注释数据是应用监督机器学习方法的要求，注释的质量对于结果至关重要。尤其是在处理不确定性多种多样的文化遗产藏品时，注释数据仍然是一项手动，艰巨的任务，由域专家执行。我们的项目始于两套已经注释的中世纪手稿图像，但是基于学术和语言差异，这些图像并不完整，并包含冲突的元数据。我们的目的是为组合数据集创建（1）一组统一的描述性标签，以及（2）对高质量的分层分类，可以用作监督机器学习的有价值的输入。为了实现这些目标，我们开发了一个视觉分析系统，以使中世纪主义者能够合并，正规化和扩展用于描述这些数据集的词汇。单词和图像嵌入的视觉接口以及数据集的注释的共发生，同时允许注释多个图像，建议注释标签候选者并支持组成标签的层次分类。我们的系统本身实现了一种半监督的方法，因为它根据中世纪主义者的反馈更新视觉表示，并且一系列用法场景记录了其对目标社区的价值。
translated by 谷歌翻译
The recent increase in public and academic interest in preserving biodiversity has led to the growth of the field of conservation technology. This field involves designing and constructing tools that utilize technology to aid in the conservation of wildlife. In this article, we will use case studies to demonstrate the importance of designing conservation tools with human-wildlife interaction in mind and provide a framework for creating successful tools. These case studies include a range of complexities, from simple cat collars to machine learning and game theory methodologies. Our goal is to introduce and inform current and future researchers in the field of conservation technology and provide references for educating the next generation of conservation technologists. Conservation technology not only has the potential to benefit biodiversity but also has broader impacts on fields such as sustainability and environmental protection. By using innovative technologies to address conservation challenges, we can find more effective and efficient solutions to protect and preserve our planet's resources.
translated by 谷歌翻译
We test grip strength and shock absorption properties of various granular material in granular jamming robotic components. The granular material comprises a range of natural, manufactured, and 3D printed material encompassing a wide range of shapes, sizes, and Shore hardness. Two main experiments are considered, both representing compelling use cases for granular jamming in soft robotics. The first experiment measures grip strength (retention force measured in Newtons) when we fill a latex balloon with the chosen grain type and use it as a granular jamming gripper to pick up a range of test objects. The second experiment measures shock absorption properties recorded by an Inertial Measurement Unit which is suspended in an envelope of granular material and dropped from a set height. Our results highlight a range of shape, size and softness effects, including that grain deformability is a key determinant of grip strength, and interestingly, that larger grain sizes in 3D printed grains create better shock absorbing materials.
translated by 谷歌翻译
Fruit harvesting has recently experienced a shift towards soft grippers that possess compliance, adaptability, and delicacy. In this context, pneumatic grippers are popular, due to provision of high deformability and compliance, however they typically possess limited grip strength. Jamming possesses strong grip capability, however has limited deformability and often requires the object to be pushed onto a surface to attain a grip. This paper describes a hybrid gripper combining pneumatics (for deformation) and jamming (for grip strength). Our gripper utilises a torus (donut) structure with two chambers controlled by pneumatic and vacuum pressure respectively, to conform around a target object. The gripper displays good adaptability, exploiting pneumatics to mould to the shape of the target object where jamming can be successfully harnessed to grip. The main contribution of the paper is design, fabrication, and characterisation of the first hybrid gripper that can use granular jamming in free space, achieving significantly larger retention forces compared to pure pneumatics. We test our gripper on a range of different sizes and shapes, as well as picking a broad range of real fruit.
translated by 谷歌翻译
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.
