我们介绍ARCHANGEL;一种新颖的分布式分类帐系统,用于确保数字视频档案的长期完整性。首先,我们描述了一种新的深度网络架构,用于计算持续时间为几分钟或几小时的视听流中的紧凑时间内容哈希(TCH)。我们的TCH对意外或恶意内容修改(篡改)敏感,但不适用于用于编码视频的编解码器。这是必要的,因为档案馆要求随着时间的推移格式化移动视频以确保无缝可访问性。其次,我们描述了TCH(以及用于驱动它们的模型)是如何通过分布在多个独立档案中的权威证明区块链来保护的。我们报告了ARCHANGEL在英国,爱沙尼亚和挪威的国家政府档案参与的试验部署背景下的功效。
translated by 谷歌翻译
信息融合是众多工程系统和生物功能的重要组成部分,例如人类认知。融合发生在许多层面,从信号的低级组合到异构决策过程的高级聚合。虽然过去十年见证了深度学习研究的爆发,但神经网络融合并没有观察到同样的革命。具体而言,大多数神经融合方法是特定的,不被理解,分布与局部,和/解释性低(如果存在的话)。在此,我们证明了模糊Choquet积分(ChI),一种强大的非线性聚合函数,可以表示为多层网络,以下称为ChIMP。我们还提出了一种改进的ChIMP(iChIMP),它根据ChI不等式约束的指数数量导致基于随机梯度下降的优化。 ChIMP / iChIMP的另一个好处是它可以实现可解释的AI(XAI)。提供了综合验证实验,并将iChIMP应用于远程感知中的一组异构架构深度模型的融合。我们展示了模型精度的提高,我们之前建立的XAI指数揭示了我们的数据,模型及其决策的质量。
translated by 谷歌翻译
用于编写,编译和优化深度学习(DL)模型的框架最近在计算机视觉和自然语言处理等领域取得了进展。扩展这些框架以适应DL模型和硬件平台的快速多样化环境,在表现力,可组合性和可移植性之间提出了挑战性的挑战。我们提出了一个新的中间表示(IR)和DLmodels的编译框架。功能性,静态类型的中继IR统一并概括了DL IR,并且可以表达最先进的模型。 Relay的表达IR需要仔细设计类型系统,自动区分和优化。 Relay的可扩展编译器可以消除抽象开销并瞄准新的硬件平台。来自Relay的设计见解可以应用于现有框架,以开发支持扩展的IR,而不会影响表现力,可组合性和可移植性。我们的评估证明,继电器原型已经可以为运行在CPU,GPU和FPGA上的各类模型提供竞争性能。
translated by 谷歌翻译
最近的研究表明,视觉语境改善了名词的跨语言感知。我们将这一系列工作扩展到更具挑战性的跨语言动词消歧歧义,介绍了用英语,德语和西班牙语动词注释的9,504张图像的MultiSensedataset。 MultiSense中的每个图像都标有英文动词及其在德语或西班牙语中的翻译。我们表明,与单峰基线相比,跨语言动词感消歧模型可以从视觉上下文中获益。我们还表明,当用于多模式翻译任务时,我们最好的消歧模型预测的动词感可以改善纯文本机器翻译系统的结果。
translated by 谷歌翻译
Commonsense reasoning is a critical AI capability , but it is difficult to construct challenging datasets that test common sense. Recent neu-ral question answering systems, based on large pre-trained models of language, have already achieved near-human-level performance on commonsense knowledge benchmarks. These systems do not possess human-level common sense, but are able to exploit limitations of the datasets to achieve human-level scores. We introduce the CODAH dataset, an adversarially-constructed evaluation dataset for testing common sense. CODAH forms a challenging extension to the recently-proposed SWAG dataset, which tests commonsense knowledge using sentence-completion questions that describe situations observed in video. To produce a more difficult dataset, we introduce a novel procedure for question acquisition in which workers author questions designed to target weaknesses of state-of-the-art neural question answering systems. Workers are rewarded for submissions that models fail to answer correctly both before and after fine-tuning (in cross-validation). We create 2.8k questions via this procedure and evaluate the performance of multiple state-of-the-art question answering systems on our dataset. We observe a significant gap between human performance, which is 95.3%, and the performance of the best baseline accuracy of 65.3% by the OpenAI GPT model.
