交叉路口交通信号控制器（TSC）中的次优化控制策略有助于拥堵，导致对人类健康和环境的负面影响。交通信号控制的强化学习（RL）是设计更好控制政策的有希望的方法，并近年来吸引了相当大的研究兴趣。但是，在该区域中完成的大多数工作使用了交通方案的简化仿真环境，以培训基于RL的TSC。要在现实世界流量系统中部署RL，必须关闭简化的仿真环境和现实应用程序之间的差距。因此，我们提出了一个基准工具，将RL代理作为TSC的基准工具，在Lemgo的德国中型镇的逼真模拟环境中。除了现实的仿真模型之外，LEMGORL还包括交通信号逻辑单元，可确保符合所有监管和安全要求。 LEMGORL提供与Killknown Openai健身房工具包相同的界面，以便在现有的研究工作中轻松进行部署。为了演示LemGorl的功能和适用性，我们利用分布式和并行RL的框架训练CPU群集的最先进的深rl算法，并将其性能与其他方法进行比较。我们的基准工具推动了RL算法对现实世界的应用。

We investigate a model for image/video quality assessment based on building a set of codevectors representing in a sense some basic properties of images, similar to well-known CORNIA model. We analyze the codebook building method and propose some modifications for it. Also the algorithm is investigated from the point of inference time reduction. Both natural and synthetic images are used for building codebooks and some analysis of synthetic images used for codebooks is provided. It is demonstrated the results on quality assessment may be improves with the use if synthetic images for codebook construction. We also demonstrate regimes of the algorithm in which real time execution on CPU is possible for sufficiently high correlations with mean opinion score (MOS). Various pooling strategies are considered as well as the problem of metric sensitivity to bitrate.

The body of research on classification of solar panel arrays from aerial imagery is increasing, yet there are still not many public benchmark datasets. This paper introduces two novel benchmark datasets for classifying and localizing solar panel arrays in Denmark: A human annotated dataset for classification and segmentation, as well as a classification dataset acquired using self-reported data from the Danish national building registry. We explore the performance of prior works on the new benchmark dataset, and present results after fine-tuning models using a similar approach as recent works. Furthermore, we train models of newer architectures and provide benchmark baselines to our datasets in several scenarios. We believe the release of these datasets may improve future research in both local and global geospatial domains for identifying and mapping of solar panel arrays from aerial imagery. The data is accessible at https://osf.io/aj539/.

There has been a great deal of recent interest in learning and approximation of functions that can be expressed as expectations of a given nonlinearity with respect to its random internal parameters. Examples of such representations include "infinitely wide" neural nets, where the underlying nonlinearity is given by the activation function of an individual neuron. In this paper, we bring this perspective to function representation by neural stochastic differential equations (SDEs). A neural SDE is an It\^o diffusion process whose drift and diffusion matrix are elements of some parametric families. We show that the ability of a neural SDE to realize nonlinear functions of its initial condition can be related to the problem of optimally steering a certain deterministic dynamical system between two given points in finite time. This auxiliary system is obtained by formally replacing the Brownian motion in the SDE by a deterministic control input. We derive upper and lower bounds on the minimum control effort needed to accomplish this steering; these bounds may be of independent interest in the context of motion planning and deterministic optimal control.

Powerful hardware services and software libraries are vital tools for quickly and affordably designing, testing, and executing quantum algorithms. A robust large-scale study of how the performance of these platforms scales with the number of qubits is key to providing quantum solutions to challenging industry problems. Such an evaluation is difficult owing to the availability and price of physical quantum processing units. This work benchmarks the runtime and accuracy for a representative sample of specialized high-performance simulated and physical quantum processing units. Results show the QMware cloud computing service can reduce the runtime for executing a quantum circuit by up to 78% compared to the next fastest option for algorithms with fewer than 27 qubits. The AWS SV1 simulator offers a runtime advantage for larger circuits, up to the maximum 34 qubits available with SV1. Beyond this limit, QMware provides the ability to execute circuits as large as 40 qubits. Physical quantum devices, such as Rigetti's Aspen-M2, can provide an exponential runtime advantage for circuits with more than 30. However, the high financial cost of physical quantum processing units presents a serious barrier to practical use. Moreover, of the four quantum devices tested, only IonQ's Harmony achieves high fidelity with more than four qubits. This study paves the way to understanding the optimal combination of available software and hardware for executing practical quantum algorithms.

