MRI中胎儿结构的体积测量很耗时，并且容易发生错误，因此需要自动分割。由于胎盘模糊边界和胎儿脑皮层复杂的褶皱，胎盘分割和准确的胎儿脑分割进行回旋评估特别具有挑战性。在本文中，我们研究了对问题的轮廓骰子损失的使用，并将其与其他边界损失以及联合骰子和横向内向损失进行比较。通过侵蚀，扩张和XOR操作员有效地计算出每个切片的损失。我们描述了类似于轮廓骰子指标的损失的新公式。骰子损失和轮廓骰子的组合为胎盘分割提供了最佳性能。对于胎儿脑部分割，最佳性能的损失是结合骰子丢失，随后是骰子和轮廓骰子损失的骰子，其性能比其他边界损失更好。

深度学习方法已被证明可以有效地分割医学成像中的结构和病理。但是，它们需要大量注释的数据集，其手动分割是一项繁琐且耗时的任务，尤其是对于大型结构。我们提出了一种新的部分注释方法，该方法使用每次扫描中的一小部分连续注释切片，其注释工作仅等于很少的注释情况。通过仅使用带注释的块进行部分注释的培训，将有关切片的信息包含在感兴趣的结构之外，并修改批处理损失函数以仅考虑带注释的切片。为了促进低数据制度中的培训，我们使用两步优化过程。我们用两个MRI序列Trufi和Fiesta用流行的软骰子损失测试了该方法，并将完整的注释状态与部分注释与类似的注释工作进行了比较。对于TRUFI数据，与完整注释相比，部分注释的使用平均表现稍好一些，骰子得分从0.936增加到0.942，并且骰子的标准偏差（STD）大幅下降22％，平均对称表面距离（ASSD）提高15％。对于嘉年华的序列，部分注释还会在分布数据中分别降低骰子分数和ASSD指标的STD和ASSD指标分别降低27.5％和33％骰子得分从0.84到0.9，从7.46降低到4.01毫米。两步优化过程有助于部分注释分别分配和分布数据。因此，建议使用两步优化器的部分注释方法在低数据制度下改善分割性能。

正常的胎儿脂肪组织（AT）发育对于围产期健康至关重要。在或简单地脂肪以脂质形式存储能量。营养不良可能导致过度或耗尽的肥胖。尽管以前的研究表明，AT和围产期结局的量之间存在相关性，但缺乏定量方法，对AT的产前评估受到限制。使用磁共振成像（MRI），可以从两个点Dixon图像中获得整个胎儿的3D脂肪和纯水图像，以在脂质定量时启用。本文是第一个提出一种基于Dixon MRI的胎儿脂肪分割的深度学习方法的方法。它优化了放射科医生的手动胎儿脂肪描述时间，以生成带注释的培训数据集。它由两个步骤组成：1）基于模型的半自动胎儿脂肪分割，由放射科医生进行了审查和纠正； 2）使用在所得的注释数据集中训练的DL网络的自动胎儿脂肪分割。培训了三个DL网络。与手动分割相比，我们显示出分割时间（3:38小时至<1小时）和观察者变异性（0.738至0.906）的显着改善。用3D残差U-NET，NN-UNET和SWIN-UNETR TRONSERTER网络对24个测试用例进行自动分割，平均骰子得分分别为0.863、0.787和0.856。这些结果比手动观察者的变异性更好，并且与自动成人和小儿脂肪分割相当。一名放射科医生审查并纠正了六个新的独立案例，并使用最佳性能网络进行了细分，导致骰子得分为0.961，校正时间显着减少了15:20分钟。使用这些新颖的分割方法和短暂的MRI获取时间，可以在临床和大型果园研究中量化全身皮下脂质的单个胎儿。

超声检查的胎儿生长评估是基于一些生物特征测量，这些测量是手动进行并相对于预期的妊娠年龄进行的。可靠的生物特征估计取决于标准超声平面中地标的精确检测。手动注释可能是耗时的和依赖操作员的任务，并且可能导致高测量可变性。现有的自动胎儿生物特征法的方法依赖于初始自动胎儿结构分割，然后是几何标记检测。但是，分割注释是耗时的，可能是不准确的，具有里程碑意义的检测需要开发特定于测量的几何方法。本文描述了Biometrynet，这是一个克服这些局限性的胎儿生物特征估计的端到端地标回归框架。它包括一种新型的动态定向测定（DOD）方法，用于在网络训练过程中执行测量特定方向的一致性。 DOD可降低网络训练中的变异性，提高标志性的定位精度，从而产生准确且健壮的生物特征测量。为了验证我们的方法，我们组装了一个来自1,829名受试者的3,398张超声图像的数据集，这些受试者在三个具有七个不同超声设备的临床部位收购。在两个独立数据集上的三个不同生物识别测量值的比较和交叉验证表明，生物元网络是稳健的，并且产生准确的测量结果，其误差低于临床上允许的误差，优于其他现有的自动化生物测定估计方法。代码可从https://github.com/netanellavisdris/fetalbiometry获得。

In this paper we take the first steps in studying a new approach to synthesis of efficient communication schemes in multi-agent systems, trained via reinforcement learning. We combine symbolic methods with machine learning, in what is referred to as a neuro-symbolic system. The agents are not restricted to only use initial primitives: reinforcement learning is interleaved with steps to extend the current language with novel higher-level concepts, allowing generalisation and more informative communication via shorter messages. We demonstrate that this approach allow agents to converge more quickly on a small collaborative construction task.

