生成神经网络能够模仿复杂的概率分布，例如手写文本，自然图像等。自从他们的初始化提出了几种模型。这些最成功的是基于对抗性（GaN），自动编码（VAE）和最大平均差异（MMD）相对复杂的架构和方案。令人惊讶的是，显然忽略了一个非常简单的架构（一个前馈神经网络）与明显的优化目标（Kullback_Leibler发散）结合。本文表明这种模型（表示其简单性的SGN）能够在视觉上和定量地竞争的样本与现有技术的前述方法相比。

Diabetic Retinopathy (DR) is a leading cause of vision loss in the world, and early DR detection is necessary to prevent vision loss and support an appropriate treatment. In this work, we leverage interactive machine learning and introduce a joint learning framework, termed DRG-Net, to effectively learn both disease grading and multi-lesion segmentation. Our DRG-Net consists of two modules: (i) DRG-AI-System to classify DR Grading, localize lesion areas, and provide visual explanations; (ii) DRG-Expert-Interaction to receive feedback from user-expert and improve the DRG-AI-System. To deal with sparse data, we utilize transfer learning mechanisms to extract invariant feature representations by using Wasserstein distance and adversarial learning-based entropy minimization. Besides, we propose a novel attention strategy at both low- and high-level features to automatically select the most significant lesion information and provide explainable properties. In terms of human interaction, we further develop DRG-Net as a tool that enables expert users to correct the system's predictions, which may then be used to update the system as a whole. Moreover, thanks to the attention mechanism and loss functions constraint between lesion features and classification features, our approach can be robust given a certain level of noise in the feedback of users. We have benchmarked DRG-Net on the two largest DR datasets, i.e., IDRID and FGADR, and compared it to various state-of-the-art deep learning networks. In addition to outperforming other SOTA approaches, DRG-Net is effectively updated using user feedback, even in a weakly-supervised manner.

Previous work has shown the potential of deep learning to predict renal obstruction using kidney ultrasound images. However, these image-based classifiers have been trained with the goal of single-visit inference in mind. We compare methods from video action recognition (i.e. convolutional pooling, LSTM, TSM) to adapt single-visit convolutional models to handle multiple visit inference. We demonstrate that incorporating images from a patient's past hospital visits provides only a small benefit for the prediction of obstructive hydronephrosis. Therefore, inclusion of prior ultrasounds is beneficial, but prediction based on the latest ultrasound is sufficient for patient risk stratification.

The COVID-19 pandemic created a deluge of questionable and contradictory scientific claims about drug efficacy -- an "infodemic" with lasting consequences for science and society. In this work, we argue that NLP models can help domain experts distill and understand the literature in this complex, high-stakes area. Our task is to automatically identify contradictory claims about COVID-19 drug efficacy. We frame this as a natural language inference problem and offer a new NLI dataset created by domain experts. The NLI framing allows us to create curricula combining existing datasets and our own. The resulting models are useful investigative tools. We provide a case study of how these models help a domain expert summarize and assess evidence concerning remdisivir and hydroxychloroquine.

Motivated by mitigating potentially harmful impacts of technologies, the AI community has formulated and accepted mathematical definitions for certain pillars of accountability: e.g. privacy, fairness, and model transparency. Yet, we argue this is fundamentally misguided because these definitions are imperfect, siloed constructions of the human values they hope to proxy, while giving the guise that those values are sufficiently embedded in our technologies. Under popularized methods, tensions arise when practitioners attempt to achieve each pillar of fairness, privacy, and transparency in isolation or simultaneously. In this position paper, we push for redirection. We argue that the AI community needs to consider all the consequences of choosing certain formulations of these pillars -- not just the technical incompatibilities, but also the effects within the context of deployment. We point towards sociotechnical research for frameworks for the latter, but push for broader efforts into implementing these in practice.

Collecting large-scale medical datasets with fully annotated samples for training of deep networks is prohibitively expensive, especially for 3D volume data. Recent breakthroughs in self-supervised learning (SSL) offer the ability to overcome the lack of labeled training samples by learning feature representations from unlabeled data. However, most current SSL techniques in the medical field have been designed for either 2D images or 3D volumes. In practice, this restricts the capability to fully leverage unlabeled data from numerous sources, which may include both 2D and 3D data. Additionally, the use of these pre-trained networks is constrained to downstream tasks with compatible data dimensions. In this paper, we propose a novel framework for unsupervised joint learning on 2D and 3D data modalities. Given a set of 2D images or 2D slices extracted from 3D volumes, we construct an SSL task based on a 2D contrastive clustering problem for distinct classes. The 3D volumes are exploited by computing vectored embedding at each slice and then assembling a holistic feature through deformable self-attention mechanisms in Transformer, allowing incorporating long-range dependencies between slices inside 3D volumes. These holistic features are further utilized to define a novel 3D clustering agreement-based SSL task and masking embedding prediction inspired by pre-trained language models. Experiments on downstream tasks, such as 3D brain segmentation, lung nodule detection, 3D heart structures segmentation, and abnormal chest X-ray detection, demonstrate the effectiveness of our joint 2D and 3D SSL approach. We improve plain 2D Deep-ClusterV2 and SwAV by a significant margin and also surpass various modern 2D and 3D SSL approaches.