translated by 谷歌翻译
从同一场景的单个或多个低分辨率图像中获取高分辨率图像的过程对于现实世界图像和信号处理应用非常感兴趣。这项研究是关于探索基于深度学习的图像超分辨率算法的潜在用法，用于为驾驶汽车内车辆驾驶员监测系统产生高质量的热成像结果。在这项工作中，我们提出并开发了一种新型的多图像超分辨率复发性神经网络，以增强分辨率并提高从未冷却的热摄像机捕获的低分辨率热成像数据的质量。端到端完全卷积神经网络在室内环境条件下从刮擦上训练了30个不同受试者的新获得的热数据。热调谐超分辨率网络的有效性已定量验证，以及在6个不同受试者的测试数据上进行定性验证。该网络能够在验证数据集上达到4倍超分辨率的平均峰信号与噪声比为39.24，在定量和质量上都超过了双色插值。
translated by 谷歌翻译
在本文中，我们将预处理技术应用于具有不同长度的多通道时间序列数据，我们称之为对齐问题，用于下游机器学习。多种原因可能发生多种渠道时间序列数据的未对准，原因有多种原因，例如丢失的数据，变化的采样率或不一致的收集时间。我们考虑从MIT SuperCloud高性能计算（HPC）中心收集的多渠道时间序列数据，其中不同的工作开始时间和HPC作业的运行时间不同，导致数据不对准。这种未对准使得为计算工作负载分类等任务构建AI/ML方法具有挑战性。在先前使用MIT SuperCloud数据集的监督分类工作的基础上，我们通过三种宽阔的低间接空间方法解决了对齐问题：从全职系列中抽样固定子集，在全职系列上执行摘要统计信息，并对系数进行取样。从映射到频域的时间序列。我们最佳性能模型的分类精度大于95％，以先前的方法对MIT SuperCloud数据集的多通道时间序列分类的表现优于5％。这些结果表明，我们的低间接费用方法与标准机器学习技术结合使用，能够达到高水平的分类准确性，并作为解决对齐问题（例如内核方法）的未来方法的基准。
translated by 谷歌翻译
近年来，深度学习（DL）方法的流行程度急剧增加，并且在生物医学科学中的监督学习问题中的应用显着增长。但是，现代生物医学数据集中缺失数据的较高流行率和复杂性对DL方法提出了重大挑战。在这里，我们在深入学习的广义线性模型的背景下，对缺失数据进行了正式处理，这是一种监督的DL架构，用于回归和分类问题。我们提出了一种新的体系结构，即\ textit {dlglm}，这是第一个能够在训练时在输入功能和响应中灵活地说明忽略和不可忽视的缺失模式之一。我们通过统计模拟证明，我们的方法在没有随机（MNAR）缺失的情况下胜过现有的监督学习任务方法。我们从UCI机器学习存储库中对银行营销数据集进行了案例研究，在该数据集中我们预测客户是否基于电话调查数据订阅了产品。
translated by 谷歌翻译
尽管基于深度学习的语音增强系统在提高语音信号的质量方面取得了迅速的进步，但它们仍然可以产生包含伪像且听起来不自然的输出。我们提出了一种新颖的语音增强方法，旨在通过优化言语的关键特征来提高增强信号的知觉质量和自然性。我们首先确定与语音质量良好相关的关键声学参数（例如抖动，微光和光谱通量），然后提出目标函数，旨在减少相对于这些功能的清洁语音和增强语音之间的差异。完整的声学特征是扩展的Geneva声学参数集（EGEMAPS），其中包括与语音感知相关的25种不同属性。考虑到这些功能计算的非差异性质，我们首先构建了EGEMAP的可区分估计器，然后使用它们来微调现有的语音增强系统。我们的方法是通用的，可以应用于任何现有的基于深度学习的增强系统，以进一步改善增强的语音信号。对深噪声抑制（DNS）挑战数据集进行的实验结果表明，我们的方法可以改善最新的基于深度学习的增强系统。
translated by 谷歌翻译
了解公众关于紧急使用未经证实的治疗剂的论述对于监视安全使用和打击错误信息至关重要。我们开发了一种基于自然语言处理（NLP）的管道，以了解公众对COVID-19与19与COVID相关药物的立场的看法。这项回顾性研究包括2020年1月29日，2020年至2021年11月30日之间的609,189个基于美国的推文，涉及四种药物，这些药物在19日期期间在流行期间引起了广泛关注：1）羟基氯喹和伊维菌素，毒品疗法，具有轶事证据； 2）Molnupiravir和Remdesivir，适合合格患者的FDA批准的治疗选择。时间趋势分析用于了解受欢迎程度和相关事件。进行了内容和人口统计分析，以探讨人们对每种药物的立场的潜在理由。时间趋势分析表明，羟氯喹和伊维菌素的讨论比Molnupiravir和Remdesivir更多，尤其是在Covid-19-19潮中期。羟氯喹和伊维菌素高度政治化，与阴谋论，传闻，名人效应等有关。美国两个主要政党之间立场的分布大不相同（p <0.001）；共和党人比民主党人更有可能支持羟氯喹（+55％）和伊维菌素（+30％）。具有医疗保健背景的人倾向于比普通人群多反对羟氯喹（+7％）。相比之下，普通人群更有可能支持伊维菌素（+14％）。我们在https://github.com/ningkko/covid-drug上提供所有数据，代码和模型。
translated by 谷歌翻译