Most AI systems are black boxes generating reasonable outputs for given inputs. Some domains, however, have explainability and trustworthiness requirements that cannot be directly met by these approaches. Various methods have therefore been developed to interpret black-box models after training. This paper advocates an alternative approach where the models are transparent and explainable to begin with. This approach, EVOTER, evolves rule-sets based on simple logical expressions. The approach is evaluated in several prediction/classification and prescription/policy search domains with and without a surrogate. It is shown to discover meaningful rule sets that perform similarly to black-box models. The rules can provide insight into the domain, and make biases hidden in the data explicit. It may also be possible to edit them directly to remove biases and add constraints. EVOTER thus forms a promising foundation for building trustworthy AI systems for real-world applications in the future.

本文描述了进化算法的固有力量。该功率取决于遗传编码的计算特性。有了一些编码，两个父母与简单的跨界操作员重新组合可以从儿童表型的任意分布中取样。此类编码在本文中称为\ emph {表达式编码}。通用函数近似值，包括遗传编程和神经网络的流行进化底物，可用于构建表达性编码。值得注意的是，这种方法不必仅应用于表型是一个函数的域：即使优化静态结构（例如二进制向量），也可以达到表现力。这样简单的设置使理论上表征表达性编码是可能的：在各种测试问题上，表达性编码被证明可以实现超过标准直接编码的超级指数收敛的速度。结论是，在诸如遗传编程，神经进化，遗传算法和理论之类的进化计算领域中，表达式编码可以成为理解和实现全部进化力量的关键。

命题满足（SAT）是一个NP完整的问题，它影响了许多研究领域，例如计划，验证和安全性。主流现代SAT求解器基于冲突驱动的子句学习（CDCL）算法。最近的工作旨在通过图神经网络（GNNS）产生的预测来改善其可变分支启发式方法来增强CDCL SAT求解器。但是，到目前为止，这种方法要么尚未使解决方案更有效，要么需要在线访问大量的GPU资源。为了使GNN改进实用，本文提出了一种称为Neurocomb的方法，该方法以两个见解为基础：（1）重要变量和条款的预测可以与动态分支相结合，为更有效的混合分支策略，（2）它是（2）它是足以在SAT解决开始之前仅查询神经模型一次。 NeuroComb被实施，以增强称为Minisat的经典CDCL求解器，以及最新的CDCL求解器，称为葡萄糖。结果，它允许Minisat在最近的SATCOMP-2021竞争问题设置中解决11％和葡萄糖更多的问题，仅计算资源需求只有一个GPU。因此，NeuroComb是通过机器学习改善SAT解决的有效和实用方法。

Neural networks require careful weight initialization to prevent signals from exploding or vanishing. Existing initialization schemes solve this problem in specific cases by assuming that the network has a certain activation function or topology. It is difficult to derive such weight initialization strategies, and modern architectures therefore often use these same initialization schemes even though their assumptions do not hold. This paper introduces AutoInit, a weight initialization algorithm that automatically adapts to different neural network architectures. By analytically tracking the mean and variance of signals as they propagate through the network, AutoInit appropriately scales the weights at each layer to avoid exploding or vanishing signals. Experiments demonstrate that AutoInit improves performance of convolutional, residual, and transformer networks across a range of activation function, dropout, weight decay, learning rate, and normalizer settings, and does so more reliably than data-dependent initialization methods. This flexibility allows AutoInit to initialize models for everything from small tabular tasks to large datasets such as ImageNet. Such generality turns out particularly useful in neural architecture search and in activation function discovery. In these settings, AutoInit initializes each candidate appropriately, making performance evaluations more accurate. AutoInit thus serves as an automatic configuration tool that makes design of new neural network architectures more robust. The AutoInit package provides a wrapper around TensorFlow models and is available at https://github.com/cognizant-ai-labs/autoinit.

随着神经网络分类器部署在现实世界应用中，它们可以可靠地检测到它们的故障至关重要。一个实际解决方案是为每个预测分配置信度分数，然后使用这些分数来过滤可能的错误分类。然而，现有的置信度量尚未充分可靠地对此作用。本文介绍了一种新的框架，可以产生用于检测错误分类错误的定量度量。此框架红色在基本分类器的顶部构建错误检测器，并估计使用高斯过程的检测分数的不确定性。在125 UCI数据集上具有其他错误检测方法的实验比较证明了这种方法是有效的。在两个概率基础分类器上进一步实现以及视觉任务中的两个大型深度学习架构进一步证实了该方法是坚固且可扩展的。第三，用分布外和对抗样本的红色的实证分析表明，该方法不仅可以检测错误，还可以使用，而且可以了解它们来自哪里。因此，红色可以使用未来更广泛地提高神经网络分类器的可信度。

