设计在边缘硬件上运行的深神经网络（DNN）仍然是一个挑战。社区已经采用了标准设计来促进神经网络模型的部署。但是，并不是很强调适应网络拓扑以适合硬件约束。在本文中，我们适应了移动硬件平台MobilenetV2的最广泛使用的架构之一，并研究了更改其拓扑结构并应用后培训后量化的影响。我们讨论了改编和模型在嵌入式硬件平台上进行面部检测的影响。

Manually analyzing spermatozoa is a tremendous task for biologists due to the many fast-moving spermatozoa, causing inconsistencies in the quality of the assessments. Therefore, computer-assisted sperm analysis (CASA) has become a popular solution. Despite this, more data is needed to train supervised machine learning approaches in order to improve accuracy and reliability. In this regard, we provide a dataset called VISEM-Tracking with 20 video recordings of 30s of spermatozoa with manually annotated bounding-box coordinates and a set of sperm characteristics analyzed by experts in the domain. VISEM-Tracking is an extension of the previously published VISEM dataset. In addition to the annotated data, we provide unlabeled video clips for easy-to-use access and analysis of the data. As part of this paper, we present baseline sperm detection performances using the YOLOv5 deep learning model trained on the VISEM-Tracking dataset. As a result, the dataset can be used to train complex deep-learning models to analyze spermatozoa. The dataset is publicly available at https://zenodo.org/record/7293726.

子格式微型航空车（MAV）中的准确而敏捷的轨迹跟踪是具有挑战性的，因为机器人的小规模会引起大型模型不确定性，要求强大的反馈控制器，而快速的动力学和计算约束则阻止了计算上昂贵的策略的部署。在这项工作中，我们提出了一种在MIT SoftFly（一个子）MAV（0.7克）上进行敏捷和计算有效轨迹跟踪的方法。我们的策略采用了级联的控制方案，在该方案中，自适应态度控制器与受过训练的神经网络政策相结合，以模仿轨迹跟踪可靠的管模型模型预测控制器（RTMPC）。神经网络政策是使用我们最近的工作获得的，这使该政策能够保留RTMPC的稳健性，但以其计算成本的一小部分。我们通过实验评估我们的方法，即使在更具挑战性的操作中，达到均方根误差也低于1.8 cm，与我们先前的工作相比，最大位置误差减少了60％，并证明了对大型外部干扰的稳健性

语言模型既展示了定量的改进，又展示了新的定性功能，随着规模的增加。尽管它们具有潜在的变革性影响，但这些新能力的特征却很差。为了为未来的研究提供信息，为破坏性的新模型能力做准备，并改善社会有害的效果，至关重要的是，我们必须了解目前和近乎未来的能力和语言模型的局限性。为了应对这一挑战，我们介绍了超越模仿游戏基准（Big Bench）。 Big Bench目前由204个任务组成，由132家机构的442位作者贡献。任务主题是多样的，从语言学，儿童发展，数学，常识性推理，生物学，物理学，社会偏见，软件开发等等。 Big-Bench专注于被认为超出当前语言模型的功能的任务。我们评估了OpenAI的GPT型号，Google内部密集变压器体系结构和大型基础上的开关稀疏变压器的行为，跨越了数百万到数十亿个参数。此外，一个人类专家评估者团队执行了所有任务，以提供强大的基准。研究结果包括：模型性能和校准都随规模改善，但绝对的术语（以及与评估者的性能相比）；在模型类中的性能非常相似，尽管带有稀疏性。逐渐和预测的任务通常涉及大量知识或记忆成分，而在临界规模上表现出“突破性”行为的任务通常涉及多个步骤或组成部分或脆性指标；社交偏见通常会随着含糊不清的环境而随着规模而增加，但这可以通过提示来改善。

医学图像分割的深度学习模型可能会出乎意料地且出乎意料地失败，而与训练图像相比，在不同中心获得的病理案例和图像，标签错误违反了专家知识。此类错误破坏了对医学图像细分的深度学习模型的可信赖性。检测和纠正此类故障的机制对于将该技术安全地转化为诊所至关重要，并且可能是对未来人工智能法规（AI）的要求。在这项工作中，我们提出了一个值得信赖的AI理论框架和一个实用系统，该系统可以使用后备方法和基于Dempster-Shafer理论的失败机制增强任何骨干AI系统。我们的方法依赖于可信赖的AI的可行定义。我们的方法会自动放弃由骨干AI预测的体素级标签，该标签违反了专家知识，并依赖于这些体素的后备。我们证明了拟议的值得信赖的AI方法在最大的报告的胎儿MRI的注释数据集中，由13个中心的540个手动注释的胎儿脑3D T2W MRI组成。我们值得信赖的AI方法改善了在各个中心获得的胎儿脑MRI和各种脑异常的胎儿的最先进的主链AI的鲁棒性。

