从运气中分离技能,即解除外部因素和随后的行动对奖励行动的影响。为实现这一目标,我们将来自因果关系的反事件的概念调整为无模型RL设置。关键思想是通过学习从轨迹中提取相关信息来应对未来事件的价值函数。我们制定了一系列政策梯度算法,这些算法使用这些未来条件的价值函数作为基准或批评,并表明它们是可怕的差异。为避免对未来信息的调理潜在偏见,我们将后视信息限制为不包含有关代理程序行为的信息。我们展示了我们对许多说明性和具有挑战性问题的算法的功效和有效性。
translated by 谷歌翻译
我们介绍并分析新的一阶优化算法系列,它概括并统一镜像血统和双平均。在该系列的框架内,我们定义了用于约束优化的新算法,这些算法结合了镜像血统和双平均的优点。我们的初步仿真研究表明,这些新算法在某些情况下显着优于可用方法。
translated by 谷歌翻译
In statistical relational learning, the link prediction problem is key to automatically understand the structure of large knowledge bases. As in previous studies, we propose to solve this problem through latent factorization. However, here we make use of complex valued embeddings. The composition of complex embeddings can handle a large variety of binary relations, among them symmetric and antisymmetric relations. Compared to state-of-the-art models such as Neural Tensor Network and Holographic Embeddings, our approach based on complex embeddings is arguably simpler, as it only uses the Hermitian dot product, the complex counterpart of the standard dot product between real vectors. Our approach is scalable to large datasets as it remains linear in both space and time, while consistently outperforming alternative approaches on standard link prediction benchmarks. 1
translated by 谷歌翻译