从几个培训示例中不断学习新课程,而不忘记以前的旧课程需要一个灵活的体系结构,而不可避免地会增加部分存储,其中可以逐步存储并有效地检索新的示例和类。一个可行的架构解决方案是将固定的深神经网络紧密融合到动态发展的明确记忆(EM)。作为该体系结构的核心,我们提出了一个EM单元,该单元在持续学习操作过程中利用节能中的内存计算(IMC)核心。我们首次证明了EM单元如何使用基于IMC Core上的操作(PCM)上的IMC核心操作,在推理期间进行了多个训练示例,扩展以适应看不见的类并进行相似性搜索。具体而言,通过PCM设备的原位进行性结晶实现了一些编码训练示例的物理叠加。与不断学习的最新完整精确基线软件模型相比,IMC核心上达到的分类精度在1.28% - 2.5%范围内保持在2.5%之内。在60个旧课程的顶部,新颖的课程(每班只有五个示例)。
translated by 谷歌翻译
We consider distributed learning in the presence of slow and unresponsive worker nodes, referred to as stragglers. In order to mitigate the effect of stragglers, gradient coding redundantly assigns partial computations to the worker such that the overall result can be recovered from only the non-straggling workers. Gradient codes are designed to tolerate a fixed number of stragglers. Since the number of stragglers in practice is random and unknown a priori, tolerating a fixed number of stragglers can yield a sub-optimal computation load and can result in higher latency. We propose a gradient coding scheme that can tolerate a flexible number of stragglers by carefully concatenating gradient codes for different straggler tolerance. By proper task scheduling and small additional signaling, our scheme adapts the computation load of the workers to the actual number of stragglers. We analyze the latency of our proposed scheme and show that it has a significantly lower latency than gradient codes.
translated by 谷歌翻译
The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.
translated by 谷歌翻译
To date, the comparison of Statistical Shape Models (SSMs) is often solely performance-based and carried out by means of simplistic metrics such as compactness, generalization, or specificity. Any similarities or differences between the actual shape spaces can neither be visualized nor quantified. In this paper, we present a first method to compare two SSMs in dense correspondence by computing approximate intersection spaces and set-theoretic differences between the affine vector spaces spanned by the models. To this end, we approximate the distribution of shapes lying in the intersection space using Markov Chain Monte Carlo, and then apply Principal Component Analysis (PCA) to its samples. By representing the resulting spaces again as an SSM, our method enables an easy and intuitive analysis of similarities between two model's shape spaces. We estimate differences between SSMs in a similar manner; here, however, the resulting shape spaces are not linear vector spaces anymore and we do not apply PCA but instead use the posterior samples for visualization. We showcase the proposed algorithm qualitatively by computing and analyzing intersection spaces and differences between publicly available face models focusing on gender-specific male and female as well as identity and expression models. Our quantitative evaluation based on SSMs built from synthetic and real-world data sets provides detailed evidence that the introduced method is able to recover ground-truth intersection spaces and differences. Finally, we demonstrate that the proposed algorithm can be easily adapted to also compute intersections and differences between color spaces.
