机器学习模型无处不在。在某些域中,例如,在医学中,模型的预测必须是可解释的。决策树,分类规则和亚组发现是三类广泛的监督机器学习模型,以可解释规则的形式呈现知识。从小数据集中学习的这些模型的准确性通常很低。获得较大的数据集通常难以不可能。我们提出了一个框架被称为PRELIM,以了解小数据的更好规则。它使用统计模型增强了数据,并采用它来学习规则基础的模型。在我们广泛的实验中,我们确定了俯视最先进的PRELIM配置。
translated by 谷歌翻译
We improve the understanding of the $\textit{golden ratio algorithm}$, which solves monotone variational inequalities (VI) and convex-concave min-max problems via the distinctive feature of adapting the step sizes to the local Lipschitz constants. Adaptive step sizes not only eliminate the need to pick hyperparameters, but they also remove the necessity of global Lipschitz continuity and can increase from one iteration to the next. We first establish the equivalence of this algorithm with popular VI methods such as reflected gradient, Popov or optimistic gradient descent-ascent in the unconstrained case with constant step sizes. We then move on to the constrained setting and introduce a new analysis that allows to use larger step sizes, to complete the bridge between the golden ratio algorithm and the existing algorithms in the literature. Doing so, we actually eliminate the link between the golden ratio $\frac{1+\sqrt{5}}{2}$ and the algorithm. Moreover, we improve the adaptive version of the algorithm, first by removing the maximum step size hyperparameter (an artifact from the analysis) to improve the complexity bound, and second by adjusting it to nonmonotone problems with weak Minty solutions, with superior empirical performance.
translated by 谷歌翻译
Visualization methods based on the nearest neighbor graph, such as t-SNE or UMAP, are widely used for visualizing high-dimensional data. Yet, these approaches only produce meaningful results if the nearest neighbors themselves are meaningful. For images represented in pixel space this is not the case, as distances in pixel space are often not capturing our sense of similarity and therefore neighbors are not semantically close. This problem can be circumvented by self-supervised approaches based on contrastive learning, such as SimCLR, relying on data augmentation to generate implicit neighbors, but these methods do not produce two-dimensional embeddings suitable for visualization. Here, we present a new method, called t-SimCNE, for unsupervised visualization of image data. T-SimCNE combines ideas from contrastive learning and neighbor embeddings, and trains a parametric mapping from the high-dimensional pixel space into two dimensions. We show that the resulting 2D embeddings achieve classification accuracy comparable to the state-of-the-art high-dimensional SimCLR representations, thus faithfully capturing semantic relationships. Using t-SimCNE, we obtain informative visualizations of the CIFAR-10 and CIFAR-100 datasets, showing rich cluster structure and highlighting artifacts and outliers.
translated by 谷歌翻译
