Neuromorphic systems require user-friendly software to support the design and optimization of experiments. In this work, we address this need by presenting our development of a machine learning-based modeling framework for the BrainScaleS-2 neuromorphic system. This work represents an improvement over previous efforts, which either focused on the matrix-multiplication mode of BrainScaleS-2 or lacked full automation. Our framework, called hxtorch.snn, enables the hardware-in-the-loop training of spiking neural networks within PyTorch, including support for auto differentiation in a fully-automated hardware experiment workflow. In addition, hxtorch.snn facilitates seamless transitions between emulating on hardware and simulating in software. We demonstrate the capabilities of hxtorch.snn on a classification task using the Yin-Yang dataset employing a gradient-based approach with surrogate gradients and densely sampled membrane observations from the BrainScaleS-2 hardware system.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

We study the convergence of several natural policy gradient (NPG) methods in infinite-horizon discounted Markov decision processes with regular policy parametrizations. For a variety of NPGs and reward functions we show that the trajectories in state-action space are solutions of gradient flows with respect to Hessian geometries, based on which we obtain global convergence guarantees and convergence rates. In particular, we show linear convergence for unregularized and regularized NPG flows with the metrics proposed by Kakade and Morimura and co-authors by observing that these arise from the Hessian geometries of conditional entropy and entropy respectively. Further, we obtain sublinear convergence rates for Hessian geometries arising from other convex functions like log-barriers. Finally, we interpret the discrete-time NPG methods with regularized rewards as inexact Newton methods if the NPG is defined with respect to the Hessian geometry of the regularizer. This yields local quadratic convergence rates of these methods for step size equal to the penalization strength.

单眼相机传感器对于智能车辆操作和自动驾驶帮助至关重要，并且在交通控制基础设施中也很大程度上使用。但是，校准单眼摄像机很耗时，通常需要大量的手动干预。在这项工作中，我们提出了一种外部摄像机校准方法，该方法通过利用来自图像和点云的语义分割信息来自动化参数估计。我们的方法依赖于对摄像头姿势的粗略初始测量，并建立在具有高精度定位的车辆上的雷达传感器上，以捕获相机环境的点云。之后，通过执行语义分段传感器数据的激光镜头到相机的注册来获得相机和世界坐标空间之间的映射。我们在模拟和现实世界中评估了我们的方法，以证明校准结果中的低误差测量值。我们的方法适用于基础设施传感器和车辆传感器，而它不需要摄像机平台的运动。

在这项工作中，我们适应了一种受原始Alphago系统启发的训练方法，以扮演不完美的侦察盲目信息游戏。我们仅使用观测值而不是对游戏状态的完整描述，我们首先在公开可用的游戏记录上训练监督代理。接下来，我们通过自我播放来提高代理商的性能，并使用彻底的强化学习算法近端策略优化。我们不使用任何搜索来避免由于游戏状态的部分可观察性引起的问题，而只使用策略网络在播放时生成动作。通过这种方法，我们在RBC排行榜上实现了1330的ELO，该纸板在撰写本文时将我们的经纪人处于27位。我们看到自我戏剧可显着提高性能，并且代理商在没有搜索的情况下可以很好地发挥，而无需对真实游戏状态做出假设。

多代理系统（例如自动驾驶或工厂）作为服务的一些最相关的应用程序显示混合动机方案，代理商可能具有相互矛盾的目标。在这些环境中，代理可能会在独立学习下的合作方面学习不良的结果，例如过度贪婪的行为。在现实世界社会的动机中，在这项工作中，我们建议利用市场力量为代理商成为合作的激励措施。正如囚犯困境的迭代版本所证明的那样，拟议的市场配方可以改变游戏的动力，以始终如一地学习合作政策。此外，我们在空间和时间扩展的设置中评估了不同数量的代理的方法。我们从经验上发现，市场的存在可以通过其交易活动改善总体结果和代理人的回报。

自然梯度场是一个矢量场，该矢量场居住在配备有杰出的Riemannian指标的模型上，例如Fisher-Rao公制，代表模型在该度量方面的目标函数的最陡峭上升的方向。实际上，一个人试图通过将普通梯度乘以与度量的革兰氏矩阵的倒数来获得参数空间上的相应方向。我们将此矢量称为参数空间，为自然参数梯度。在本文中，我们研究了自然参数梯度的推动力等于天然梯度。此外，我们研究了自然参数梯度的不变特性。这两个问题均在过度隔离的环境中解决。

可靠的跟踪算法对于自动驾驶至关重要。但是，现有的一致性措施不足以满足汽车部门日益增长的安全需求。因此，这项工作提出了一种基于卡尔曼过滤和主观逻辑的混乱中单对象跟踪自我评估的新方法。该方法的一个关键特征是，它还提供了在线可靠性评分中收集的统计证据的量度。这样，可靠性的各个方面，例如假定的测量噪声，检测概率和混乱速率的正确性，除了基于可用证据的整体评估外，还可以监视。在这里，我们提出了用于研究问题的自我评估模块中使用的参考分布的数学推导。此外，我们介绍了一个公式，该公式描述了如何为冲突程度选择阈值，这是用于可靠性决策的主观逻辑比较度量。我们的方法在旨在建模不利天气条件的挑战性模拟场景中进行了评估。模拟表明，我们的方法可以显着提高多个方面杂物中单对象跟踪的可靠性检查。

在自动驾驶领域内，环境感知的明显趋势趋于更多的传感器，更高的冗余和计算能力的总体增加。这主要是由范例驱动，以尽可能地掌握整个环境。然而，由于功能复杂性的持续上升，必须考虑妥协以确保感知系统的实时能力。在这项工作中，我们介绍了一种情况感知环境感知的概念，以控制资源分配在数据内处理相关区域，以及仅用于用于环境感知的功能模块的子集，如果足够的驱动任务。具体地，我们建议评估自动化车辆的上下文，以得出定义相关区域的多层注意图（MLAM）。使用此MLAM，动态配置有源功能模块的最佳状态，并强制执行仅相关数据的模块内处理。我们概述了我们概念在手头的直接实施中使用真实数据应用的可行性。在保留整体功能的同时，我们实现了59％的累计处理时间的降低。

BRINSCALES神经形态计算系统目前通过千兆 - 以太网网络技术连接到计算集群。这方便目前使用的实验模式，其中神经元网络在大多数晶片模块上覆盖。当建模较大尺寸的网络时，例如全尺寸的皮质微电路模型，必须考虑将晶片模块连接到更大网络的神经元。这可以使用扩展网络技术来完成，该技术提供高带宽和低延迟，以及低开销分组协议格式。