尽管具有优势，但正常化的流量通常会遇到几个缺点，包括它们产生不现实数据（例如图像）的趋势及其未能检测到分布数据的数据。这些缺陷的原因之一在于培训策略传统上仅利用最大似然原则。本文提出了一个新的训练范式，该训练范式基于结合最大似然原理（MLE）和切成薄片的距离的混合目标函数。在合成玩具示例和真实图像数据集上获得的结果在生成样品的可能性和视觉方面都显示出更好的生成能力。相度地，提出的方法导致分布数据的可能性较低，表明所得流的数据保真度更高。

最佳运输（OT）提供了比较和映射概率度量的有效工具。我们建议利用神经网络的灵活性学习近似的最佳传输图。更确切地说，我们提出了一种新的原始方法，以解决将有限的样本集与第一个基础未知分布相关的有限样本，向另一个未知分布中绘制的有限样本集有关。我们表明，可逆神经网络的特定实例，即归一化流，可用于近似一对经验分布之间的该OT问题的解决方案。为此，我们建议通过通过最小化相应的瓦斯坦距离来替换推送前措施的相等性约束来放松OT的蒙加公式。然后将要检索的推向运算符被限制为正常化的流，该流程通过优化所得的成本函数来训练。这种方法允许将传输图离散作为函数的组成。这些功能中的每一个都与网络的一个子流有关，其输出提供了原始测量和目标度量之间传输的中间步骤。这种离散化也产生了两种感兴趣量度之间的一组中间重点。在玩具示例上进行的实验以及无监督翻译的具有挑战性的任务证明了该方法的兴趣。最后，一些实验表明，提出的方法导致了真实OT的良好近似值。

在地球观察的背景下，检测变化是从具有不同特征和模态的传感器获得的多阶段图像进行的。即使限制了光学方式，一旦传感器提供不同的空间和/或频谱分辨率的图像，该任务也已被证明是具有挑战性的。本文提出了一种新颖的无监督变更检测方法，该方法专用于这种所谓的异质光学图像。该方法利用了最新进展，将变更检测问题构成了强大的融合框架。更确切地说，我们表明，事先设计和训练的深层对抗网络可以通过具有相同体系结构的网络轻松地互补，以融合一对多播放图像，以执行更改检测。最终的整体体系结构本身遵循一种对抗性策略，其中融合网络和附加网络被解释为发电机的基本构建块。与最先进的变更检测方法的比较证明了所提出方法的多功能性和有效性。

This article formulates a generic representation of a path-following controller operating under contained motion, which was developed in the context of surgical robotics. It reports two types of constrained motion: i) Bilateral Constrained Motion, also called Remote Center Motion (RCM), and ii) Unilaterally Constrained Motion (UCM). In the first case, the incision hole has almost the same diameter as the robotic tool. In contrast, in the second state, the diameter of the incision orifice is larger than the tool diameter. The second case offers more space where the surgical instrument moves freely without constraints before touching the incision wall. The proposed method combines two tasks that must operate hierarchically: i) respect the RCM or UCM constraints formulated by equality or inequality, respectively, and ii) perform a surgical assignment, e.g., scanning or ablation expressed as a 3D path-following task. The proposed methods and materials were tested first on our simulator that mimics realistic conditions of middle ear surgery, and then on an experimental platform. Different validation scenarios were carried out experimentally to assess quantitatively and qualitatively each developed approach. Although ultimate precision was not the goal of this work, our concept is validated with enough accuracy (inferior to 100 micrometres) for ear surgery.

Several self-supervised representation learning methods have been proposed for reinforcement learning (RL) with rich observations. For real-world applications of RL, recovering underlying latent states is crucial, particularly when sensory inputs contain irrelevant and exogenous information. In this work, we study how information bottlenecks can be used to construct latent states efficiently in the presence of task-irrelevant information. We propose architectures that utilize variational and discrete information bottlenecks, coined as RepDIB, to learn structured factorized representations. Exploiting the expressiveness bought by factorized representations, we introduce a simple, yet effective, bottleneck that can be integrated with any existing self-supervised objective for RL. We demonstrate this across several online and offline RL benchmarks, along with a real robot arm task, where we find that compressed representations with RepDIB can lead to strong performance improvements, as the learned bottlenecks help predict only the relevant state while ignoring irrelevant information.

