本文介绍了2021年进行的一系列教育事件的方法和结果，该活动利用机器人群来教育高中生和大学生有关流行病学模型以及如何为社会和政府政策提供信息。这些事件特别关注Covid-19的大流行，由4个在线和3个面对面的研讨会组成，学生有机会与一群20个定制的Brushbots互动 - 针对优化的小规模振动驱动的机器人便携性和鲁棒性。通过对事后调查中收集的数据的分析，本文展示了这些事件如何对学生对指导现实世界决策的科学方法的看法产生积极影响，以及他们对机器人技术的兴趣。

在对多机器人系统的约束驱动控制的背景下，在本文中，我们提出了一个基于优化的框架，该框架能够确保机器人团队的韧性和能源意识。该方法基于一种新颖的，框架理论的弹性度量，使我们能够分析和执行多机器人系统的弹性行为。弹性和能量意识的属性被编码为凸优化程序的约束，该程序用于合成机器人控制输入。这允许将此类属性与执行协调任务相结合，以实现弹性和能源感知机器人操作。在模拟场景中说明了所提出方法的有效性，其中部署了一个机器人团队以执行受能量和弹性约束的两个任务。

在许多情况下，增强学习（RL）已被证明是有效的。但是，通常需要探索足够多的国家行动对，其中一些对不安全。因此，其应用于安全至关重要的系统仍然是一个挑战。解决安全性的越来越普遍的方法涉及将RL动作投射到安全的一组动作上的安全层。反过来，此类框架的困难是如何有效地将RL与安全层搭配以提高学习绩效。在本文中，我们将安全性作为基于型号的RL框架中的可区分强大控制式 - 助推器功能层。此外，我们还提出了一种模块化学习基本奖励驱动的任务的方法，独立于安全限制。我们证明，这种方法既可以确保安全性，又可以有效地指导一系列实验中的训练期间的探索，包括以模块化的方式学习奖励时，包括零拍传递。

This paper provides an introduction and overview of recent work on control barrier functions and their use to verify and enforce safety properties in the context of (optimization based) safety-critical controllers. We survey the main technical results and discuss applications to several domains including robotic systems.

Objective: Accurate visual classification of bladder tissue during Trans-Urethral Resection of Bladder Tumor (TURBT) procedures is essential to improve early cancer diagnosis and treatment. During TURBT interventions, White Light Imaging (WLI) and Narrow Band Imaging (NBI) techniques are used for lesion detection. Each imaging technique provides diverse visual information that allows clinicians to identify and classify cancerous lesions. Computer vision methods that use both imaging techniques could improve endoscopic diagnosis. We address the challenge of tissue classification when annotations are available only in one domain, in our case WLI, and the endoscopic images correspond to an unpaired dataset, i.e. there is no exact equivalent for every image in both NBI and WLI domains. Method: We propose a semi-surprised Generative Adversarial Network (GAN)-based method composed of three main components: a teacher network trained on the labeled WLI data; a cycle-consistency GAN to perform unpaired image-to-image translation, and a multi-input student network. To ensure the quality of the synthetic images generated by the proposed GAN we perform a detailed quantitative, and qualitative analysis with the help of specialists. Conclusion: The overall average classification accuracy, precision, and recall obtained with the proposed method for tissue classification are 0.90, 0.88, and 0.89 respectively, while the same metrics obtained in the unlabeled domain (NBI) are 0.92, 0.64, and 0.94 respectively. The quality of the generated images is reliable enough to deceive specialists. Significance: This study shows the potential of using semi-supervised GAN-based classification to improve bladder tissue classification when annotations are limited in multi-domain data.

DeeProb-kit is a unified library written in Python consisting of a collection of deep probabilistic models (DPMs) that are tractable and exact representations for the modelled probability distributions. The availability of a representative selection of DPMs in a single library makes it possible to combine them in a straightforward manner, a common practice in deep learning research nowadays. In addition, it includes efficiently implemented learning techniques, inference routines, statistical algorithms, and provides high-quality fully-documented APIs. The development of DeeProb-kit will help the community to accelerate research on DPMs as well as to standardise their evaluation and better understand how they are related based on their expressivity.

