日常生活的活动措施(ADL)是整体健康状况的重要指标,但难以测量诊所。使用手腕磨损的加速度计自动和准确的人类活动识别(HAR)可以实现ADL的实用和成本高效的远程监控。开发高质量Har中的关键障碍是缺乏大型标记的数据集和在将小型策级数据集培训的模型应用于现实生活中的不均匀数据的连续流时缺乏大型标记数据集和性能损失。在这项工作中,我们设计了一个自我监督的学习范例,以创建可以跨设备和主题概括的加速度计数据的强大表示。我们展示了这种代表可以使用很少的标签分离日常生活活动并实现强大的RAR准确性(在多个基准数据集上)。我们还提出了一种分割算法,可以识别突出活动的段,并在连续的现实生活数据上升高掌握。
translated by 谷歌翻译
Learning enabled autonomous systems provide increased capabilities compared to traditional systems. However, the complexity of and probabilistic nature in the underlying methods enabling such capabilities present challenges for current systems engineering processes for assurance, and test, evaluation, verification, and validation (TEVV). This paper provides a preliminary attempt to map recently developed technical approaches in the assurance and TEVV of learning enabled autonomous systems (LEAS) literature to a traditional systems engineering v-model. This mapping categorizes such techniques into three main approaches: development, acquisition, and sustainment. We review the latest techniques to develop safe, reliable, and resilient learning enabled autonomous systems, without recommending radical and impractical changes to existing systems engineering processes. By performing this mapping, we seek to assist acquisition professionals by (i) informing comprehensive test and evaluation planning, and (ii) objectively communicating risk to leaders.
translated by 谷歌翻译
Detecting actions in untrimmed videos should not be limited to a small, closed set of classes. We present a simple, yet effective strategy for open-vocabulary temporal action detection utilizing pretrained image-text co-embeddings. Despite being trained on static images rather than videos, we show that image-text co-embeddings enable openvocabulary performance competitive with fully-supervised models. We show that the performance can be further improved by ensembling the image-text features with features encoding local motion, like optical flow based features, or other modalities, like audio. In addition, we propose a more reasonable open-vocabulary evaluation setting for the ActivityNet data set, where the category splits are based on similarity rather than random assignment.
translated by 谷歌翻译
State-of-the-art image and text classification models, such as Convectional Neural Networks and Transformers, have long been able to classify their respective unimodal reasoning satisfactorily with accuracy close to or exceeding human accuracy. However, images embedded with text, such as hateful memes, are hard to classify using unimodal reasoning when difficult examples, such as benign confounders, are incorporated into the data set. We attempt to generate more labeled memes in addition to the Hateful Memes data set from Facebook AI, based on the framework of a winning team from the Hateful Meme Challenge. To increase the number of labeled memes, we explore semi-supervised learning using pseudo-labels for newly introduced, unlabeled memes gathered from the Memotion Dataset 7K. We find that the semi-supervised learning task on unlabeled data required human intervention and filtering and that adding a limited amount of new data yields no extra classification performance.
translated by 谷歌翻译
Proximal Policy Optimization (PPO) is a highly popular policy-based deep reinforcement learning (DRL) approach. However, we observe that the homogeneous exploration process in PPO could cause an unexpected stability issue in the training phase. To address this issue, we propose PPO-UE, a PPO variant equipped with self-adaptive uncertainty-aware explorations (UEs) based on a ratio uncertainty level. The proposed PPO-UE is designed to improve convergence speed and performance with an optimized ratio uncertainty level. Through extensive sensitivity analysis by varying the ratio uncertainty level, our proposed PPO-UE considerably outperforms the baseline PPO in Roboschool continuous control tasks.
translated by 谷歌翻译
显微镜图像的质量通常患有光差。这些畸变及其相关点的扩散功能必须进行定量估计以恢复畸变的图像。基于卷积神经网络的最新最先进的方法可以准确量化畸变,但仅限于点光源的图像,例如荧光珠。在这项研究中,我们描述了Phasenet的扩展,使其能够在生物样品的3D图像上使用。为此,我们的方法将特定于对象的信息结合到用于培训网络的模拟图像中。此外,我们通过Richardson-Lucy Deonvolution添加了基于Python的图像恢复。我们证明,具有预测的PSF的反卷积不仅可以消除模拟畸变,还可以提高使用未知残留PSF的真实原始显微镜图像的质量。我们提供代码,以快速,方便的预测和纠正畸变。
translated by 谷歌翻译
用于评估有条件自然语言生成的传统自动化指标使用单个生成的文本和最佳匹配的金标准地面真相文本之间的成对比较。当有多个基础真相可用时,分数将使用参考中的平均或最大操作进行汇总。尽管这种方法在地面真相数据中的多样性(即有条件文本的分布的分散)可以归因于噪声,例如自动语音识别中,但在地面上的多样性的情况下,它不允许进行强有力的评估。真理代表模型的信号。在这项工作中,我们认为现有的指标不适合诸如视觉描述或摘要之类的域,而地面真理在语义上是多样的,并且这些字幕中的多样性捕获了有关上下文的有用的其他信息。我们提出了一种新的范式,用于对条件语言生成模型的多键入评估以及一个新的指标家族,该指标家族使用每种少量样本集比较参考和模型生成的字幕集的分布。我们通过视觉描述中的案例研究证明了方法的实用性:我们在其中证明现有模型优化了单描述质量而不是多样性,并获得了对采样方法和温度影响如何描述质量和多样性的一些见解。
translated by 谷歌翻译
对国际气候变化小组(IPCC)的第六次评估指出,“过去十年(2010-2019)的累积净二氧化碳排放量与剩下的11个碳预算可能会限制为1.5C(中等信心)大约相同)。”这样的报告直接培养了公众的话语,但是诸如信念和信心程度之类的细微差别常常失去。在本文中,我们提出了一个正式的帐户,以允许在抽象论证设置中使用这种信念和相关的信心来标记论证。与概率论证中的其他建议不同,我们关注对Sato分布语义的选择构建的概率推断的任务,Sato的分布语义已被证明涵盖了包括贝叶斯网络的语义在内的各种情况。从有关此类语义的大量文献中借用,我们研究了如何在考虑不确定概率的情况下在实践中处理此类任务,并与现有的概率论点的现有建议讨论联系。
translated by 谷歌翻译
在二阶不确定的贝叶斯网络中,条件概率仅在分布中已知,即概率上的概率。Delta方法已应用于扩展精确的一阶推理方法,以通过从贝叶斯网络得出的总和产物网络传播均值和方差,从而表征了认知不确定性或模型本身的不确定性。另外,已经证明了Polytrees的二阶信仰传播,但没有针对一般的定向无环形结构。在这项工作中,我们将循环信念传播扩展到二阶贝叶斯网络的设置,从而产生二阶循环信念传播(SOLBP)。对于二阶贝叶斯网络,SOLBP生成了与Sum-Propoduct网络生成的网络一致的推论,同时更加有效且可扩展。
translated by 谷歌翻译
当历史数据受到限制时,与贝叶斯网络节点相关的条件概率不确定,并且可以在经验上进行估计。二阶估计方法为估计概率和量化这些估计的不确定性提供了一个框架。我们将这些案例称为Uncer Tain或二阶贝叶斯网络。当完成此类数据时,即每个实例化都观察到所有可变值,已知有条件的概率是dirichlet分布的。本文通过使他们能够学习参数(即条件概率),通过不完整的数据来学习不确定的贝叶斯网络的当前最新方法。我们广泛评估各种方法,通过各种查询的置信界的所需和经验得出的强度来学习参数的后验。
translated by 谷歌翻译