To face the dependency on fossil fuels and limit carbon emissions, fuel cells are a very promising technology and appear to be a key candidate to tackle the increase of the energy demand and promote the energy transition. To meet future needs for both transport and stationary applications, the time to market of fuel cell stacks must be drastically reduced. Here, a new concept to shorten their development time by introducing a disruptive and highefficiency data augmentation approach based on artificial intelligence is presented. Our results allow reducing the testing time before introducing a product on the market from a thousand to a few hours. The innovative concept proposed here can support engineering and research tasks during the fuel cell development process to achieve decreased development costs alongside a reduced time to market.

A learned system uses machine learning (ML) internally to improve performance. We can expect such systems to be vulnerable to some adversarial-ML attacks. Often, the learned component is shared between mutually-distrusting users or processes, much like microarchitectural resources such as caches, potentially giving rise to highly-realistic attacker models. However, compared to attacks on other ML-based systems, attackers face a level of indirection as they cannot interact directly with the learned model. Additionally, the difference between the attack surface of learned and non-learned versions of the same system is often subtle. These factors obfuscate the de-facto risks that the incorporation of ML carries. We analyze the root causes of potentially-increased attack surface in learned systems and develop a framework for identifying vulnerabilities that stem from the use of ML. We apply our framework to a broad set of learned systems under active development. To empirically validate the many vulnerabilities surfaced by our framework, we choose 3 of them and implement and evaluate exploits against prominent learned-system instances. We show that the use of ML caused leakage of past queries in a database, enabled a poisoning attack that causes exponential memory blowup in an index structure and crashes it in seconds, and enabled index users to snoop on each others' key distributions by timing queries over their own keys. We find that adversarial ML is a universal threat against learned systems, point to open research gaps in our understanding of learned-systems security, and conclude by discussing mitigations, while noting that data leakage is inherent in systems whose learned component is shared between multiple parties.

In intensively managed forests in Europe, where forests are divided into stands of small size and may show heterogeneity within stands, a high spatial resolution (10 - 20 meters) is arguably needed to capture the differences in canopy height. In this work, we developed a deep learning model based on multi-stream remote sensing measurements to create a high-resolution canopy height map over the "Landes de Gascogne" forest in France, a large maritime pine plantation of 13,000 km$^2$ with flat terrain and intensive management. This area is characterized by even-aged and mono-specific stands, of a typical length of a few hundred meters, harvested every 35 to 50 years. Our deep learning U-Net model uses multi-band images from Sentinel-1 and Sentinel-2 with composite time averages as input to predict tree height derived from GEDI waveforms. The evaluation is performed with external validation data from forest inventory plots and a stereo 3D reconstruction model based on Skysat imagery available at specific locations. We trained seven different U-net models based on a combination of Sentinel-1 and Sentinel-2 bands to evaluate the importance of each instrument in the dominant height retrieval. The model outputs allow us to generate a 10 m resolution canopy height map of the whole "Landes de Gascogne" forest area for 2020 with a mean absolute error of 2.02 m on the Test dataset. The best predictions were obtained using all available satellite layers from Sentinel-1 and Sentinel-2 but using only one satellite source also provided good predictions. For all validation datasets in coniferous forests, our model showed better metrics than previous canopy height models available in the same region.

Recently, extensive studies on photonic reinforcement learning to accelerate the process of calculation by exploiting the physical nature of light have been conducted. Previous studies utilized quantum interference of photons to achieve collective decision-making without choice conflicts when solving the competitive multi-armed bandit problem, a fundamental example of reinforcement learning. However, the bandit problem deals with a static environment where the agent's action does not influence the reward probabilities. This study aims to extend the conventional approach to a more general multi-agent reinforcement learning targeting the grid world problem. Unlike the conventional approach, the proposed scheme deals with a dynamic environment where the reward changes because of agents' actions. A successful photonic reinforcement learning scheme requires both a photonic system that contributes to the quality of learning and a suitable algorithm. This study proposes a novel learning algorithm, discontinuous bandit Q-learning, in view of a potential photonic implementation. Here, state-action pairs in the environment are regarded as slot machines in the context of the bandit problem and an updated amount of Q-value is regarded as the reward of the bandit problem. We perform numerical simulations to validate the effectiveness of the bandit algorithm. In addition, we propose a multi-agent architecture in which agents are indirectly connected through quantum interference of light and quantum principles ensure the conflict-free property of state-action pair selections among agents. We demonstrate that multi-agent reinforcement learning can be accelerated owing to conflict avoidance among multiple agents.

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.