Optical coherence tomography (OCT) captures cross-sectional data and is used for the screening, monitoring, and treatment planning of retinal diseases. Technological developments to increase the speed of acquisition often results in systems with a narrower spectral bandwidth, and hence a lower axial resolution. Traditionally, image-processing-based techniques have been utilized to reconstruct subsampled OCT data and more recently, deep-learning-based methods have been explored. In this study, we simulate reduced axial scan (A-scan) resolution by Gaussian windowing in the spectral domain and investigate the use of a learning-based approach for image feature reconstruction. In anticipation of the reduced resolution that accompanies wide-field OCT systems, we build upon super-resolution techniques to explore methods to better aid clinicians in their decision-making to improve patient outcomes, by reconstructing lost features using a pixel-to-pixel approach with an altered super-resolution generative adversarial network (SRGAN) architecture.
translated by 谷歌翻译
光学相干断层扫描(OCT)是一种非侵入性技术,可在微米分辨率中捕获视网膜的横截面区域。它已被广泛用作辅助成像参考,以检测与眼睛有关的病理学并预测疾病特征的纵向进展。视网膜层分割是至关重要的特征提取技术之一,其中视网膜层厚度的变化和由于液体的存在而引起的视网膜层变形高度相关,与多种流行性眼部疾病(如糖尿病性视网膜病)和年龄相关的黄斑疾病高度相关。变性(AMD)。但是,这些图像是从具有不同强度分布或换句话说的不同设备中获取的,属于不同的成像域。本文提出了一种分割引导的域适应方法,以将来自多个设备的图像调整为单个图像域,其中可用的最先进的预训练模型可用。它避免了即将推出的新数据集的手动标签的时间消耗以及现有网络的重新培训。网络的语义一致性和全球特征一致性将最大程度地减少许多研究人员报告的幻觉效果,这些效应对周期矛盾的生成对抗网络(Cyclegan)体系结构。
translated by 谷歌翻译
语言模型既展示了定量的改进,又展示了新的定性功能,随着规模的增加。尽管它们具有潜在的变革性影响,但这些新能力的特征却很差。为了为未来的研究提供信息,为破坏性的新模型能力做准备,并改善社会有害的效果,至关重要的是,我们必须了解目前和近乎未来的能力和语言模型的局限性。为了应对这一挑战,我们介绍了超越模仿游戏基准(Big Bench)。 Big Bench目前由204个任务组成,由132家机构的442位作者贡献。任务主题是多样的,从语言学,儿童发展,数学,常识性推理,生物学,物理学,社会偏见,软件开发等等。 Big-Bench专注于被认为超出当前语言模型的功能的任务。我们评估了OpenAI的GPT型号,Google内部密集变压器体系结构和大型基础上的开关稀疏变压器的行为,跨越了数百万到数十亿个参数。此外,一个人类专家评估者团队执行了所有任务,以提供强大的基准。研究结果包括:模型性能和校准都随规模改善,但绝对的术语(以及与评估者的性能相比);在模型类中的性能非常相似,尽管带有稀疏性。逐渐和预测的任务通常涉及大量知识或记忆成分,而在临界规模上表现出“突破性”行为的任务通常涉及多个步骤或组成部分或脆性指标;社交偏见通常会随着含糊不清的环境而随着规模而增加,但这可以通过提示来改善。
translated by 谷歌翻译
Many current approaches to machine learning in particle physics use generic architectures that require large numbers of parameters and disregard underlying physics principles, limiting their applicability as scientific modeling tools. In this work, we present a machine learning architecture that uses a set of inputs maximally reduced with respect to the full 6-dimensional Lorentz symmetry, and is fully permutation-equivariant throughout. We study the application of this network architecture to the standard task of top quark tagging and show that the resulting network outperforms all existing competitors despite much lower model complexity. In addition, we present a Lorentz-covariant variant of the same network applied to a 4-momentum regression task.