背景：以自我为中心的视频已成为监测社区中四肢瘫痪者的手部功能的潜在解决方案，尤其是因为它在家庭环境中检测功能使用的能力。目的：开发和验证一个基于可穿戴视力的系统，以测量四肢植物患者的家庭使用。方法：开发并比较了几种用于检测功能手动相互作用的深度学习算法。最精确的算法用于从20名参与者在家庭中记录的65小时的无脚本视频中提取手部功能的度量。这些措施是：总记录时间（PERC）的交互时间百分比；单个相互作用的平均持续时间（DUR）；每小时互动数（NUM）。为了证明技术的临床有效性，以验证的措施与经过验证的手部功能和独立性的临床评估相关（逐渐定义了强度，敏感性和预性的评估 - GRASSP，上肢运动评分 - UEM和脊髓独立措施 - SICIM- SICIM- SICIM） 。结果：手动相互作用以0.80（0.67-0.87）的中位数得分自动检测到手动相互作用。我们的结果表明，较高的UEM和更好的预性与花费更长的时间相互作用有关，而较高的cim和更好的手动感觉会导致在以eg中心的视频记录期间进行的更多相互作用。结论：第一次，在四肢瘫痪者中，在不受约束的环境中自动估计的手部功能的度量已得到了国际接受的手部功能量度的验证。未来的工作将需要对基于以自我为中心的手工使用的绩效指标的可靠性和响应能力进行正式评估。

在过去的几年中，在深度学习中，在深度学习中广泛研究了域的概括问题，但对对比增强成像的关注受到了有限的关注。但是，临床中心之间的对比度成像方案存在明显差异，尤其是在对比度注入和图像采集之间，而与可用的非对抗成像的可用数据集相比，访问多中心对比度增强图像数据受到限制。这需要新的工具来概括单个中心的深度学习模型，跨越新的看不见的域和临床中心，以对比增强成像。在本文中，我们介绍了深度学习技术的详尽评估，以实现对对比度增强图像分割的看不见的临床中心的普遍性。为此，研究，优化和系统评估了几种技术，包括数据增强，域混合，转移学习和域的适应性。为了证明域泛化对对比增强成像的潜力，评估了对对比增强心脏磁共振成像（MRI）中的心室分割的方法。结果是根据位于三个国家（法国，西班牙和中国）的四家医院中获得的多中心心脏对比增强的MRI数据集获得的。他们表明，数据增强和转移学习的组合可以导致单中心模型，这些模型可以很好地推广到训练过程中未包括的新临床中心。在对比增强成像中，具有合适的概括程序的单域神经网络可以达到甚至超过多中心多供应商模型的性能，从而消除了对综合多中心数据集的需求，以训练可概括的模型。

Computational units in artificial neural networks follow a simplified model of biological neurons. In the biological model, the output signal of a neuron runs down the axon, splits following the many branches at its end, and passes identically to all the downward neurons of the network. Each of the downward neurons will use their copy of this signal as one of many inputs dendrites, integrate them all and fire an output, if above some threshold. In the artificial neural network, this translates to the fact that the nonlinear filtering of the signal is performed in the upward neuron, meaning that in practice the same activation is shared between all the downward neurons that use that signal as their input. Dendrites thus play a passive role. We propose a slightly more complex model for the biological neuron, where dendrites play an active role: the activation in the output of the upward neuron becomes optional, and instead the signals going through each dendrite undergo independent nonlinear filterings, before the linear combination. We implement this new model into a ReLU computational unit and discuss its biological plausibility. We compare this new computational unit with the standard one and describe it from a geometrical point of view. We provide a Keras implementation of this unit into fully connected and convolutional layers and estimate their FLOPs and weights change. We then use these layers in ResNet architectures on CIFAR-10, CIFAR-100, Imagenette, and Imagewoof, obtaining performance improvements over standard ResNets up to 1.73%. Finally, we prove a universal representation theorem for continuous functions on compact sets and show that this new unit has more representational power than its standard counterpart.

Humans have internal models of robots (like their physical capabilities), the world (like what will happen next), and their tasks (like a preferred goal). However, human internal models are not always perfect: for example, it is easy to underestimate a robot's inertia. Nevertheless, these models change and improve over time as humans gather more experience. Interestingly, robot actions influence what this experience is, and therefore influence how people's internal models change. In this work we take a step towards enabling robots to understand the influence they have, leverage it to better assist people, and help human models more quickly align with reality. Our key idea is to model the human's learning as a nonlinear dynamical system which evolves the human's internal model given new observations. We formulate a novel optimization problem to infer the human's learning dynamics from demonstrations that naturally exhibit human learning. We then formalize how robots can influence human learning by embedding the human's learning dynamics model into the robot planning problem. Although our formulations provide concrete problem statements, they are intractable to solve in full generality. We contribute an approximation that sacrifices the complexity of the human internal models we can represent, but enables robots to learn the nonlinear dynamics of these internal models. We evaluate our inference and planning methods in a suite of simulated environments and an in-person user study, where a 7DOF robotic arm teaches participants to be better teleoperators. While influencing human learning remains an open problem, our results demonstrate that this influence is possible and can be helpful in real human-robot interaction.

While the brain connectivity network can inform the understanding and diagnosis of developmental dyslexia, its cause-effect relationships have not yet enough been examined. Employing electroencephalography signals and band-limited white noise stimulus at 4.8 Hz (prosodic-syllabic frequency), we measure the phase Granger causalities among channels to identify differences between dyslexic learners and controls, thereby proposing a method to calculate directional connectivity. As causal relationships run in both directions, we explore three scenarios, namely channels' activity as sources, as sinks, and in total. Our proposed method can be used for both classification and exploratory analysis. In all scenarios, we find confirmation of the established right-lateralized Theta sampling network anomaly, in line with the temporal sampling framework's assumption of oscillatory differences in the Theta and Gamma bands. Further, we show that this anomaly primarily occurs in the causal relationships of channels acting as sinks, where it is significantly more pronounced than when only total activity is observed. In the sink scenario, our classifier obtains 0.84 and 0.88 accuracy and 0.87 and 0.93 AUC for the Theta and Gamma bands, respectively.