冠心病（CHD）是现代世界中死亡的主要原因。用于诊断和治疗CHD的现代分析工具的开发正在从科学界受到极大的关注。基于深度学习的算法，例如分割网络和检测器，通过及时分析患者的血管造影来协助医疗专业人员，在协助医疗专业人员方面发挥着重要作用。本文着重于X射线冠状动脉造影（XCA），该血管造影被认为是CHD诊断和治疗中的“黄金标准”。首先，我们描述了XCA图像的公开可用数据集。然后，审查了图像预处理的经典和现代技术。此外，讨论了共同的框架选择技术，这是输入质量以及模型性能的重要因素。在以下两章中，我们讨论了现代血管分割和狭窄检测网络，最后是当前最新技术的开放问题和当前局限性。

在现实世界条件下运行的原因是由于部分可观察性引起的广泛故障而具有挑战性。在相对良性的环境中，可以通过重试或执行少量手工恢复策略之一来克服这种失败。相比之下，诸如打开门和组装家具之类的接触式连续操作任务不适合详尽的手工设计。为了解决这个问题，我们提出了一种以样本效率的方式来鲁棒化操作策略的一般方法。我们的方法通过在模拟中探索发现当前策略的故障模式，从而提高了鲁棒性，然后学习其他恢复技能来处理这些失败。为了确保有效的学习，我们提出了一种在线算法值上限限制（值UCL），该算法选择要优先级的故障模式以及要恢复到哪种状态，以使预期的性能在每个培训情节中最大程度地提高。我们使用我们的方法来学习开门的恢复技能，并在模拟和实际机器人中对其进行评估。与开环执行相比，我们的实验表明，即使是有限的恢复学习也可以从模拟中的71 \％提高到92.4 \％，从75 \％到90 \％的实际机器人。

深度学习归一化技术的基本特性，例如批准归一化，正在使范围前的参数量表不变。此类参数的固有域是单位球，因此可以通过球形优化的梯度优化动力学以不同的有效学习率（ELR）来表示，这是先前研究的。在这项工作中，我们使用固定的ELR直接研究了训练量表不变的神经网络的特性。我们根据ELR值发现了这种训练的三个方案：收敛，混乱平衡和差异。我们详细研究了这些制度示例的理论检查，以及对真实规模不变深度学习模型的彻底经验分析。每个制度都有独特的特征，并反映了内在损失格局的特定特性，其中一些与先前对常规和规模不变的神经网络培训的研究相似。最后，我们证明了如何在归一化网络的常规培训以及如何利用它们以实现更好的Optima中反映发现的制度。

现代基于深度学习的系统的性能极大地取决于输入对象的质量。例如，对于模糊或损坏的输入，面部识别质量将较低。但是，在更复杂的情况下，很难预测输入质量对所得准确性的影响。我们提出了一种深度度量学习的方法，该方法允许直接估算不确定性，几乎没有额外的计算成本。开发的\ textit {scaleface}算法使用可训练的比例值，以修改嵌入式空间中的相似性。这些依赖于输入的量表值代表了对识别结果的信心的度量，从而允许估计不确定性。我们提供了有关面部识别任务的全面实验，这些实验表明与其他不确定性感知的面部识别方法相比，比例表面的表现出色。我们还将结果扩展到了文本到图像检索的任务，表明所提出的方法以显着的利润击败了竞争对手。

机器学习（ML）为生物处理工程的发展做出了重大贡献，但其应用仍然有限，阻碍了生物过程自动化的巨大潜力。用于模型构建自动化的ML可以看作是引入另一种抽象水平的一种方式，将专家的人类集中在生物过程开发的最认知任务中。首先，概率编程用于预测模型的自动构建。其次，机器学习会通过计划实验来测试假设并进行调查以收集信息性数据来自动评估替代决策，以收集基于模型预测不确定性的模型选择的信息数据。这篇评论提供了有关生物处理开发中基于ML的自动化的全面概述。一方面，生物技术和生物工程社区应意识到现有ML解决方案在生物技术和生物制药中的应用的限制。另一方面，必须确定缺失的链接，以使ML和人工智能（AI）解决方案轻松实施在有价值的生物社区解决方案中。我们总结了几个重要的生物处理系统的ML实施，并提出了两个至关重要的挑战，这些挑战仍然是生物技术自动化的瓶颈，并减少了生物技术开发的不确定性。没有一个合适的程序；但是，这项综述应有助于确定结合生物技术和ML领域的潜在自动化。