基于模拟的推理的神经后验估计方法可能不适合通过在多个观测值上进行条件来处理后验分布，因为它们可能需要大量的模拟器调用以产生准确的近似值。神经可能性估计方法可以自然处理多个观察结果，但需要单独的推论步骤，这可能会影响其效率和性能。我们引入了一种基于模拟的推理的新方法，该方法享有两种方法的好处。我们建议对单个观察值引起的后验分布进行建模，并引入采样算法，该算法将学习分数结合在一起以有效地从目标中进行样本。

高效地培训专家模型的大规模混合，现代硬件需要将数据点分配给不同的专家，每个专家都具有有限的容量。最近提出的任务程序缺乏概率解释和使用偏见估算进行培训。作为替代方案，我们提出了基于原则的随机分配程序的两个无偏的估计，其中跳过超过专家容量的DataPoints，以及使用Gumbel匹配分布的延伸来示范完全平衡的作业[29]。两个估算器都是无偏见的，因为它们纠正了使用的采样程序。在玩具实验中，我们发现“Skip'-Expliesator比平衡采样更有效，并且在解决任务方面比偏置替代方案更加强大。

We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show that it improves upon β-VAE by providing a better trade-off between disentanglement and reconstruction quality. Moreover, we highlight the problems of a commonly used disentanglement metric and introduce a new metric that does not suffer from them.

The reparameterization trick enables optimizing large scale stochastic computation graphs via gradient descent. The essence of the trick is to refactor each stochastic node into a differentiable function of its parameters and a random variable with fixed distribution. After refactoring, the gradients of the loss propagated by the chain rule through the graph are low variance unbiased estimators of the gradients of the expected loss. While many continuous random variables have such reparameterizations, discrete random variables lack useful reparameterizations due to the discontinuous nature of discrete states. In this work we introduce CONCRETE random variables-CONtinuous relaxations of disCRETE random variables. The Concrete distribution is a new family of distributions with closed form densities and a simple reparameterization. Whenever a discrete stochastic node of a computation graph can be refactored into a one-hot bit representation that is treated continuously, Concrete stochastic nodes can be used with automatic differentiation to produce low-variance biased gradients of objectives (including objectives that depend on the log-probability of latent stochastic nodes) on the corresponding discrete graph. We demonstrate the effectiveness of Concrete relaxations on density estimation and structured prediction tasks using neural networks.

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.

Federated learning (FL) enables the building of robust and generalizable AI models by leveraging diverse datasets from multiple collaborators without centralizing the data. We created NVIDIA FLARE as an open-source software development kit (SDK) to make it easier for data scientists to use FL in their research and real-world applications. The SDK includes solutions for state-of-the-art FL algorithms and federated machine learning approaches, which facilitate building workflows for distributed learning across enterprises and enable platform developers to create a secure, privacy-preserving offering for multiparty collaboration utilizing homomorphic encryption or differential privacy. The SDK is a lightweight, flexible, and scalable Python package, and allows researchers to bring their data science workflows implemented in any training libraries (PyTorch, TensorFlow, XGBoost, or even NumPy) and apply them in real-world FL settings. This paper introduces the key design principles of FLARE and illustrates some use cases (e.g., COVID analysis) with customizable FL workflows that implement different privacy-preserving algorithms. Code is available at https://github.com/NVIDIA/NVFlare.

头颈肿瘤分割挑战（Hecktor）2022为研究人员提供了一个平台，可以将其解决方案与3D CT和PET图像的肿瘤和淋巴结分割。在这项工作中，我们描述了针对Hecktor 2022分割任务的解决方案。我们将所有图像重新样本为共同的分辨率，在头颈部和颈部区域周围的作物，并从Monai训练Segresnet语义分割网络。我们使用5倍的交叉验证来选择最佳模型检查点。最终提交是3次运行中的15个型号的合奏。我们的解决方案（NVAUTO团队名称）以0.78802的汇总骰子得分在Hecktor22挑战排行榜上获得第一名。

颅内出血分割挑战（实例2022）为研究人员提供了一个平台，以将其解决方案与3D CTS的出血中风区域进行分割。在这项工作中，我们将解决方案描述为实例2022。我们使用2D分割网络，来自Monai的Segresnet，在不重采样的情况下操作切片。最终提交是18个模型的合奏。我们的解决方案（NVAUTO团队名称）在骰子度量标准（0.721）和总排名2方面获得了最高位置。

缺血性中风病变细分挑战（Isles 2022）为研究人员提供了一个平台，可以将其解决方案与3D MRI的缺血性中风区域进行比较。在这项工作中，我们描述了我们对2022分段任务的解决方案。我们将所有图像重新样本为一个共同的分辨率，使用两种输入MRI模式（DWI和ADC），并使用MONAI的Train Segresnet语义分割网络。最终提交是15个模型的合奏（来自3倍交叉验证的3次运行）。我们的解决方案（NVAUTO团队名称）在骰子度量标准（0.824）和总排名第2（基于合并的度量排名）方面获得了最高位置。

已经提出了分裂学习（SL）以分散的方式训练深度学习模型。对于具有垂直数据分配的分散医疗保健应用，SL可以有益，因为它允许具有互补功能或图像的机构为一组共享的患者共同开发更强大且可推广的模型。在这项工作中，我们提出了“ split-u-net”，并成功地将SL应用于协作生物医学图像分割。但是，SL需要交换中间激活图和梯度，以允许跨不同特征空间的训练模型，这可能会泄漏数据并提高隐私问题。因此，我们还量化了用于生物医学图像分割的常见SL情况下的数据泄漏量，并通过应用适当的防御策略提供了抵消此类泄漏的方法。