联邦学习文学中的许多假设存在于最实际应用中不能满足的最佳情况。异步设置反映了逼真的环境，其中联合学习方法必须能够可靠地运行。除了参与者的不同数量的非IID数据之外，由于可用的计算电源和电池约束，异步设置模拟异构客户端参与，并且还考虑了客户端和服务器之间的延迟通信。为了减少与异步在线联合学习（ASO Fed）相关的通信开销，我们使用基于部分共享的通信的原则。以这种方式，我们减少了参与者的通信负载，因此，渲染参与学习任务更可访问。我们证明了拟议的ASO供给的融合并提供了进一步分析其行为的模拟。模拟显示，在异步设置中，可以实现与联邦随机梯度（在线FEDSGD）相同的收敛，同时减少通信十倍。

State-of-the-art object detectors are treated as black boxes due to their highly non-linear internal computations. Even with unprecedented advancements in detector performance, the inability to explain how their outputs are generated limits their use in safety-critical applications. Previous work fails to produce explanations for both bounding box and classification decisions, and generally make individual explanations for various detectors. In this paper, we propose an open-source Detector Explanation Toolkit (DExT) which implements the proposed approach to generate a holistic explanation for all detector decisions using certain gradient-based explanation methods. We suggests various multi-object visualization methods to merge the explanations of multiple objects detected in an image as well as the corresponding detections in a single image. The quantitative evaluation show that the Single Shot MultiBox Detector (SSD) is more faithfully explained compared to other detectors regardless of the explanation methods. Both quantitative and human-centric evaluations identify that SmoothGrad with Guided Backpropagation (GBP) provides more trustworthy explanations among selected methods across all detectors. We expect that DExT will motivate practitioners to evaluate object detectors from the interpretability perspective by explaining both bounding box and classification decisions.

There has been a concurrent significant improvement in the medical images used to facilitate diagnosis and the performance of machine learning techniques to perform tasks such as classification, detection, and segmentation in recent years. As a result, a rapid increase in the usage of such systems can be observed in the healthcare industry, for instance in the form of medical image classification systems, where these models have achieved diagnostic parity with human physicians. One such application where this can be observed is in computer vision tasks such as the classification of skin lesions in dermatoscopic images. However, as stakeholders in the healthcare industry, such as insurance companies, continue to invest extensively in machine learning infrastructure, it becomes increasingly important to understand the vulnerabilities in such systems. Due to the highly critical nature of the tasks being carried out by these machine learning models, it is necessary to analyze techniques that could be used to take advantage of these vulnerabilities and methods to defend against them. This paper explores common adversarial attack techniques. The Fast Sign Gradient Method and Projected Descent Gradient are used against a Convolutional Neural Network trained to classify dermatoscopic images of skin lesions. Following that, it also discusses one of the most popular adversarial defense techniques, adversarial training. The performance of the model that has been trained on adversarial examples is then tested against the previously mentioned attacks, and recommendations to improve neural networks robustness are thus provided based on the results of the experiment.

Knowledge graph (KG) is used to represent data in terms of entities and structural relations between the entities. This representation can be used to solve complex problems such as recommendation systems and question answering. In this study, a set of candidate drugs for COVID-19 are proposed by using Drug repurposing knowledge graph (DRKG). DRKG is a biological knowledge graph constructed using a vast amount of open source biomedical knowledge to understand the mechanism of compounds and the related biological functions. Node and relation embeddings are learned using knowledge graph embedding models and neural network and attention related models. Different models are used to get the node embedding by changing the objective of the model. These embeddings are later used to predict if a candidate drug is effective to treat a disease or how likely it is for a drug to bind to a protein associated to a disease which can be modelled as a link prediction task between two nodes. RESCAL performed the best on the test dataset in terms of MR, MRR and Hits@3.

As multimodal learning finds applications in a wide variety of high-stakes societal tasks, investigating their robustness becomes important. Existing work has focused on understanding the robustness of vision-and-language models to imperceptible variations on benchmark tasks. In this work, we investigate the robustness of multimodal classifiers to cross-modal dilutions - a plausible variation. We develop a model that, given a multimodal (image + text) input, generates additional dilution text that (a) maintains relevance and topical coherence with the image and existing text, and (b) when added to the original text, leads to misclassification of the multimodal input. Via experiments on Crisis Humanitarianism and Sentiment Detection tasks, we find that the performance of task-specific fusion-based multimodal classifiers drops by 23.3% and 22.5%, respectively, in the presence of dilutions generated by our model. Metric-based comparisons with several baselines and human evaluations indicate that our dilutions show higher relevance and topical coherence, while simultaneously being more effective at demonstrating the brittleness of the multimodal classifiers. Our work aims to highlight and encourage further research on the robustness of deep multimodal models to realistic variations, especially in human-facing societal applications. The code and other resources are available at https://claws-lab.github.io/multimodal-robustness/.

