近年来，应用深入的强化学习（RL）在解决各种领域的具有挑战性的问题方面取得了重大进展。然而，由于算法的不稳定性和方差以及基准环境中的随机性，各种方法的收敛性遭受了不一致的影响。特别是，尽管该代理商的性能平均可能会有所改善，但在训练的后期阶段可能会突然恶化。在这项工作中，我们通过提供有关所获得的历史或参考基准策略的保守更新来研究增强代理学习过程的方法。我们的方法称为珠穆朗玛峰，通过参考策略的信心范围获得了高度改善的信心。通过广泛的经验分析，我们证明了我们方法在绩效和稳定方面的好处，并在连续控制和ATARI基准方面有了显着改善。

With large-scale adaption to biometric based applications, security and privacy of biometrics is utmost important especially when operating in unsupervised online mode. This work proposes a novel approach for generating new artificial fingerprints also called proxy fingerprints that are natural looking, non-invertible, revocable and privacy preserving. These proxy biometrics can be generated from original ones only with the help of a user-specific key. Instead of using the original fingerprint, these proxy templates can be used anywhere with same convenience. The manuscripts walks through an interesting way in which proxy fingerprints of different types can be generated and how they can be combined with use-specific keys to provide revocability and cancelability in case of compromise. Using the proposed approach a proxy dataset is generated from samples belonging to Anguli fingerprint database. Matching experiments were performed on the new set which is 5 times larger than the original, and it was found that their performance is at par with 0 FAR and 0 FRR in the stolen key, safe key scenarios. Other parameters on revocability and diversity are also analyzed for protection performance.

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.

Much recent work in task-oriented parsing has focused on finding a middle ground between flat slots and intents, which are inexpressive but easy to annotate, and powerful representations such as the lambda calculus, which are expressive but costly to annotate. This paper continues the exploration of task-oriented parsing by introducing a new dataset for parsing pizza and drink orders, whose semantics cannot be captured by flat slots and intents. We perform an extensive evaluation of deep-learning techniques for task-oriented parsing on this dataset, including different flavors of seq2seq systems and RNNGs. The dataset comes in two main versions, one in a recently introduced utterance-level hierarchical notation that we call TOP, and one whose targets are executable representations (EXR). We demonstrate empirically that training the parser to directly generate EXR notation not only solves the problem of entity resolution in one fell swoop and overcomes a number of expressive limitations of TOP notation, but also results in significantly greater parsing accuracy.

Chest X-ray (CXR) datasets hosted on Kaggle, though useful from a data science competition standpoint, have limited utility in clinical use because of their narrow focus on diagnosing one specific disease. In real-world clinical use, multiple diseases need to be considered since they can co-exist in the same patient. In this work, we demonstrate how federated learning (FL) can be used to make these toy CXR datasets from Kaggle clinically useful. Specifically, we train a single FL classification model (`global`) using two separate CXR datasets -- one annotated for presence of pneumonia and the other for presence of pneumothorax (two common and life-threatening conditions) -- capable of diagnosing both. We compare the performance of the global FL model with models trained separately on both datasets (`baseline`) for two different model architectures. On a standard, naive 3-layer CNN architecture, the global FL model achieved AUROC of 0.84 and 0.81 for pneumonia and pneumothorax, respectively, compared to 0.85 and 0.82, respectively, for both baseline models (p>0.05). Similarly, on a pretrained DenseNet121 architecture, the global FL model achieved AUROC of 0.88 and 0.91 for pneumonia and pneumothorax, respectively, compared to 0.89 and 0.91, respectively, for both baseline models (p>0.05). Our results suggest that FL can be used to create global `meta` models to make toy datasets from Kaggle clinically useful, a step forward towards bridging the gap from bench to bedside.

Impact craters are formed due to continuous impacts on the surface of planetary bodies. Most recent deep learning-based crater detection methods treat craters as circular shapes, and less attention is paid to extracting the exact shapes of craters. Extracting precise shapes of the craters can be helpful for many advanced analyses, such as crater formation. This paper proposes a combination of unsupervised non-deep learning and semi-supervised deep learning approach to accurately extract shapes of the craters and detect missing craters from the existing catalog. In unsupervised non-deep learning, we have proposed an adaptive rim extraction algorithm to extract craters' shapes. In this adaptive rim extraction algorithm, we utilized the elevation profiles of DEMs and applied morphological operation on DEM-derived slopes to extract craters' shapes. The extracted shapes of the craters are used in semi-supervised deep learning to get the locations, size, and refined shapes. Further, the extracted shapes of the craters are utilized to improve the estimate of the craters' diameter, depth, and other morphological factors. The craters' shape, estimated diameter, and depth with other morphological factors will be publicly available.

