Deep learning classifiers provide the most accurate means of automatically diagnosing diabetic retinopathy (DR) based on optical coherence tomography (OCT) and its angiography (OCTA). The power of these models is attributable in part to the inclusion of hidden layers that provide the complexity required to achieve a desired task. However, hidden layers also render algorithm outputs difficult to interpret. Here we introduce a novel biomarker activation map (BAM) framework based on generative adversarial learning that allows clinicians to verify and understand classifiers decision-making. A data set including 456 macular scans were graded as non-referable or referable DR based on current clinical standards. A DR classifier that was used to evaluate our BAM was first trained based on this data set. The BAM generation framework was designed by combing two U-shaped generators to provide meaningful interpretability to this classifier. The main generator was trained to take referable scans as input and produce an output that would be classified by the classifier as non-referable. The BAM is then constructed as the difference image between the output and input of the main generator. To ensure that the BAM only highlights classifier-utilized biomarkers an assistant generator was trained to do the opposite, producing scans that would be classified as referable by the classifier from non-referable scans. The generated BAMs highlighted known pathologic features including nonperfusion area and retinal fluid. A fully interpretable classifier based on these highlights could help clinicians better utilize and verify automated DR diagnosis.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Previous work has shown that a neural network with the rectified linear unit (ReLU) activation function leads to a convex polyhedral decomposition of the input space. These decompositions can be represented by a dual graph with vertices corresponding to polyhedra and edges corresponding to polyhedra sharing a facet, which is a subgraph of a Hamming graph. This paper illustrates how one can utilize the dual graph to detect and analyze adversarial attacks in the context of digital images. When an image passes through a network containing ReLU nodes, the firing or non-firing at a node can be encoded as a bit ($1$ for ReLU activation, $0$ for ReLU non-activation). The sequence of all bit activations identifies the image with a bit vector, which identifies it with a polyhedron in the decomposition and, in turn, identifies it with a vertex in the dual graph. We identify ReLU bits that are discriminators between non-adversarial and adversarial images and examine how well collections of these discriminators can ensemble vote to build an adversarial image detector. Specifically, we examine the similarities and differences of ReLU bit vectors for adversarial images, and their non-adversarial counterparts, using a pre-trained ResNet-50 architecture. While this paper focuses on adversarial digital images, ResNet-50 architecture, and the ReLU activation function, our methods extend to other network architectures, activation functions, and types of datasets.

细菌感染负责全球高死亡率。感染潜在的抗菌素耐药性，多方面的患者的临床状况会阻碍正确选择抗生素治疗。随机临床试验提供了平均治疗效果估计值，但对于治疗选择的风险分层和优化，即个性化治疗效果（ITE）并不理想。在这里，我们利用了从美国南部学术诊所收集的大规模电子健康记录数据，模仿临床试验，即“目标试验”，并为诊断患有急性细菌的患者开发了死亡率预测和ITE估计的机器学习模型皮肤和皮肤结构感染（ABSSI）是由于金黄色葡萄球菌（MRSA）引起的。 ABSSI-MRSA是一个充满挑战的疾病，治疗选择减少 - 万古霉素是首选的选择，但它具有不可忽略的副作用。首先，我们使用倾向评分匹配来模仿试验并创建随机治疗（万古霉素与其他抗生素）数据集。接下来，我们使用此数据来训练各种机器学习方法（包括增强/Lasso Logistic回归，支持向量机和随机森林），并通过引导验证选择接收器特征（AUC）下的面积最佳模型。最后，我们使用这些模型来计算ITE并通过改变治疗的变化来避免死亡。排出外测试表明，SVM和RF是最准确的，AUC分别为81％和78％，但BLR/Lasso不远（76％）。通过使用BLR/Lasso计算反事实，万古霉素增加了死亡的风险，但显示出很大的变化（优势比1.2，95％范围0.4-3.8），对结果概率的贡献是适度的。取而代之的是，RF在ITE中表现出更大的变化，表明更复杂的治疗异质性。

高分辨率气象雷达图像的可用性是有效的预测和决策。在超越传统雷达覆盖范围之外，生成模型已成为一种重要的合成能力，融合更普遍的数据来源，例如卫星图像和数值天气模型，进入准确的雷达样产品。在这里，我们展示了使用量子辅助模型来增强传统卷积神经网络的方法，用于全球合成天气雷达中的生成任务。我们表明Quantum Kernels原则上可以根据相关底层数据上的古典学习机来表现出基本上更复杂的任务。我们的结果建立了合成气象雷达作为量子计算能力的有效启发式基准，并在高影响力的相关问题上设定了详细量子优势基准测试的阶段。