translated by 谷歌翻译
Hololens(Microsoft Corp.,WA Redmond,WA)是一款头饰,光学透明的增强现实展示,是最近提高医学增强现实研究的主要参与者。在医疗环境中,HoloLens使医生能够立即了解患者信息,直接与他们对临床方案的看法,医学生,可以更好地了解复杂的解剖学或程序,甚至可以通过执行治疗任务。改进,沉浸式指导。在这篇系统的综述中,我们提供了有关医疗领域第一代霍洛伦斯在2016年3月发布到2021年的全面使用的全面概述,一直关注其继任者霍洛伦斯2号。通过系统搜索PubMed和Scopus数据库确定了171个相关出版物。我们分析了这些出版物的预期用例,注册和跟踪的技术方法,数据源,可视化以及验证和评估。我们发现,尽管已经显示出在各种医学场景中使用Hololens的可行性,但在精确,可靠性,可用性,工作流程和感知方面的努力增加了在临床实践中建立AR。
translated by 谷歌翻译
虚拟测试是确保自动驾驶安全性的至关重要的任务,而传感器仿真是该域中的重要任务。大多数当前的激光雷达模拟非常简单,主要用于执行初始测试,而大多数见解是在道路上收集的。在本文中,我们提出了一种轻巧的方法,以实现更现实的激光雷达模拟,该方法从测试驱动器数据中学习了真实传感器的行为,并将其转换为虚拟域。核心思想是将仿真施加到图像到图像翻译问题中。我们将基于PIX2PIX的架构训练两个现实世界数据集,即流行的Kitti数据集和提供RGB和LIDAR图像的Audi自动驾驶数据集。我们将该网络应用于合成渲染,并表明它从真实图像到模拟图像充分概括。该策略使我们可以在我们的合成世界中跳过传感器特异性,昂贵且复杂的LIDAR物理模拟,并避免过度简化和通过干净的合成环境较大的域间隙。
translated by 谷歌翻译
期刊影响因素(JIF)通常等同于期刊质量和提交给该期刊的论文的同行评审质量。我们通过分析提交给1,644家医学和生命科学期刊的10,000个同行评审报告,研究了同行评审与JIF的内容之间的关联。两名研究人员手工编码了2,000个句子的随机样本。然后,我们训练了机器学习模型,以将所有187,240个句子分类为贡献或不为内容类别做出贡献。我们研究了JIF DICILES定义的十组期刊与使用线性混合效应模型的同行评审的内容之间的关联,并调整了评论的长度。 JIF的范围为0.21至74.70。同行评审长度从最低(单词中位数185)增加到JIF组(387个单词)。分配给不同内容类别的句子的比例甚至在JIF组中也有很大变化。为了彻底,与最低的JIF组相比,关于“材料和方法”的句子在最高的JIF期刊中更为普遍(7.8个百分点; 95%CI 4.9至10.7%)。 “演示和报告”的趋势朝相反的方向发展,最高的JIF期刊对此类内容的重视程度较小(差异-8.9%; 95%CI -11.3至-6.5%)。为了有助于,对更高的JIF期刊的评论更少关注“建议和解决方案”,而提供的示例少于较低的影响因素期刊。对于其他内容类别而言,没有,或者只有很小的差异。总之,在讨论使用的方法时,在提出解决方案和提供示例方面,在讨论所使用的方法但较小的帮助时,较高的JIF期刊的同行评审往往更为透彻。差异是适度的,可变性很高,表明JIF是对单个手稿的同伴评论质量的不良预测指标。
translated by 谷歌翻译
科学出版物的产出成倍增长。因此,跟踪趋势和变化越来越具有挑战性。了解科学文档是下游任务的重要一步,例如知识图构建,文本挖掘和纪律分类。在这个研讨会中,我们从科学出版物的摘要中可以更好地理解关键字和键形酶提取。
translated by 谷歌翻译
数据已成为当今世界上最有价值的资源。随着数据驱动算法的大量扩散,例如基于深度学习的方法,数据的可用性引起了极大的兴趣。在这种情况下,特别需要高质量的培训,验证和测试数据集。体积数据是医学中非常重要的资源,因为它范围从疾病诊断到治疗监测。如果数据集足够,则可以培训模型来帮助医生完成这些任务。不幸的是,在某些情况和应用程序中,大量数据不可用。例如,在医疗领域,罕见疾病和隐私问题可能导致数据可用性受到限制。在非医学领域,获得足够数量的高质量数据的高成本也可能引起人们的关注。解决这些问题的方法可能是生成合成数据,以结合其他更传统的数据增强方法来执行数据增强。因此,关于3D生成对抗网络(GAN)的大多数出版物都在医疗领域内。生成现实合成数据的机制的存在是克服这一挑战的好资产,尤其是在医疗保健中,因为数据必须具有良好的质量并且接近现实,即现实,并且没有隐私问题。在这篇综述中,我们提供了使用GAN生成现实的3D合成数据的作品的摘要。因此,我们概述了具有共同体系结构,优势和缺点的这些领域中基于GAN的方法。我们提出了一种新颖的分类学,评估,挑战和研究机会,以提供医学和其他领域甘恩当前状态的整体概述。
translated by 谷歌翻译
通过填写数据集中的缺失值,插入允许这些数据集与无法自行处理缺失值的算法一起使用。但是,缺少的价值原则上可能会贡献通过插补而丢失的有用信息。缺失的指示方法可以与归档的结合使用,而是将此信息表示为数据集的一部分。有几个理论上的考虑因素为什么缺失指导者可能会或可能没有好处,但是在现实生活中没有任何大规模实践实验来测试此问题以进行机器学习预测。我们根据二十个现实生活数据集对三种归纳策略和一系列不同的分类算法进行此实验。我们发现,在这些数据集上,缺失指标通常会提高分类性能。此外,我们没有发现大多数算法的证据表明,最近的邻居和迭代插补比简单的平均/模式插补带来更好的性能。因此,我们建议使用具有平均/模式归档的缺失指标作为安全的默认值,需要将决策树用于防止过度拟合。在后续实验中,我们确定每个分类器的属性特异性缺失阈值,在该实验中,缺失指标更有可能增加分类性能,并观察到这些阈值的分类要比数值属性要低得多。最后,我们认为,数值属性的插补的平均值可能会保留一些信息中的某些信息,并且我们表明,在没有缺失的指示器的情况下,将平均插入量应用于单热编码的分类属性而不是,而不是有用模式插补。
translated by 谷歌翻译