Machine Learning for Source Code (ML4Code) is an active research field in which extensive experimentation is needed to discover how to best use source code's richly structured information. With this in mind, we introduce JEMMA, an Extensible Java Dataset for ML4Code Applications, which is a large-scale, diverse, and high-quality dataset targeted at ML4Code. Our goal with JEMMA is to lower the barrier to entry in ML4Code by providing the building blocks to experiment with source code models and tasks. JEMMA comes with a considerable amount of pre-processed information such as metadata, representations (e.g., code tokens, ASTs, graphs), and several properties (e.g., metrics, static analysis results) for 50,000 Java projects from the 50KC dataset, with over 1.2 million classes and over 8 million methods. JEMMA is also extensible allowing users to add new properties and representations to the dataset, and evaluate tasks on them. Thus, JEMMA becomes a workbench that researchers can use to experiment with novel representations and tasks operating on source code. To demonstrate the utility of the dataset, we also report results from two empirical studies on our data, ultimately showing that significant work lies ahead in the design of context-aware source code models that can reason over a broader network of source code entities in a software project, the very task that JEMMA is designed to help with.
translated by 谷歌翻译
The Codex model has demonstrated extraordinary competence in synthesizing code from natural language problem descriptions. However, in order to reveal unknown failure modes and hidden biases, such large-scale models must be systematically subjected to multiple and diverse evaluation studies. In this work, we evaluate the code synthesis capabilities of the Codex model based on a set of 115 Python problem statements from a popular competitive programming portal: HackerRank. Our evaluation shows that Codex is indeed proficient in Python, solving 96% of the problems in a zero-shot setting, and 100% of the problems in a few-shot setting. However, Codex exhibits clear signs of generating memorized code based on our evaluation. This is alarming, especially since the adoption and use of such models could directly impact how code is written and produced in the foreseeable future. With this in mind, we further discuss and highlight some of the prominent risks associated with large-scale models of source code. Finally, we propose a framework for code-synthesis evaluation using variations of problem statements based on mutations.
translated by 谷歌翻译
Coronary Computed Tomography Angiography (CCTA) provides information on the presence, extent, and severity of obstructive coronary artery disease. Large-scale clinical studies analyzing CCTA-derived metrics typically require ground-truth validation in the form of high-fidelity 3D intravascular imaging. However, manual rigid alignment of intravascular images to corresponding CCTA images is both time consuming and user-dependent. Moreover, intravascular modalities suffer from several non-rigid motion-induced distortions arising from distortions in the imaging catheter path. To address these issues, we here present a semi-automatic segmentation-based framework for both rigid and non-rigid matching of intravascular images to CCTA images. We formulate the problem in terms of finding the optimal \emph{virtual catheter path} that samples the CCTA data to