目的：慢性主动脉疾病的监测成像，如解剖，依赖于在预定义主动脉地标随时间获得和比较预定义主动脉标志的横截面直径测量。由于缺乏鲁棒工具，横截面平面的方向由高训练的操作员手动定义。我们展示了如何有效地使用诊所中常规收集的手动注释来缓解该任务，尽管在测量中存在不可忽略的互操作器可变性。影响：通过利用不完美，回顾性的临床注释，可以缓解或自动化且重复的成像任务的弊端。方法论：在这项工作中，我们结合了卷积神经网络和不确定量化方法来预测这种横截面的取向。我们使用11个操作员随机处理的临床数据进行培训，并在3个独立运营商处理的较小集合上进行测试，以评估互通器变异性。结果：我们的分析表明，手动选择的横截面平面的特点是10.6 ^ \ CirC $ 10.6 ^ \ riC $和每角度为21.4美元的协议限额为95％我们的方法显示，静态误差减少3.57秒^ \ rIC $（$ 40.2 $％）和$ 4.11 ^ \ rIC $（$ 32.8 $％），而不是5.4 ^ \ rIC $（$ 49.0 $％）和16.0美元^ \ CIRC $（$ 74.6 $％）对手动处理。结论：这表明预先存在的注释可以是诊所的廉价资源，以便于易于提出和重复的任务，如横截面提取，以便监测主动脉夹层。

许多连续的决策问题是使用使用其他一些策略收集的历史数据，需要使用历史数据的高赌注并要求新策略（OPE）。提供无偏估计的最常见的OPE技术之一是基于轨迹的重要性采样（是）。但是，由于轨迹的高方差是估计，最近通过了基于国家行动探索分布（SIS）的重要性采样方法。不幸的是，虽然SIS经常为长视野提供较低的方差估计，但估算状态行动分配比可能是具有挑战性的并且导致偏差估计。在本文中，我们对该偏差差异进行了新的视角，并显示了存在终点是SIS的估计频谱的存在。此外，我们还建立了这些估算器的双重强大和加权版本的频谱。我们提供了经验证据，即该频谱中的估计值可用于在IS和SIS的偏差和方差之间进行折衷，并且可以实现比两者和SIS更低的平均平方误差。

脑转移性疾病的治疗决策依赖于主要器官位点的知识，目前用活组织检查和组织学进行。在这里，我们开发了一种具有全脑MRI数据的准确非侵入性数字组织学的新型深度学习方法。我们的IRB批准的单网回顾性研究由患者（n = 1,399）组成，提及MRI治疗规划和伽马刀放射牢房超过19年。对比增强的T1加权和T2加权流体减毒的反转恢复脑MRI考试（n = 1,582）被预处理，并输入肿瘤细分，模态转移和主要部位分类的建议深度学习工作流程为五个课程之一（肺，乳腺，黑色素瘤，肾等）。十倍的交叉验证产生的总体AUC为0.947（95％CI：0.938,0.955），肺类AUC，0.899（95％CI：0.884,0.915），乳房类AUC为0.990（95％CI：0.983,0.997） ，黑色素瘤ACAC为0.882（95％CI：0.858,0.906），肾类AUC为0.870（95％CI：0.823,0.918），以及0.885的其他AUC（95％CI：0.843,0.949）。这些数据确定全脑成像特征是判别的，以便准确诊断恶性肿瘤的主要器官位点。我们的端到端深度射出方法具有巨大的分类来自全脑MRI图像的转移性肿瘤类型。进一步的细化可以提供一种无价的临床工具，以加快对精密治疗和改进的结果的原发性癌症现场鉴定。

Pennylane是用于量子计算机可区分编程的Python 3软件框架。该库为近期量子计算设备提供了统一的体系结构，支持量子和连续变化的范例。 Pennylane的核心特征是能够以与经典技术（例如反向传播）兼容的方式来计算变异量子电路的梯度。因此，Pennylane扩展了在优化和机器学习中常见的自动分化算法，以包括量子和混合计算。插件系统使该框架与任何基于门的量子模拟器或硬件兼容。我们为硬件提供商提供插件，包括Xanadu Cloud，Amazon Braket和IBM Quantum，允许Pennylane优化在公开访问的量子设备上运行。在古典方面，Pennylane与加速的机器学习库（例如Tensorflow，Pytorch，Jax和Autograd）接口。 Pennylane可用于优化变分的量子本素体，量子近似优化，量子机学习模型和许多其他应用。

We demonstrate a proof-of-concept of a large language model conducting corporate lobbying related activities. We use an autoregressive large language model (OpenAI's text-davinci-003) to determine if proposed U.S. Congressional bills are relevant to specific public companies and provide explanations and confidence levels. For the bills the model deems as relevant, the model drafts a letter to the sponsor of the bill in an attempt to persuade the congressperson to make changes to the proposed legislation. We use hundreds of ground-truth labels of the relevance of a bill to a company to benchmark the performance of the model, which outperforms the baseline of predicting the most common outcome of irrelevance. However, we test the ability to determine the relevance of a bill with the previous OpenAI GPT-3 model (text-davinci-002), which was state-of-the-art on many language tasks until text-davinci-003 was released on November 28, 2022. The performance of text-davinci-002 is worse than simply always predicting that a bill is irrelevant to a company. These results suggest that, as large language models continue to improve core natural language understanding capabilities, performance on corporate lobbying related tasks will continue to improve. We then discuss why this could be problematic for societal-AI alignment.