translated by 谷歌翻译
In many research fields, the sizes of the existing datasets vary widely. Hence, there is a need for machine learning techniques which are well-suited for these different datasets. One possible technique is the self-organizing map (SOM), a type of artificial neural network which is, so far, weakly represented in the field of machine learning. The SOM's unique characteristic is the neighborhood relationship of the output neurons. This relationship improves the ability of generalization on small datasets. SOMs are mostly applied in unsupervised learning and few studies focus on using SOMs as supervised learning approach. Furthermore, no appropriate SOM package is available with respect to machine learning standards and in the widely used programming language Python. In this paper, we introduce the freely available SUpervised Self-organIzing maps (SUSI) Python package which performs supervised regression and classification. The implementation of SUSI is described with respect to the underlying mathematics. Then, we present first evaluations of the SOM for regression and classification datasets from two different domains of geospatial image analysis. Despite the early stage of its development, the SUSI framework performs well and is characterized by only small performance differences between the training and the test datasets. A comparison of the SUSI framework with existing Python and R packages demonstrates the importance of the SUSI framework. In future work, the SUSI framework will be extended, optimized and upgraded e.g. with tools to better understand and visualize the input data as well as the handling of missing and incomplete data.
translated by 谷歌翻译
快照镶嵌多光谱图像通过获取每个空间像素的单个光谱测量来获取欠采样数据立方体。因此,传感器需要$ p $频率,对完整数据立方体进行严重的$ 1 / p $欠采样。我们表明,使用来自稀疏近似的非凸技术和使用传统去马赛克算法初始化的矩阵完成,可以准确地插入缺失的条目。特别地,我们观察到峰值信噪比通常可以通过2到5 dB过流现有技术方法在模拟$ p = 16 $马赛克传感器时进行测量,该传感器测量高低层城市和乡村场景基于场景的场景。
translated by 谷歌翻译
The ability to obtain accurate food security metrics in developing areas where relevant data can be sparse is critically important for policy makers tasked with implementing food aid programs. As a result, a great deal of work has been dedicated to predicting important food security metrics such as annual crop yields using a variety of methods including simulation, remote sensing, weather models, and human expert input. As a complement to existing techniques in crop yield prediction, this work develops neural network models for predicting the the sentiment of Twitter feeds from farming communities. Specifically, we investigate the potential of both direct learning on a small dataset of agriculturally-relevant tweets and transfer learning from larger, well-labeled sentiment datasets from other domains (e.g. politics) to accurately predict agricultural sentiment, which we hope would ultimately serve as a useful crop yield predictor. We find that direct learning from small, relevant datasets outperforms transfer learning from large, fully-labeled datasets, that convolutional neural networks broadly outperform recurrent neural networks on Twitter sentiment classification, and that these models perform substantially less well on ternary sentiment problems characteristic of practical settings than on binary problems often found in the literature.
translated by 谷歌翻译
获取描述当地粮食安全指标(FSM)的可靠数据,这些数据对政策制定者提供信息,需要进行昂贵且难以进行的调查,特别是在发展中国家。我们在公共可用的卫星数据上描述土地覆盖分类,并使用转移学习和直接训练来建立纯粹来自卫星图像数据的FSM预测模型。然后,我们通过传递学习,马尔可夫搜索算法和贝叶斯网络为高分辨率卫星资产提出有效的任务算法。
translated by 谷歌翻译
下一代嵌入式信息和通信技术(ICT)系统是能够执行自主任务的互联协作智能系统。在Edge设备上培训和部署此类系统无论如何都需要对数据和工具进行细粒度的集成,以实现高精度并克服功能和非功能需求。在这项工作中,我们提出了一个模块化AI管道作为集成框架,将数据,算法和部署工具结合在一起。通过这些方式,我们能够连接特定系统的不同实体或阶段,并提供AI产品的端到端开发。我们通过解决自动语音识别挑战来证明AI管道的有效性,并且说明了导致Key-wordSpotting任务的端到端开发的所有步骤:语音数据的导入,分区和预处理,不同神经元的训练网络架构及其在异构嵌入式平台上的部署。
translated by 谷歌翻译