Quantum entanglement is a fundamental property commonly used in various quantum information protocols and algorithms. Nonetheless, the problem of quantifying entanglement has still not reached general solution for systems larger than two qubits. In this paper, we investigate the possibility of detecting entanglement with the use of the supervised machine learning method, namely the deep convolutional neural networks. We build a model consisting of convolutional layers, which is able to recognize and predict the presence of entanglement for any bipartition of the given multi-qubit system. We demonstrate that training our model on synthetically generated datasets collecting random density matrices, which either include or exclude challenging positive-under-partial-transposition entangled states (PPTES), leads to the different accuracy of the model and its possibility to detect such states. Moreover, it is shown that enforcing entanglement-preserving symmetry operations (local operations on qubit or permutations of qubits) by using triple Siamese network, can significantly increase the model performance and ability to generalize on types of states not seen during the training stage. We perform numerical calculations for 3,4 and 5-qubit systems, therefore proving the scalability of the proposed approach.

我们介绍了一种有效的策略来产生可用于培训深层学习模型的培养皿的微生物图像的合成数据集。开发的发电机采用传统的计算机视觉算法以及用于数据增强的神经风格传输方法。我们表明该方法能够合成可用于培训能够定位，分割和分类五种不同微生物物种的神经网络模型的现实看起来的数据集。我们的方法需要更少的资源来获取有用的数据集，而不是收集和标记具有注释的整个大型真实图像。我们表明，只有100个真实图像开始，我们可以生成数据以培训一个探测器，该探测器实现了相同的探测器，而是在真实的，几十次更大的数据集上培训。我们证明了微生物检测和分割方法的有用性，但我们预计它是一般而灵活的，也可以适用于其他科学和工业领域来检测各种物体。

We study the fundamental question of how to define and measure the distance from calibration for probabilistic predictors. While the notion of perfect calibration is well-understood, there is no consensus on how to quantify the distance from perfect calibration. Numerous calibration measures have been proposed in the literature, but it is unclear how they compare to each other, and many popular measures such as Expected Calibration Error (ECE) fail to satisfy basic properties like continuity. We present a rigorous framework for analyzing calibration measures, inspired by the literature on property testing. We propose a ground-truth notion of distance from calibration: the $\ell_1$ distance to the nearest perfectly calibrated predictor. We define a consistent calibration measure as one that is a polynomial factor approximation to the this distance. Applying our framework, we identify three calibration measures that are consistent and can be estimated efficiently: smooth calibration, interval calibration, and Laplace kernel calibration. The former two give quadratic approximations to the ground truth distance, which we show is information-theoretically optimal. Our work thus establishes fundamental lower and upper bounds on measuring distance to calibration, and also provides theoretical justification for preferring certain metrics (like Laplace kernel calibration) in practice.

通过融合单个模式（例如文本，图像或音频）来创建有意义的表示形式是多模式学习的核心概念。尽管已经证明了几种用于构建多模式表示的技术，但尚未进行比较。因此，在给定情况下，可以预期哪种技术可以产生最佳结果，以及在选择这种技术时应考虑哪些因素。本文探讨了构建多模式数据表示的最常见技术 - 晚期融合，早期融合和草图，并在分类任务中进行比较。实验是在三个数据集上进行的：Amazon评论，Movielens25M和Movielens1M数据集。通常，我们的结果证实，多模式表示能够在亚马逊评论上将单峰模型的性能从0.919的精度提高到0.969，而Movielens25m上的AUC的表现为0.907至0.918。但是，两个Movielens数据集的实验表明有意义的输入数据对给定任务的重要性。在本文中，我们表明，构建多模式表示技术的选择对于获得最高模型的性能至关重要，这与适当的模式组合有关。这种选择依赖于：每种形态对分析的机器学习（ML）问题的影响； ML任务的类型；训练和预测阶段时的内存约束。

由于其弱监督性，多个实例学习（MIL）在许多现实生活中的机器学习应用中都获得了受欢迎程度。但是，解释MIL滞后的相应努力，通常仅限于提出对特定预测至关重要的袋子的实例。在本文中，我们通过引入Protomil，这是一种新型的自我解释的MIL方法，该方法受到基于案例的推理过程的启发，该方法是基于案例的推理过程，该方法在视觉原型上运行。由于将原型特征纳入对象描述中，Protomil空前加入了模型的准确性和细粒度的可解释性，我们在五个公认的MIL数据集上进行了实验。

近年来，在基于视觉的施工站点安全系统的背景下，特别是关于个人保护设备，对深度学习方法引起了很多关注。但是，尽管有很多关注，但仍然没有可靠的方法来建立工人与硬帽之间的关系。为了回答此问题，本文提出了深入学习，对象检测和头部关键点本地化的结合以及简单的基于规则的推理。在测试中，该解决方案基于不同实例的相对边界框位置以及直接检测硬帽佩戴者和非磨损者的方法超过了先前的方法。结果表明，新颖的深度学习方法与基于人性化的规则系统的结合可能会导致一种既可靠又可以成功模仿现场监督的解决方案。这项工作是开发完全自主建筑工地安全系统的下一步，表明该领域仍有改进的余地。