In order for artificial neural networks to begin accurately mimicking biological ones, they must be able to adapt to new exigencies without forgetting what they have learned from previous training. Lifelong learning approaches to artificial neural networks attempt to strive towards this goal, yet have not progressed far enough to be realistically deployed for natural language processing tasks. The proverbial roadblock of catastrophic forgetting still gate-keeps researchers from an adequate lifelong learning model. While efforts are being made to quell catastrophic forgetting, there is a lack of research that looks into the importance of class ordering when training on new classes for incremental learning. This is surprising as the ordering of "classes" that humans learn is heavily monitored and incredibly important. While heuristics to develop an ideal class order have been researched, this paper examines class ordering as it relates to priming as a scheme for incremental class learning. By examining the connections between various methods of priming found in humans and how those are mimicked yet remain unexplained in life-long machine learning, this paper provides a better understanding of the similarities between our biological systems and the synthetic systems while simultaneously improving current practices to combat catastrophic forgetting. Through the merging of psychological priming practices with class ordering, this paper is able to identify a generalizable method for class ordering in NLP incremental learning tasks that consistently outperforms random class ordering.

Low Earth Orbit (LEO) constellations, each comprising a large number of satellites, have become a new source of big data "from the sky". Downloading such data to a ground station (GS) for big data analytics demands very high bandwidth and involves large propagation delays. Federated Learning (FL) offers a promising solution because it allows data to stay in-situ (never leaving satellites) and it only needs to transmit machine learning model parameters (trained on the satellites' data). However, the conventional, synchronous FL process can take several days to train a single FL model in the context of satellite communication (Satcom), due to a bottleneck caused by straggler satellites. In this paper, we propose an asynchronous FL framework for LEO constellations called AsyncFLEO to improve FL efficiency in Satcom. Not only does AsynFLEO address the bottleneck (idle waiting) in synchronous FL, but it also solves the issue of model staleness caused by straggler satellites. AsyncFLEO utilizes high-altitude platforms (HAPs) positioned "in the sky" as parameter servers, and consists of three technical components: (1) a ring-of-stars communication topology, (2) a model propagation algorithm, and (3) a model aggregation algorithm with satellite grouping and staleness discounting. Our extensive evaluation with both IID and non-IID data shows that AsyncFLEO outperforms the state of the art by a large margin, cutting down convergence delay by 22 times and increasing accuracy by 40%.

Reinforcement Learning (RL) algorithms are known to scale poorly to environments with many available actions, requiring numerous samples to learn an optimal policy. The traditional approach of considering the same fixed action space in every possible state implies that the agent must understand, while also learning to maximize its reward, to ignore irrelevant actions such as $\textit{inapplicable actions}$ (i.e. actions that have no effect on the environment when performed in a given state). Knowing this information can help reduce the sample complexity of RL algorithms by masking the inapplicable actions from the policy distribution to only explore actions relevant to finding an optimal policy. This is typically done in an ad-hoc manner with hand-crafted domain logic added to the RL algorithm. In this paper, we propose a more systematic approach to introduce this knowledge into the algorithm. We (i) standardize the way knowledge can be manually specified to the agent; and (ii) present a new framework to autonomously learn these state-dependent action constraints jointly with the policy. We show experimentally that learning inapplicable actions greatly improves the sample efficiency of the algorithm by providing a reliable signal to mask out irrelevant actions. Moreover, we demonstrate that thanks to the transferability of the knowledge acquired, it can be reused in other tasks to make the learning process more efficient.

Point cloud completion, as the upstream procedure of 3D recognition and segmentation, has become an essential part of many tasks such as navigation and scene understanding. While various point cloud completion models have demonstrated their powerful capabilities, their robustness against adversarial attacks, which have been proven to be fatally malicious towards deep neural networks, remains unknown. In addition, existing attack approaches towards point cloud classifiers cannot be applied to the completion models due to different output forms and attack purposes. In order to evaluate the robustness of the completion models, we propose PointCA, the first adversarial attack against 3D point cloud completion models. PointCA can generate adversarial point clouds that maintain high similarity with the original ones, while being completed as another object with totally different semantic information. Specifically, we minimize the representation discrepancy between the adversarial example and the target point set to jointly explore the adversarial point clouds in the geometry space and the feature space. Furthermore, to launch a stealthier attack, we innovatively employ the neighbourhood density information to tailor the perturbation constraint, leading to geometry-aware and distribution-adaptive modifications for each point. Extensive experiments against different premier point cloud completion networks show that PointCA can cause a performance degradation from 77.9% to 16.7%, with the structure chamfer distance kept below 0.01. We conclude that existing completion models are severely vulnerable to adversarial examples, and state-of-the-art defenses for point cloud classification will be partially invalid when applied to incomplete and uneven point cloud data.

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.