不断增加的材料科学文章使得很难从已发表的文献中推断化学结构 - 培训关系。我们使用自然语言处理（NLP）方法从聚合物文献的摘要中自动提取材料属性数据。作为我们管道的组成部分，我们使用240万材料科学摘要培训了一种语言模型的材料，该材料模型在用作文本编码器时，在五分之三命名实体识别数据集中的其他基线模型都优于其他基线模型。使用此管道，我们在60小时内从约130,000个摘要中获得了约300,000个物质记录。分析了提取的数据，分析了各种应用，例如燃料电池，超级电容器和聚合物太阳能电池，以恢复非平凡的见解。通过我们的管道提取的数据可通过https://polymerscholar.org的Web平台提供，该数据可方便地定位摘要中记录的材料属性数据。这项工作证明了自动管道的可行性，该管道从已发布的文献开始，并以一组完整的提取物质属性信息结束。

在具有可再生生成的大量份额的网格中，由于负载和发电的波动性增加，运营商将需要其他工具来评估运营风险。正向不确定性传播问题的计算要求必须解决众多安全受限的经济调度（SCED）优化，是这种实时风险评估的主要障碍。本文提出了一个即时风险评估学习框架（Jitralf）作为替代方案。 Jitralf训练风险代理，每天每小时一个，使用机器学习（ML）来预测估计风险所需的数量，而无需明确解决SCED问题。这大大减轻了正向不确定性传播的计算负担，并允许快速，实时的风险估计。本文还提出了一种新颖的，不对称的损失函数，并表明使用不对称损失训练的模型的性能优于使用对称损耗函数的模型。在法国传输系统上评估了Jitralf，以评估运营储量不足的风险，减轻负载的风险和预期的运营成本。

传入/传出车辆的记录是根本原因分析的关键信息，以打击各种敏感组织中的安全违规事件。 RFID标记会阻碍物流和技术方面的车辆跟踪解决方案的可扩展性。例如，要求标记为RFID的每个传入车辆（部门或私人）是严重的限制，并且与RFID一起检测异常车辆运动的视频分析是不平凡的。我们利用公开可用的计算机视觉算法实现，使用有限状态机形式主义开发可解释的车辆跟踪算法。国家机器将用于状态转换的级联对象检测和光学特征识别（OCR）模型中的输入。我们从系统部署站点中评估了75个285辆车的视频片段中提出的方法。我们观察到检测率受速度和车辆类型的影响最大。当车辆运动仅限于在检查点类似于RFID标记的检查点时，将达到最高的检测率。我们进一步分析了700个对Live DATA的车辆跟踪预测，并确定大多数车辆数量预测误差是由于无法辨认的文本，图像布鲁尔，文本遮挡，文本遮挡和vecab外字母引起的。为了进行系统部署和性能增强，我们希望我们正在进行的系统监控能够提供证据，以在安全检查点上建立更高的车辆通知SOP，并将已部署的计算机视觉模型和状态模型的微调驱动为建立拟议的方法作为RFID标记的有希望的替代方法。

产量估计是葡萄园管理中的强大工具，因为它允许种植者微调实践以优化产量和质量。但是，目前使用手动抽样进行估计，这是耗时和不精确的。这项研究表明，近端成像的应用与深度学习相结合，以进行葡萄园中的产量估计。使用车辆安装的传感套件进行连续数据收集，并使用商业收益率监控器在收获时结合了地面真实收益数据的收集，可以生成一个23,581个收益点和107,933张图像的大数据集。此外，这项研究是在机械管理的商业葡萄园中进行的，代表了一个充满挑战的图像分析环境，但在加利福尼亚中央山谷中的一组常见条件。测试了三个模型架构：对象检测，CNN回归和变压器模型。对象检测模型在手工标记的图像上进行了训练以定位葡萄束，并将束数量或像素区域求和以与葡萄产量相关。相反，回归模型端到端训练，以预测图像数据中的葡萄产量，而无需手动标记。结果表明，在代表性的保留数据集上，具有相当的绝对百分比误差为18％和18.5％的变压器和具有像素区域处理的对象检测模型。使用显着映射来证明CNN模型的注意力位于葡萄束的预测位置附近以及葡萄树冠的顶部。总体而言，该研究表明，近端成像和深度学习对于大规模预测葡萄群的适用性。此外，端到端建模方法能够与对象检测方法相当地执行，同时消除了手工标记的需求。