recapitulate the coronary artery morphology found in the intravascular image. We validate our co-registration framework on a cohort of $n=40$ patients using bifurcation landmarks as ground truth for longitudinal and rotational registration. Our results indicate that our non-rigid registration significantly outperforms other co-registration approaches for luminal bifurcation alignment in both longitudinal (mean mismatch: 3.3 frames) and rotational directions (mean mismatch: 28.6 degrees). By providing a differentiable framework for automatic multi-modal intravascular data fusion, our developed co-registration modules significantly reduces the manual effort required to conduct large-scale multi-modal clinical studies while also providing a solid foundation for the development of machine learning-based co-registration approaches.
translated by 谷歌翻译
旨在进行巴氏杀菌和量化特定现象的任何方法都必须包括使用强大的统计方法进行数据分析。考虑到这一点,这项研究的目的是介绍非参数非均匀数据框架中可能采用的统计方法,并检查其在自然语言处理和语言集群领域的应用。此外,本文讨论了语言数据挖掘和处理中非参数方法的许多用途。数据深度思想允许在任何维度上进行中心排序,从而导致新的非参数多元统计分析,该分析不需要任何分布假设。层次结构的概念用于历史语言分类和结构化,其目的是使用相同的前提将语言组织和聚集到亚家族中。在这方面,当前的研究提出了一种基于通过各种语言的单词类型结构产生的非参数方法的语言家族结构的新方法,然后使用MDS将其转换为笛卡尔框架。这种基于统计深度的架构允许使用基于数据深度的方法来实现强大的离群检测,这对于理解各种边界语言的分类非常有用,并允许对现有分类系统进行重新评估。其他基于深度的方法也适用于无监督和监督聚类等过程。因此,本文概述了可以在非参数框架中应用于非均匀语言分类系统的过程。
translated by 谷歌翻译
小麦是全球主要的主食之一。因此,必须衡量,维护和改善人类消费的小麦质量。传统的小麦质量测量方法主要具有侵入性,破坏性,并且仅限于小麦样本。在典型的小麦供应链中,有许多接收点,散装小麦到来,根据要求将其存储和转发。在此接受点,传统质量测量方法的应用非常困难,而且通常非常昂贵。因此,需要非侵入性,无损的实时方法来进行小麦质量评估。满足上述标准的一种这样的方法是用于食品质量测量的高光谱成像(HSI),也可以应用于批量样品。在本文中,我们研究了如何在文献中使用HSI来评估储存的小麦质量。因此,可以在单个紧凑的文档中提供所需的信息,以在澳大利亚供应链的不同阶段实施实时数字质量评估方法。
translated by 谷歌翻译
具有基于块体系结构的运动建模已被广泛用于视频编码中,其中框架分为固定尺寸的块,这些块是独立补偿的。这通常会导致编码效率低下,因为固定尺寸的块几乎与对象边界不符。尽管已经引入了层次结构分区来解决这一问题,但运动矢量的增加限制了收益。最近,与立方体分配的图像的近似分割已经普及。可变大小的矩形片段(立方体)不仅容易适应基于块的图像/视频编码技术,而且还可以很好地与对象边界保持一致。这是因为立方分区基于同质性约束,从而最大程度地减少了平方误差的总和(SSE)。在本文中,我们研究了针对可扩展视频编码中使用的固定尺寸块的运动模型的潜力。具体而言,我们使用图片组(GOP)中的锚框的立方分区信息构建了运动补偿帧。然后,预测的当前帧已用作基础层,同时使用可扩展的HEVC编码器编码当前帧作为增强层。实验结果确认4K视频序列上节省了6.71%-10.90%的比特率。
translated by 谷歌翻译
在过去的几年中,几乎没有学习的领域取得了重大改进。这种学习范式已经显示出对挑战性检测的挑战性问题的令人鼓舞的结果,在这种情况下,一般任务是应对重型阶级失衡。我们的论文提出了一种新的方法来进行几次分类,我们采用了多种预训练的卷积模型的知识基础,这些卷积模型是我们提出的几杆框架的骨干。我们的框架使用一种新颖的结合技术来提高准确性,同时大大降低了总参数计数,从而为实时实现铺平了道路。我们使用电源线缺陷检测数据集执行广泛的超参数搜索,并获得5-way 5-Shot任务的精度为92.30%。在不进一步调整的情况下,我们使用现有的最先进方法评估我们的模型,并胜过它们。
translated by 谷歌翻译
人类在需要快速传达对象信息的游戏中显示出高级的抽象功能。他们将消息内容分解为多个部分,并以可解释的协议将它们传达。为了为机器提供这种功能,我们提出了基于原始的草图抽象任务,其目标是在预算影响下使用一组固定的绘图原始图表示草图。为了解决这项任务,我们的原始匹配网络(PMN)以自我监督的方式学习了草图的可解释抽象。具体而言,PMN将草图的每个笔划都映射到给定集中最相似的原始性,预测了仿射转换将所选原始词与目标冲程对齐的仿射转换。我们学习了端到端的这一笔触至关重要的映射,当原始草图精确地用预测的原语重建时,距离转换损失是最小的。我们的PMN抽象在经验上取得了素描识别和基于草图的图像检索的最高性能,同时也是高度可解释的。这为草图分析打开了新的可能性,例如通过提取定义对象类别的最相关的原始图来比较草图。代码可在https://github.com/explainableml/sketch-primitives上找到。
translated by 谷歌翻译
无人驾驶飞机(UAV)用作空中基础站,可将时间敏感的包装从物联网设备传递到附近的陆地底站(TBS)。在此类无人产用的物联网网络中安排数据包,以确保TBS在TBS上确保新鲜(或最新的)物联网设备的数据包是一个挑战性的问题,因为它涉及两个同时的步骤(i)(i)在IOT设备上生成的数据包的同时进行样本由UAVS [HOP-1]和(ii)将采样数据包从UAVS更新到TBS [Hop-2]。为了解决这个问题,我们建议针对两跳UAV相关的IoT网络的信息年龄(AOI)调度算法。首先,我们提出了一个低复杂的AOI调度程序,称为MAF-MAD,该计划使用UAV(HOP-1)和最大AOI差异(MAD)策略采样最大AOI(MAF)策略,以更新从无人机到TBS(Hop-2)。我们证明,MAF-MAD是理想条件下的最佳AOI调度程序(无线无线通道和在物联网设备上产生交通生成)。相反,对于一般条件(物联网设备的损失渠道条件和不同的周期性交通生成),提出了深厚的增强学习算法,即近端政策优化(PPO)基于调度程序。仿真结果表明,在所有考虑的一般情况下,建议的基于PPO的调度程序优于MAF-MAD,MAF和Round-Robin等其他调度程序。
translated by 谷歌翻译
尖峰神经网络的事件驱动性质使它们具有生物学上可符合的和比人工神经网络更节能。在这项工作中,我们展示了二维视野中对象的运动检测。这里呈现的网络架构是生物学卓越的,并使用CMOS模拟泄漏整合和灭火神经元和超低功耗多层RRAM突触。具体的跨晶体管纤维Spice模拟表明,所提出的结构可以在二维视野中准确可靠地检测物体的复杂运动。
translated by 谷歌翻译