Artificial Intelligence (AI) has become commonplace to solve routine everyday tasks. Because of the exponential growth in medical imaging data volume and complexity, the workload on radiologists is steadily increasing. We project that the gap between the number of imaging exams and the number of expert radiologist readers required to cover this increase will continue to expand, consequently introducing a demand for AI-based tools that improve the efficiency with which radiologists can comfortably interpret these exams. AI has been shown to improve efficiency in medical-image generation, processing, and interpretation, and a variety of such AI models have been developed across research labs worldwide. However, very few of these, if any, find their way into routine clinical use, a discrepancy that reflects the divide between AI research and successful AI translation. To address the barrier to clinical deployment, we have formed MONAI Consortium, an open-source community which is building standards for AI deployment in healthcare institutions, and developing tools and infrastructure to facilitate their implementation. This report represents several years of weekly discussions and hands-on problem solving experience by groups of industry experts and clinicians in the MONAI Consortium. We identify barriers between AI-model development in research labs and subsequent clinical deployment and propose solutions. Our report provides guidance on processes which take an imaging AI model from development to clinical implementation in a healthcare institution. We discuss various AI integration points in a clinical Radiology workflow. We also present a taxonomy of Radiology AI use-cases. Through this report, we intend to educate the stakeholders in healthcare and AI (AI researchers, radiologists, imaging informaticists, and regulators) about cross-disciplinary challenges and possible solutions.

Standard imitation learning can fail when the expert demonstrators have different sensory inputs than the imitating agent. This is because partial observability gives rise to hidden confounders in the causal graph. We break down the space of confounded imitation learning problems and identify three settings with different data requirements in which the correct imitation policy can be identified. We then introduce an algorithm for deconfounded imitation learning, which trains an inference model jointly with a latent-conditional policy. At test time, the agent alternates between updating its belief over the latent and acting under the belief. We show in theory and practice that this algorithm converges to the correct interventional policy, solves the confounding issue, and can under certain assumptions achieve an asymptotically optimal imitation performance.

元梯度提供了一种一般方法，以优化增强学习算法（RL）算法的元参数。元梯度的估计对于这些元算法的性能至关重要，并且已经在MAML式短距离元元RL问题的情况下进行了研究。在这种情况下，先前的工作调查了对RL目标的Hessian的估计，并通过进行抽样校正来解决信贷分配问题，以解决预先适应行为。但是，我们表明，例如由DICE及其变体实施的Hessian估计始终会增加偏差，还可以为元梯度估计增加差异。同时，在重要的长马设置中，元梯度估计的研究较少，在这种情况下，通过完整的内部优化轨迹的反向传播是不可行的。我们研究了截短的反向传播和采样校正引起的偏见和差异权衡，并与进化策略进行了比较，这是最近流行的长期替代策略。虽然先前的工作隐含地选择了这个偏见变化空间中的点，但我们解散了偏见和差异的来源，并提出了将现有估计器相互关联的经验研究。

可靠的点云数据对于机器人技术和自主驾驶应用程序中的感知任务\ textit {efextit {e.g。}至关重要。不利的天气会导致特定类型的噪声检测和范围（LIDAR）传感器数据，从而大大降低了点云的质量。为了解决这个问题，这封信提出了一种新颖的点云不利天气，使深度学习算法（4Denoisenet）。我们的算法利用了时间维度，与文献中深度学习不利的天气变质方法不同。与以前的工作相比，它的交集比联合度量的交点更好10 \％，并且在计算上更有效。这些结果是在我们的新型Snowkitti数据集上实现的，该数据集具有40000多个不良天气注释点云。此外，对加拿大不利驾驶条件数据集的强烈定性结果表明，对域移动和不同传感器内在的可推广性良好。

算法选择向导是有效且通用的工具，它们会自动选择有关该问题和可用计算资源的高级信息的优化算法，例如决策变量的数量和类型，最大程度的评估数量，并行评估等。艺术算法选择向导很复杂且难以改进。我们在这项工作中建议使用自动配置方法来通过找到构成它们的算法的更好配置来改善其性能。特别是，我们使用精英迭代赛车（IRACE）来找到特定人工基准测试的CMA配置，这些基准取代了Nevergrad平台提供的NGOPT向导中当前使用的手工制作的CMA配置。我们详细讨论了IRACE的设置，目的是生成在每个基准内的各种问题实例集合中都可以正常工作的配置。我们的方法也提高了NGOPT向导的性能，即使在不属于Irace的一部分的基准套件上。