We explore the impact of environmental conditions on the competency of machine learning agents and how real-time competency assessments improve the reliability of ML agents. We learn a representation of conditions which impact the strategies and performance of the ML agent enabling determination of actions the agent can make to maintain operator expectations in the case of a convolutional neural network that leverages visual imagery to aid in the obstacle avoidance task of a simulated self-driving vehicle.
translated by 谷歌翻译
当将同时映射和本地化(SLAM)调整到现实世界中的应用程序(例如自动驾驶汽车,无人机和增强现实设备)时,其内存足迹和计算成本是限制性能和应用程序范围的两个主要因素。在基于稀疏特征的SLAM算法中,解决此问题的一种有效方法是通过选择可能对本地和全局捆绑捆绑调整(BA)有用的点来限制地图点大小。这项研究提出了用于大量系统中稀疏地图点的有效图优化。具体而言,我们将最大姿势可见度和最大空间多样性问题作为最小成本最大流量图优化问题。提出的方法是现有SLAM系统的附加步骤,因此可以在常规或基于学习的SLAM系统中使用。通过广泛的实验评估,我们证明了所提出的方法以大约1/3的MAP点和1/2的计算实现了更准确的相机姿势。
translated by 谷歌翻译
胃内窥镜筛查是在早期决定适当的胃癌(GC)治疗的有效方法,从而降低了与GC相关的死亡率。尽管人工智能(AI)带来了一个巨大的希望,可以帮助病理学家筛选数字化整个幻灯片图像,但现有的AI系统受到细粒癌症亚赛的限制,在计划癌症治疗方面几乎没有可用性。我们提出了一个实用的AI系统,该系统可以实现五个GC病理的亚分类,可以直接与一般的GC治疗指南相匹配。 AI系统旨在通过模仿人类病理学家理解组织学的方式,通过使用2阶段混合视觉变压器(VIT)网络通过多尺度的自我注意力转换器(VIT)网络通过多尺度的自我发项机制来有效区分多级GC。 AI系统通过在多中心队列中达到1,212张幻灯片,通过达到高于0.85的类平均灵敏度来显示可靠的诊断性能。此外,与人类病理学家相比,AI辅助病理学家显示出12%的诊断敏感性显着提高了12%。我们的结果表明,在实际临床环境中,AI辅助胃内窥镜筛查具有提供假定的病理学意见和适当的胃癌癌症治疗的巨大潜力。
translated by 谷歌翻译
由于许多安全性系统(例如手术机器人和自动驾驶汽车)在不稳定的环境中运行,具有传感器噪声和不完整的数据,因此希望对象探测器将本地化不确定性考虑在内。但是,基于锚的对象检测的现有不确定性估计方法存在几个局限性。 1)它们对具有不同特征和尺度的异质对象性质的不确定性进行建模,例如位置(中心点)和尺度(宽度,高度),这可能很难估算。 2)它们将框偏移型为高斯分布,这与遵循Dirac Delta分布的地面真相边界框不兼容。 3)由于基于锚的方法对锚定超参数敏感,因此它们的定位不确定性也可能对选择超参数的选择高度敏感。为了应对这些局限性,我们提出了一种称为UAD的新定位不确定性估计方法,用于无锚对象检测。我们的方法捕获了均匀的四个方向(左,右,顶部,底部)的四个方向的不确定性,因此它可以判断哪个方向不确定,并在[0,1]中提供不确定性的定量值。为了实现这种不确定性估计,我们设计了一种新的不确定性损失,负功率对数可能性损失,以通过加权其IOU加权可能性损失来衡量本地化不确定性,从而减轻了模型错误指定问题。此外,我们提出了反映分类评分的估计不确定性的不确定性感知局灶性损失。可可数据集的实验结果表明,我们的方法在不牺牲计算效率的情况下显着提高了最高1.8点的FCO。
translated by 谷歌翻译
The time-series forecasting (TSF) problem is a traditional problem in the field of artificial intelligence. Models such as Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), and GRU (Gate Recurrent Units) have contributed to improving the predictive accuracy of TSF. Furthermore, model structures have been proposed to combine time-series decomposition methods, such as seasonal-trend decomposition using Loess (STL) to ensure improved predictive accuracy. However, because this approach is learned in an independent model for each component, it cannot learn the relationships between time-series components. In this study, we propose a new neural architecture called a correlation recurrent unit (CRU) that can perform time series decomposition within a neural cell and learn correlations (autocorrelation and correlation) between each decomposition component. The proposed neural architecture was evaluated through comparative experiments with previous studies using five univariate time-series datasets and four multivariate time-series data. The results showed that long- and short-term predictive performance was improved by more than 10%. The experimental results show that the proposed CRU is an excellent method for TSF problems compared to other neural architectures.
