The task of automatic text summarization produces a concise and fluent text summary while preserving key information and overall meaning. Recent approaches to document-level summarization have seen significant improvements in recent years by using models based on the Transformer architecture. However, the quadratic memory and time complexities with respect to the sequence length make them very expensive to use, especially with long sequences, as required by document-level summarization. Our work addresses the problem of document-level summarization by studying how efficient Transformer techniques can be used to improve the automatic summarization of very long texts. In particular, we will use the arXiv dataset, consisting of several scientific papers and the corresponding abstracts, as baselines for this work. Then, we propose a novel retrieval-enhanced approach based on the architecture which reduces the cost of generating a summary of the entire document by processing smaller chunks. The results were below the baselines but suggest a more efficient memory a consumption and truthfulness.
translated by 谷歌翻译
命令和控制（C2）通信是任何结构化网络攻击的关键组成部分。因此，安全操作积极尝试检测其网络中的这种通信。这为合法的申请人构成了一个问题，这些问题试图保持未被发现，因为通常使用的pentesting工具（例如Metasploit）生成了恒定的流量模式，这些流量模式易于与常规的网络流量区分开。在本文中，我们从Metasploit的C2流量中的这些可识别的模式开始，并表明基于机器学习的检测器即使加密也能够以很高的精度检测到这种流量的存在。然后，我们概述并对元跨框架进行了一组修改，以降低该分类器的检测率。为了评估这些修改的性能，我们使用两个威胁模型，对这些修改的认识越来越多。我们查看逃避性能以及修改的字节数和运行时开销。我们的结果表明，在第二个增强的意识威胁模型中，框架侧交通修改比仅有效载荷侧的修改（50％）获得更好的检测回避率（90％）。我们还表明，尽管修改使用的TLS有效载荷比原始时间高3倍，但运行时没有显着更改，并且字节总数（包括TLS有效载荷）减少。
translated by 谷歌翻译
本文涉及一种特殊的认知失明味，称为c-causal失明或C-CB。获得目标的政策导致避免国家的政策。C -CB的一个字面例子是Kurt G \“ Odel决定“害怕被毒死”饿死 - 以此为前提A.目标是“避免被毒死（为了不死）”：C，计划或政策是“不吃东西”：B，而实际结果是“死去的”：不是C- G \“ Odel想要避免开始的状态。像许多人一样，g \” Odel采取了一种导致他想避免的结果的策略。提出了一个实验计算框架，以显示使用隐藏的Markov模型在大脑计算，逻辑和计算机计算中C-CB之间的同构关系。
translated by 谷歌翻译
几次学习的元学习算法旨在训练能够仅使用几个示例将新任务概括为新任务的神经网络。早期停滞对于性能至关重要，在对新任务分布达到最佳概括时停止模型训练。元学习的早期机制通常依赖于从训练（源）数据集中绘制的元验证集中的标记示例上测量模型性能。这在几个射击传输学习设置中是有问题的，其中元测试集来自不同的目标数据集（OOD），并且可能会在元验证集中具有较大的分配转移。在这项工作中，我们提出了基于激活的早期停滞（ABE），这是使用基于验证的早期播放进行元学习的替代方法。具体而言，我们分析了每个隐藏层的神经激活期间的演变，在目标任务分布的一项任务中，在一组未标记的支持示例上，因为这构成了从最小值和合理的信息中。目标问题。我们的实验表明，有关激活的简单标签不可知统计提供了一种有效的方法来估计目标概括如何随着时间的推移如何发展。在每个隐藏层，我们从第一阶和二阶矩来表征激活分布，然后沿特征维度进一步汇总，从而在四维空间中产生紧凑而直观的表征。检测何时，在整个训练时间以及在哪个层上，目标激活轨迹与源数据的激活轨迹有所不同，使我们能够在大量的几个射击传输学习设置中执行早期停滞并改善概括，并在不同算法，源和目标数据集。
translated by 谷歌翻译
我们证明了Yolov5模型（一种基于通用卷积的单杆对象检测模型）的应用，在从当前生成干涉仪检测器的重力数据中检测到二进制中子星（BNS）聚合事件的任务。我们还基于用于模型训练，验证和测试步骤的大概波形模型对合成数据生成和准备任务的详尽说明。使用这种方法，我们实现平均平均精度（$ \ text {map} _ {[0.50]} $）的单个类验证数据集的值为0.945，测试数据集的平均值为0.945，高达0.978。此外，训练有素的模型成功地识别了LIGO H1检测器数据中的GW170817事件。 LIGO L1检测器数据也可以通过附加的预处理步骤进行识别，而无需在Inspiral的最后阶段消除大故障。 GW190425事件的检测不太成功，这证明了信噪比的性能退化。我们的研究表明，Yolov5模型是第一阶段检测警报管道的有趣方法，并且在整合到更复杂的管道中时，用于实时推断物理源参数。
translated by 谷歌翻译
It would be useful for machines to use computers as humans do so that they can aid us in everyday tasks. This is a setting in which there is also the potential to leverage large-scale expert demonstrations and human judgements of interactive behaviour, which are two ingredients that have driven much recent success in AI. Here we investigate the setting of computer control using keyboard and mouse, with goals specified via natural language. Instead of focusing on hand-designed curricula and specialized action spaces, we focus on developing a scalable method centered on reinforcement learning combined with behavioural priors informed by actual human-computer interactions. We achieve state-of-the-art and human-level mean performance across all tasks within the MiniWob++ benchmark, a challenging suite of computer control problems, and find strong evidence of cross-task transfer. These results demonstrate the usefulness of a unified human-agent interface when training machines to use computers. Altogether our results suggest a formula for achieving competency beyond MiniWob++ and towards controlling computers, in general, as a human would.
translated by 谷歌翻译
Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn. In this paper we describe how to use Relation Networks (RNs) as a simple plug-and-play module to solve problems that fundamentally hinge on relational reasoning. We tested RN-augmented networks on three tasks: visual question answering using a challenging dataset called CLEVR, on which we achieve state-of-the-art, super-human performance; text-based question answering using the bAbI suite of tasks; and complex reasoning about dynamic physical systems. Then, using a curated dataset called Sort-of-CLEVR we show that powerful convolutional networks do not have a general capacity to solve relational questions, but can gain this capacity when augmented with RNs. Our work shows how a deep learning architecture equipped with an RN module can implicitly discover and learn to reason about entities and their relations.
translated by 谷歌翻译