Artificial Intelligence (AI) is having a tremendous impact across most areas of science. Applications of AI in healthcare have the potential to improve our ability to detect, diagnose, prognose, and intervene on human disease. For AI models to be used clinically, they need to be made safe, reproducible and robust, and the underlying software framework must be aware of the particularities (e.g. geometry, physiology, physics) of medical data being processed. This work introduces MONAI, a freely available, community-supported, and consortium-led PyTorch-based framework for deep learning in healthcare. MONAI extends PyTorch to support medical data, with a particular focus on imaging, and provide purpose-specific AI model architectures, transformations and utilities that streamline the development and deployment of medical AI models. MONAI follows best practices for software-development, providing an easy-to-use, robust, well-documented, and well-tested software framework. MONAI preserves the simple, additive, and compositional approach of its underlying PyTorch libraries. MONAI is being used by and receiving contributions from research, clinical and industrial teams from around the world, who are pursuing applications spanning nearly every aspect of healthcare.

修剪技术可全面使用图像分类压缩卷积神经网络（CNN）。但是，大多数修剪方法需要一个经过良好训练的模型，以提供有用的支持参数，例如C1-核心，批处理值和梯度信息，如果预训练的模型的参数为，这可能会导致过滤器评估的不一致性不太优化。因此，我们提出了一种基于敏感性的方法，可以通过为原始模型增加额外的损害来评估每一层的重要性。由于准确性的性能取决于参数在所有层而不是单个参数中的分布，因此基于灵敏度的方法将对参数的更新具有鲁棒性。也就是说，我们可以获得对不完美训练和完全训练的模型之间每个卷积层的相似重要性评估。对于CIFAR-10上的VGG-16，即使原始模型仅接受50个时期训练，我们也可以对层的重要性进行相同的评估，并在对模型进行充分训练时的结果。然后，我们将通过量化的灵敏度从每一层中删除过滤器。我们基于敏感性的修剪框架在VGG-16，分别具有CIFAR-10，MNIST和CIFAR-100的VGG-16上有效验证。

本文对我们的系统进行了概述和比较分析，该系统专为Sapien Maniskill Challenge挑战2021中的以下两个轨道而设计：无相互作用轨迹：从预采用的演示轨迹中学习政策的无相互作用轨迹目标。我们研究了这两个基于模仿学习的方法，即使用经典监督学习技术模仿观察到的行为，以及基于线之后的基于强化学习的方法。此外，通过基于变压器的网络利用对象和机器人臂的几何结构和纹理结构，以促进模仿学习。无限制轨道：在此轨道中，我们设计了一种基于启发式规则的方法（HRM）来通过将任务分解为一系列子任务来触发高质量对象操作。对于每个子任务，采用简单的基于规则的控制策略来预测可以应用于机器人臂的动作。为了简化系统的实现，所有源代码和预训练的模型均可在\ url {https://github.com/caiqi/silver-bullet-3d/}上获得。

图像变压器最近使用监督（VIT，DEIT等）或自我监督（BEIT，MAE等）预训练技术取得了显着的自然图像理解进展。在本文中，我们提出了\ textbf {dit}，一种自我保护的预训练\ textbf {d} ocument \ textbf {i} mage \ textbf {t} ransformer模型，使用大规模的不尺度的文本图像用于文档AI任务，这是必不可少的，因为由于缺乏人类标记的文档图像，因此没有受到监督的同行。我们将DIT作为骨干网络在各种基于视觉的文档AI任务中，包括文档图像分类，文档布局分析，表检测以及OCR的文本检测。实验结果表明，自我监管的预训练的DIT模型可在这些下游任务上实现新的最新结果，例如文档图像分类（91.11 $ \ rightarrow $ 92.69），文档布局分析（91.0 $ \ rightArow $ 94.9），表检测（94.23 $ \ rightArrow $ 96.55）和OCR的文本检测（93.07 $ \ rightarrow $ 94.29）。代码和预培训模型可在\ url {https://aka.ms/msdit}上公开获得。

运动，作为视频中最明显的现象，涉及随时间的变化，对视频表示学习的发展是独一无二的。在本文中，我们提出了问题：特别是对自我监督视频表示学习的运动有多重要。为此，我们撰写了一个二重奏，用于利用对比学习政权的数据增强和特征学习的动作。具体而言，我们介绍了一种以前的对比学习（MCL）方法，其将这种二重奏视为基础。一方面，MCL大写视频中的每个帧的光流量，以在时间上和空间地样本地样本（即，横跨时间的相关帧斑块的序列）作为数据增强。另一方面，MCL进一步将卷积层的梯度图对准来自空间，时间和时空视角的光流程图，以便在特征学习中地进行地面运动信息。在R（2 + 1）D骨架上进行的广泛实验证明了我们MCL的有效性。在UCF101上，在MCL学习的表示上培训的线性分类器实现了81.91％的前1个精度，表现优于6.78％的训练预测。在动力学-400上，MCL在线方案下实现66.62％的前1个精度。代码可在https://github.com/yihengzhang-cv/mcl-motion-focused-contrastive-learning。