translated by 谷歌翻译
We develop a wall model for large-eddy simulation (LES) that takes into account various pressure-gradient effects using multi-agent reinforcement learning (MARL). The model is trained using low-Reynolds-number flow over periodic hills with agents distributed on the wall along the computational grid points. The model utilizes a wall eddy-viscosity formulation as the boundary condition, which is shown to provide better predictions of the mean velocity field, rather than the typical wall-shear stress formulation. Each agent receives states based on local instantaneous flow quantities at an off-wall location, computes a reward based on the estimated wall-shear stress, and provides an action to update the wall eddy viscosity at each time step. The trained wall model is validated in wall-modeled LES (WMLES) of flow over periodic hills at higher Reynolds numbers, and the results show the effectiveness of the model on flow with pressure gradients. The analysis of the trained model indicates that the model is capable of distinguishing between the various pressure gradient regimes present in the flow.
translated by 谷歌翻译
Deep metric learning (DML) aims to automatically construct task-specific distances or similarities of data, resulting in a low-dimensional representation. Several significant metric-learning methods have been proposed. Nonetheless, no approach guarantees the preservation of the ordinal nature of the original data in a low-dimensional space. Ordinal data are ubiquitous in real-world problems, such as the severity of symptoms in biomedical cases, production quality in manufacturing, rating level in businesses, and aging level in face recognition. This study proposes a novel angular triangle distance (ATD) and ordinal triplet network (OTD) to obtain an accurate and meaningful embedding space representation for ordinal data. The ATD projects the ordinal relation of data in the angular space, whereas the OTD learns its ordinal projection. We also demonstrated that our new distance measure satisfies the distance metric properties mathematically. The proposed method was assessed using real-world data with an ordinal nature, such as biomedical, facial, and hand-gestured images. Extensive experiments have been conducted, and the results show that our proposed method not only semantically preserves the ordinal nature but is also more accurate than existing DML models. Moreover, we also demonstrate that our proposed method outperforms the state-of-the-art ordinal metric learning method.
translated by 谷歌翻译
多模式的机器学习已被广​​泛研究以开发通用智能。最近,感知者和感知者IO出色的多模式算法对各种数据集域和任务显示了竞争结果。但是,最近的作品,感知者和感知者IO专注于异质模式,包括图像,文本和语音,并且对于图形结构化数据集的研究作品很少。图是最概括的数据集结构之一,我们可以代表其他数据集,包括图像,文本和语音作为图形结构化数据。图具有与其他数据集域(例如文本和图像)不同的邻接矩阵,并且处理拓扑信息,关系信息和规范的位置信息并不微不足道。在这项研究中,我们提供了图形感知器IO,即图形结构化数据集的感知器IO。我们将图形感知器IO的主要结构保留为感知器IO,因为除了图形结构化数据集外,感知器IO已经很好地处理了各种数据集。图形感知器IO是一种通用方法,它可以处理各种数据集,例如图形结构化数据以及文本和图像。比较图形神经网络,图感知器IO需要较低的复杂性,并且可以有效地合并局部和全局信息。我们表明,图形感知器IO显示了与图形相关任务的各种竞争结果,包括节点分类,图形分类和链接预测。
translated by 谷歌翻译
深度神经网络(DNN)的训练过程通常是用阶段进行管道的,用于在CPU上进行数据制备,然后对GPU等加速器进行梯度计算。在理想的管道中,端到端训练吞吐量最终受到加速器的吞吐量的限制,而不是数据准备。过去,DNN训练管道通过使用使用轻巧,有损的图像格式(如JPEG)编码的数据集实现了近乎最佳的吞吐量。但是,随着高分辨率,无损编码的数据集变得越来越流行,对于需要高精度的应用程序,由于CPU上的低通量图像解码,在数据准备阶段出现了性能问题。因此,我们提出了L3,这是一种用于高分辨率,高通量DNN训练的定制轻巧,无损的图像格式。 L3的解码过程在加速器上有效平行,从而最大程度地减少了在DNN培训期间进行数据制备的CPU干预。 L3比最流行的无损图像格式PNG获得了9.29倍的数据准备吞吐量,用于NVIDIA A100 GPU上的CityScapes数据集,该数据集可导致1.71倍更高的端到端训练吞吐量。与JPEG和WebP相比,两种流行的有损图像格式,L3分别以同等的度量性能为Imagenet提供高达1.77倍和2.87倍的端到端训练吞吐量。
translated by 谷歌翻译
弱监督的对象检测(WSOD)是一项任务,可使用仅在图像级注释上训练的模型来检测图像中的对象。当前的最新模型受益于自我监督的实例级别的监督,但是由于弱监督不包括计数或位置信息,因此最常见的``Argmax''标签方法通常忽略了许多对象实例。为了减轻此问题,我们提出了一种新颖的多个实例标记方法,称为对象发现。我们进一步在弱监督下引入了新的对比损失,在该监督下,没有实例级信息可用于采样,称为弱监督对比损失(WSCL)。WSCL旨在通过利用一致的功能来嵌入同一类中的向量来构建对象发现的可靠相似性阈值。结果,我们在2014年和2017年MS-Coco以及Pascal VOC 2012上取得了新的最新结果,并在Pascal VOC 2007上取得了竞争成果。
translated by 谷歌翻译