translated by 谷歌翻译
旋转和姿势在许多科学和工程领域中无处不在,例如机器人技术,航空航天,计算机视觉和图形。在本文中,我们根据其矩阵谎言组表示的特征结构提供了旋转和姿势的完整表征,SO(3),SE(3)和AD(SE(SE(3)))。姿势表示的特征成分表明,它们可以被施放成与旋转非常相似的形式,尽管前者的结构可能会根据所涉及的翻译和旋转的相对性质而变化。理解这些重要数量的特征结构本身就是值得的,但是要欣赏诸如旋转和姿势以及雅各布人的计算之类的实际结果也至关重要。此外,我们可以说,主轴的姿势与主轴轮换的方式几乎相同。
translated by 谷歌翻译
The potential for complex systems to exhibit tipping points in which an equilibrium state undergoes a sudden and often irreversible shift is well established, but prediction of these events using standard forecast modeling techniques is quite difficult. This has led to the development of an alternative suite of methods that seek to identify signatures of critical phenomena in data, which are expected to occur in advance of many classes of dynamical bifurcation. Crucially, the manifestations of these critical phenomena are generic across a variety of systems, meaning that data-intensive deep learning methods can be trained on (abundant) synthetic data and plausibly prove effective when transferred to (more limited) empirical data sets. This paper provides a proof of concept for this approach as applied to lattice phase transitions: a deep neural network trained exclusively on 2D Ising model phase transitions is tested on a number of real and simulated climate systems with considerable success. Its accuracy frequently surpasses that of conventional statistical indicators, with performance shown to be consistently improved by the inclusion of spatial indicators. Tools such as this may offer valuable insight into climate tipping events, as remote sensing measurements provide increasingly abundant data on complex geospatially-resolved Earth systems.
translated by 谷歌翻译
数据增强是自然语言处理(NLP)模型的鲁棒性评估的重要组成部分,以及增强他们培训的数据的多样性。在本文中,我们呈现NL-Cogmenter,这是一种新的参与式Python的自然语言增强框架,它支持创建两个转换(对数据的修改)和过滤器(根据特定功能的数据拆分)。我们描述了框架和初始的117个变换和23个过滤器,用于各种自然语言任务。我们通过使用其几个转换来分析流行自然语言模型的鲁棒性来证明NL-Upmenter的功效。基础架构,Datacards和稳健性分析结果在NL-Augmenter存储库上公开可用(\ url {https://github.com/gem-benchmark/nl-augmenter})。
translated by 谷歌翻译
机器人和计算机视觉问题通常需要处理包括翻译和旋转的刚体运动 - 一起被称为姿势。在一些情况下,姿势的矢量参数化可以是有用的,其中向矩阵Lie组进行外钟映射矢量空间的元素。例如,这些向量表示可以用于优化以及对组的不确定性表示。最常见的映射是矩阵指数,其将Lie代数的元素映射到相关Lie组上。但是,这种选择并不唯一。它以前已经显示了如何表征SO(3),旋转组的所有此类矢量参数化。一些结果也是已知的,其中姿势组也是可以构建包括矩阵指数的映射系列以及凯利转化的系列。我们将这些姿势映射所熟知的众所周知的是在机器人中的4×4表示中,并且还演示了所提出的姿势映射的三个不同示例:(i)姿势插值,(ii)姿势伺服控制,(iii)姿势估计在一个Portcloud对齐问题中。在PointCloud对准问题中,我们的结果导致了一种基于Cayley转换的新算法,我们称之为Cayper。
translated by 谷歌翻译
变分贝叶斯推断是一个重要的机器学习工具,可从统计数据中找到应用到机器人技术。目的是从所选家族中找到一个近似概率密度函数(PDF),从某种意义上说,它最接近贝叶斯后部。接近度通常是通过选择适当的损失功能(例如Kullback-Leibler(KL)差异)来定义的。在本文中,我们通过利用(大多数)PDF是贝叶斯希尔伯特空间的成员,在仔细定义矢量添加,标量乘法和内部产品的情况下,探讨了变异推断的新表述。我们表明,在适当的条件下,基于KL差异的变异推断可以等于迭代性投影,从欧几里得意义上讲,贝叶斯后部到对应于所选近似族的子空间上。我们通过此通用框架的细节为高斯近似家族的特定情况进行了努力,并显示了与另一种高斯变异推理方法的等效性。此外,我们讨论了表现出稀疏性的系统的含义,该系统在贝叶斯空间中自然处理,并给出了一个高维机器人状态估计问题的示例,因此可以解决。我们提供了一些初步示例,说明如何将方法应用于非高斯推论,并详细讨论该方法的局限性,以鼓励沿着这些路线进行跟进。
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