虽然近年来，深层加强学习代理人取得了前所未有的成功，但他们所学的政策可能是脆弱的，甚至无法概括到甚至略微修改他们的环境或不熟悉的情况。神经网络学习动态的黑匣子性质使得无法审核培训的深层代理并从这种失败中恢复过来。在本文中，我们提出了一种新颖的表示和学习方法来捕获环境动态而不使用神经网络。它起源于观察，在为人们设计的游戏中，动作的效果通常可以以连续的视觉观测的局部变化的形式感知。我们的算法旨在提取基于视觉的更改，并将其冷凝成一组依赖于依赖的描述性规则，我们调用“Visual Rewrite规则”（VRRS）。我们还提出了可以探索，扩展其规则集的VRR代理的初步结果，并通过规划与其学习的VRR世界模型来解决游戏。在若干古典游戏中，与几个主流深层代理相比，我们的非深度代理商证明了卓越的性能，极端样品效率和鲁棒泛化能力。

移动和金融技术的繁荣已经为更广泛的人们培育和扩展了各种金融产品，这有助于倡导金融包容。它具有递减金融不平等的非琐碎的社会效益。然而，由独特的特征分布和新用户的信用史有限造成的个人金融风险评估的技术挑战，以及新用户的缺乏经验，在处理复杂数据和获得准确的标签方面，妨碍了进一步推动金融包容性。为了解决这些挑战，本文开发了一种新颖的转移学习算法（即转换），其结合了基于树的模型和内核方法的优点。 Transpoost设计具有平行树结构和有效的重量更新机制，具有理论上的保证，使其能够以$ O（n）$时间复杂度的高维特征和稀疏性在解决现实世界数据中。我们对两个公共数据集进行了广泛的实验，以及腾讯移动支付的独特大规模数据集。结果表明，在具有卓越效率的预测精度方面，转换越野越优于其他最先进的基准传输学习算法，表现出对数据稀疏性的更强的鲁棒性，并提供有意义的模型解释。此外，鉴于财务风险等级，转博稳定使金融服务提供商能够满足最多的用户，包括其他算法。也就是说，转船改善了金融包容性。

Objective: Traumatic brain injury can be caused by head impacts, but many brain injury risk estimation models are not equally accurate across the variety of impacts that patients may undergo and the characteristics of different types of impacts are not well studied. We investigated the spectral characteristics of different head impact types with kinematics classification. Methods: Data was analyzed from 3,262 head impacts from lab reconstruction, American football, mixed martial arts, and publicly available car crash data. A random forest classifier with spectral densities of linear acceleration and angular velocity was built to classify head impact types (e.g., football, car crash, mixed martial arts). To test the classifier robustness, another 271 lab-reconstructed impacts were obtained from 5 other instrumented mouthguards. Finally, with the classifier, type-specific, nearest-neighbor regression models were built for brain strain. Results: The classifier reached a median accuracy of 96% over 1,000 random partitions of training and test sets. The most important features in the classification included both low-frequency and high-frequency features, both linear acceleration features and angular velocity features. Different head impact types had different distributions of spectral densities in low-frequency and high-frequency ranges (e.g., the spectral densities of MMA impacts were higher in high-frequency range than in the low-frequency range). The type-specific regression showed a generally higher R^2-value than baseline models without classification. Conclusion: The machine-learning-based classifier enables a better understanding of the impact kinematics spectral density in different sports, and it can be applied to evaluate the quality of impact-simulation systems and on-field data augmentation.

We study a multi-agent reinforcement learning (MARL) problem where the agents interact over a given network. The goal of the agents is to cooperatively maximize the average of their entropy-regularized long-term rewards. To overcome the curse of dimensionality and to reduce communication, we propose a Localized Policy Iteration (LPI) algorithm that provably learns a near-globally-optimal policy using only local information. In particular, we show that, despite restricting each agent's attention to only its $\kappa$-hop neighborhood, the agents are able to learn a policy with an optimality gap that decays polynomially in $\kappa$. In addition, we show the finite-sample convergence of LPI to the global optimal policy, which explicitly captures the trade-off between optimality and computational complexity in choosing $\kappa$. Numerical simulations demonstrate the effectiveness of LPI.

Using functional magnetic resonance imaging (fMRI) and deep learning to explore functional brain networks (FBNs) has attracted many researchers. However, most of these studies are still based on the temporal correlation between the sources and voxel signals, and lack of researches on the dynamics of brain function. Due to the widespread local correlations in the volumes, FBNs can be generated directly in the spatial domain in a self-supervised manner by using spatial-wise attention (SA), and the resulting FBNs has a higher spatial similarity with templates compared to the classical method. Therefore, we proposed a novel Spatial-Temporal Convolutional Attention (STCA) model to discover the dynamic FBNs by using the sliding windows. To validate the performance of the proposed method, we evaluate the approach on HCP-rest dataset. The results indicate that STCA can be used to discover FBNs in a dynamic way which provide a novel approach to better understand human brain.