用于在线状态估计的随机过滤器是自治系统的核心技术。此类过滤器的性能是系统能力的关键限制因素之一。此类过滤器的渐近行为(例如,用于常规操作)和瞬态响应(例如,对于快速初始化和重置)对于保证自主系统的稳健操作至关重要。本文使用n个方向测量值(包括车身框架和参考框架方向类型测量值)引入了陀螺仪辅助姿态估计器的新通用公式。该方法基于一种集成状态公式,该公式结合了导航,所有方向传感器的外部校准以及在单个模棱两可的几何结构中的陀螺式偏置状态。这种新提出的对称性允许模块化的不同方向测量及其外部校准,同时保持在同一对称性中包括偏置态的能力。随后使用此对称性的基于滤波器的估计量明显改善了瞬态响应,与最新方法相比,渐近偏置和外部校准估计。估计器在统计代表性的模拟中得到了验证,并在现实世界实验中进行了测试。
translated by 谷歌翻译
具有许多移动代理的城市环境的运动计划可以看作是组合问题。通过在左右之后,左右或左后通过障碍物,自动驾驶汽车可以选择执行多个选项。这些组合方面需要在计划框架中考虑到。我们通过提出一种结合轨迹计划和操纵推理的新型计划方法来解决这个问题。我们定义了沿参考曲线的动态障碍的分类,使我们能够提取战术决策序列。我们将纵向和横向运动分开,以加快基于优化的轨迹计划。为了将获得的轨迹集绘制为操纵变体,我们定义了一种语义来描述它们。这使我们能够选择最佳轨迹,同时还可以确保随着时间的推移操纵的一致性。我们证明了我们的方法的能力,即仍被普遍认为是具有挑战性的场景。
translated by 谷歌翻译
背景:在信息提取和自然语言处理域中,可访问的数据集对于复制和比较结果至关重要。公开可用的实施和工具可以用作基准,并促进更复杂的应用程序的开发。但是,在临床文本处理的背景下,可访问数据集的数量很少 - 现有工具的数量也很少。主要原因之一是数据的敏感性。对于非英语语言,这个问题更为明显。方法:为了解决这种情况,我们介绍了一个工作台:德国临床文本处理模型的集合。这些模型接受了德国肾脏病报告的识别语料库的培训。结果:提出的模型为内域数据提供了有希望的结果。此外,我们表明我们的模型也可以成功应用于德语的其他生物医学文本。我们的工作台公开可用,因此可以开箱即用,或转移到相关问题上。
translated by 谷歌翻译
Single-cell transcriptomics enabled the study of cellular heterogeneity in response to perturbations at the resolution of individual cells. However, scaling high-throughput screens (HTSs) to measure cellular responses for many drugs remains a challenge due to technical limitations and, more importantly, the cost of such multiplexed experiments. Thus, transferring information from routinely performed bulk RNA HTS is required to enrich single-cell data meaningfully. We introduce chemCPA, a new encoder-decoder architecture to study the perturbational effects of unseen drugs. We combine the model with an architecture surgery for transfer learning and demonstrate how training on existing bulk RNA HTS datasets can improve generalisation performance. Better generalisation reduces the need for extensive and costly screens at single-cell resolution. We envision that our proposed method will facilitate more efficient experiment designs through its ability to generate in-silico hypotheses, ultimately accelerating drug discovery.
translated by 谷歌翻译
ising机器是一个有前途的非von-neumann用于神经网络训练和组合优化的计算概念。然而,虽然可以用诸如展示机器实现各种神经网络,但是它们无法执行快速统计采样使得它们与数字计算机相比训练这些神经网络的效率低。在这里,我们通过注入模拟噪声来介绍一个通用概念,以实现具有ising机器的超快统计抽样。通过光电型机,我们证明这可用于精确采样Boltzmann分布和无监督的神经网络训练,具有与基于软件的培训等于准确性。通过模拟,我们发现ising机器可以比基于软件的方法更快地执行统计采样顺序。这使得Ising Machines成为机器学习的有效工具和超出组合优化的其他应用。
translated by 谷歌翻译
在本文中,我们提出了一种新的深度神经网络架构,用于联合类禁止对象分割和使用平行板夹持器的机器人拾取任务的掌握检测。我们引入深度感知的坐标卷积(CoordConv),一种方法来提高基于点提案的对象实例分段精度,在复杂的场景中不添加任何其他网络参数或计算复杂性。深度感知CoordConv使用深度数据来提取有关对象位置的先前信息以实现高度准确的对象实例分段。这些产生的分割掩模与预测的掌握候选者组合,导致使用平行板夹具抓住的完整场景描述。我们评估掌握检测和实例分割对具有挑战性机器人拣选数据集的准确性,即SIL \'EANE和OCID_GRASP,并展示了在真实世界机器人采摘任务上的联合掌握检测和分割的益处。
translated by 谷歌翻译
邻居Embeddings是一种使用$ k $ nn图来可视化复杂的高维数据集的方法。为了找到低维嵌入,这些算法将相邻对点之间的吸引力与所有点之间的排斥力相结合。这种算法的最受欢迎的例子之一是T-SNE。在这里,我们经验证明使用夸张参数改变T-SNE中的吸引力和排斥力之间的平衡产生了一种嵌入式,其特点是简单的折衷:更强的吸引力可以更好地代表连续的歧管结构,而更强排斥可以更好地代表离散的集群结构,并收益率较高$ K $ NN召回。我们发现Umap Embeddings对应于涉及吸引力的T-SNE;数学分析表明,这是因为UMAP采用的负采样优化策略强烈降低了有效的排斥。同样,Forceatlas2通常用于可视化发育​​单细胞转录组数据,产生与T-SNE相对应的嵌入,吸引力增加更多。在这个频谱的极端Lieglacian eigenmaps。我们的结果表明,许多突出的邻居嵌入算法可以放置在吸引力频谱上,并突出显示它们之间的固有折衷。
translated by 谷歌翻译