In this paper, we introduce MINTIME, a video deepfake detection approach that captures spatial and temporal anomalies and handles instances of multiple people in the same video and variations in face sizes. Previous approaches disregard such information either by using simple a-posteriori aggregation schemes, i.e., average or max operation, or using only one identity for the inference, i.e., the largest one. On the contrary, the proposed approach builds on a Spatio-Temporal TimeSformer combined with a Convolutional Neural Network backbone to capture spatio-temporal anomalies from the face sequences of multiple identities depicted in a video. This is achieved through an Identity-aware Attention mechanism that attends to each face sequence independently based on a masking operation and facilitates video-level aggregation. In addition, two novel embeddings are employed: (i) the Temporal Coherent Positional Embedding that encodes each face sequence's temporal information and (ii) the Size Embedding that encodes the size of the faces as a ratio to the video frame size. These extensions allow our system to adapt particularly well in the wild by learning how to aggregate information of multiple identities, which is usually disregarded by other methods in the literature. It achieves state-of-the-art results on the ForgeryNet dataset with an improvement of up to 14% AUC in videos containing multiple people and demonstrates ample generalization capabilities in cross-forgery and cross-dataset settings. The code is publicly available at https://github.com/davide-coccomini/MINTIME-Multi-Identity-size-iNvariant-TIMEsformer-for-Video-Deepfake-Detection.

基于连续的潜在空间（例如变异自动编码器）的概率模型可以理解为无数混合模型，其中组件连续取决于潜在代码。它们具有用于生成和概率建模的表达性工具，但与可牵引的概率推断不符，即计算代表概率分布的边际和条件。同时，可以将概率模型（例如概率电路（PC））理解为层次离散混合模型，从而使它们可以执行精确的推断，但是与连续的潜在空间模型相比，它们通常显示出低于标准的性能。在本文中，我们研究了一种混合方法，即具有较小潜在尺寸的可拖动模型的连续混合物。尽管这些模型在分析上是棘手的，但基于一组有限的集成点，它们非常适合数值集成方案。有足够数量的集成点，近似值变得精确。此外，使用一组有限的集成点，可以将近似方法编译成PC中，以“在近似模型中的精确推断”执行。在实验中，我们表明这种简单的方案被证明非常有效，因为PC在许多标准密度估计基准上以这种方式为可拖动模型设定了新的最新模型。

由于监视摄像头网络的无处不在，从图像中计算的自动人士最近引起了现代智能城市的城市监测的注意。当前的计算机视觉技术依赖于基于深度学习的算法，这些算法估算了静止图像中的行人密度。只有一堆作品利用视频序列中的时间一致性。在这项工作中，我们提出了一个时空的细心神经网络，以估计监视视频中的行人数量。通过利用连续帧之间的时间相关性，我们在广泛使用的FDST基准上将最新的计数误差降低了5％，定位误差降低了7.5％。

深度神经网络的学习算法通常基于有误后传播（BackProp）的监督端到端随机梯度下降（SGD）培训。 Backprop算法需要大量标记的训练样本才能获得高性能。但是，在许多现实的应用中，即使有很多图像样本，很少有标签被标记，并且必须使用半监督的样品培训策略。 Hebbian学习代表了一种可能采取样本培训的方法；但是，在当前解决方案中，它不能很好地扩展到大型数据集。在本文中，我们提出了FastheBB，这是HEBBIAN学习的有效且可扩展的解决方案，通过1）合并在一批输入上更新计算和聚集，以及2）利用有效的GPU上的有效矩阵乘法算法。在半监督的学习方案中，我们在不同的计算机视觉基准测试方面验证了我们的方法。 FastheBB在训练速度方面最多优于先前的解决方案，尤其是，我们首次能够将HEBBIAN算法带入ImageNet量表。