光环伴形培养基中的离子气体通过热阳光阳光层（TSZ）效应在宇宙微波背景上留下烙印。来自活性银河核（AGN）和超新星的反馈会影响晕孔集成TSZ通量的测量（$ y_ \ mathrm {sz} $），并导致其与光晕质量的关系（$ y_ \ mathrm {sz} -mm $ ）偏离病毒定理的自相似幂律预测。我们对使用骆驼，一套流体动力模拟的套件进行了全面研究，反馈处方的差异很大。我们使用两个机器学习工具（随机森林和符号回归）的组合来搜索$ y-m $关系的类似物，这对低质量的反馈过程（$ m \ sillesim 10^{14} \，h^， {-1} \，m_ \ odot $）;我们发现，仅替换$ y \ rightarrow y（1+m _*/m_ \ mathrm {gas}）$在关系中使其非常相似。这可以用作低质量簇和星系组的强大多波长质量代理。我们的方法通常对于提高其他天体分级关系的有效性领域通常也很有用。我们还预测，$ y-m $关系的测量值可以在反馈参数的某些组合和/或排除超级新闻和AGN反馈模型的主要部分，以提供百分比的约束。艺术流体动力模拟。我们的结果对于使用即将进行的SZ调查（例如SO，CMB-S4）和Galaxy Surveys（例如Desi和Rubin）来限制Baryonic反馈的性质。最后，我们发现，$ y-m _*$的另一种关系提供了有关反馈的补充信息，而不是$ y-m $。

有监督的深度学习算法具有自动化筛查，监视和分级的医学图像的巨大潜力。但是，培训表现模型通常需要大量的标记数据，这在医疗领域几乎无法获得。自我监督的对比框架通过首先从未标记的图像中学习来放松这种依赖性。在这项工作中，我们表明使用两种对比方法进行了预处理，即SIMCLR和BYOL，就与年龄相关的黄斑变性（AMD）的临床评估有关深度学习的实用性。在实验中，使用两个大型临床数据集，其中包含7,912名患者的170,427个光学相干断层扫描（OCT）图像，我们评估了从AMD阶段和类型分类到功能性终点的七个下游任务，从七个下游任务进行预处理，从在标签较少的七个任务中，六个任务中有六个显着增加。但是，标准的对比框架具有两个已知的弱点，这些弱点不利于医疗领域的预处理。用于创建正面对比对的几种图像转换不适用于灰度医学扫描。此外，医学图像通常描绘了相同的解剖区域和疾病的严重程度，从而导致许多误导性负面对。为了解决这些问题，我们开发了一种新颖的元数据增强方法，该方法利用了丰富的固有可用患者信息集。为此，我们采用了患者身份，眼睛位置（即左或右）和时间序列数据的记录，以指示典型的不可知的对比关系。通过利用这种经常被忽视的信息，我们元数据增强的对比预处理可带来进一步的好处，并且在下游七个任务中有五个任务中的五个中的五分之一。

在基于模型的马尔可夫决策过程的大多数应用中，通常从经验数据中估算出未知基础模型的参数。由于噪音，从估计模型中学到的政策通常与基础模型的最佳政策相去甚远。当应用于基础模型的环境时，学习的政策会导致次优性能，因此要求提供更好的概括性能的解决方案。在这项工作中，我们采用贝叶斯的观点，并通过先验信息将马尔可夫决策过程的目标函数正规化，以获得更强大的策略。提出了两种方法，一种基于$ l^1 $正则化，另一种基于相对熵正则化。我们评估了有关合成模拟和大规模在线购物商店的现实搜索日志的建议算法。我们的结果证明了正则MDP策略对模型中存在的噪声的鲁棒性。

3D形状比2D图像提供了更多的信息。但是，与获取2D图像相比，有时会非常困难甚至不可能，因此有必要从2D图像中得出3D形状。尽管通常这是数学上不适的问题，但可以通过使用先验信息来限制问题公式来解决。在这里，我们提出了一种基于肯德尔的形状空间的新方法，可从单眼2D图像重建3D形状。这项工作是由研究Basking Shark的喂养行为的应用，这是一种濒临灭绝的物种，其巨大的大小和迁移率使3D形状数据几乎无法获得，从而阻碍了对其喂养行为和生态学的了解。但是，这些动物处于进食位置的2D图像很容易获得。我们将方法与基于最先进的形状的方法进行了比较，无论是在人棒模型还是在鲨鱼头骨架上。我们使用一系列的训练形状表明，Kendall Shape空间方法比以前的方法更强大，并导致形状合理的形状。这对于标本很少见的激励应用至关重要，因此只有很少的训练形状可用。