自然界中多元化的生态学在许多物种中具有各种形式的群体行为。蝴蝶物种是随机飞行的突出物种之一，有点有见地，并将其转化为人造隐喻将导致巨大的可能性。本文认为一种这种隐喻称为蝴蝶交配优化（BMO）。在BMO中，BFLE遵循巡逻的交配现象，并同时捕获了多模式函数的所有局部优势。为了模仿该算法，设计了一个移动机器人（BFlyBot），以满足BMO算法中BFLE的功能。此外，多Bflybot群的设计旨在像蝴蝶本质上的作用，并遵循该算法的规则。实时实验是在多动物领域的BMO算法上进行的，并将信号源视为光源。实验结果表明，BMO算法适用于检测多个信号源，其运动的变化显着，即静态和动态。在静态信号源的情况下，随着BFlybot的初始位置的不同，收敛性在时间和平稳性方面受到影响。而具有不同阶梯尺寸的实验会导致它们在机器人的执行时间和速度方面的变化。在这项工作中，在动态环境中进行了实验，在该环境中，信号源在操纵和非操作场景中的运动。 Bflybot群能够检测到单个和多信号源，在两个固定点之间在两个固定点之间进行线性移动，以圆形，向上和向下运动。评估BMO现象，各种正在进行的和前瞻性的作品，例如中海船舶检测，讨论了空中搜索应用和地震预测。

在过去的十年中，由于雷达目的的现场特异性，高保真射频（RF）建模和仿真工具的催化，在过去的十年中，经典方法的数据驱动公式迅速增长。尽管有这种激增，但有限的焦点已针对这些经典方法的理论基础。在这方面，作为我们正在进行的数据驱动的雷达时空自适应处理方法（Stap）的一部分，我们在雷达目标定位的背景下分析了精选子空间分离方法的渐近性能保证，并通过拟议目标位置估计的深度学习框架。在我们的方法中，我们通过使用RFView（由ISL Inc.开发的一个特定于站点的RF建模和模拟工具）将可变强度的目标随机放置在预定的约束区域中。在范围内，方位角和归一化自适应匹配过滤器（NAMF）测试统计量以及广义Sidelobe canceller（GSC）的输出功率的高度。使用我们的深度学习框架，我们从这些热图张量估算目标位置，以证明我们数据驱动方法在匹配和不匹配的设置中提供的可行性和显着改进。

在这项工作中，我们解决了为野外任何演讲者发出静音唇部视频演讲的问题。与以前的作品形成鲜明对比的是，我们的方法（i）不仅限于固定数量的扬声器，（ii）并未明确对域或词汇构成约束，并且（iii）涉及在野外记录的视频，反对实验室环境。该任务提出了许多挑战，关键是，所需的目标语音的许多功能（例如语音，音调和语言内容）不能完全从无声的面部视频中推断出来。为了处理这些随机变化，我们提出了一种新的VAE-GAN结构，该结构学会了将唇部和语音序列关联到变化中。在指导培训过程的多个强大的歧视者的帮助下，我们的发电机学会了以任何人的唇部运动中的任何声音综合语音序列。多个数据集上的广泛实验表明，我们的优于所有基线的差距很大。此外，我们的网络可以在特定身份的视频上进行微调，以实现与单扬声器模型相当的性能，该模型接受了$ 4 \ times $ $数据的培训。我们进行了大量的消融研究，以分析我们体系结构不同模块的效果。我们还提供了一个演示视频，该视频与我们的网站上的代码和经过训练的模型一起展示了几个定性结果： -合成}}

近年来，通过深层生成模型，音频合成的进展很大。但是，最新的很难量化。在报告结果时，不同的研究通常使用不同的评估方法和不同的指标，从而直接与其他系统进行比较，即使不是不可能。此外，在大多数情况下，报告指标的感知相关性和含义都未知，禁止对实际的可用性和音频质量的任何结论性见解。本文介绍了一项研究，该研究与（i）一组先前提出的用于音频重建的客观指标以及（ii）一项听力研究，研究了最先进的方法。结果表明，当前使用的客观指标不足以描述当前系统的感知质量。

许多具有某种形式听力损失的人认为唇读是他们日常交流的主要模式。但是，寻找学习或提高唇部阅读技能的资源可能具有挑战性。由于对与同行和言语治疗师的直接互动的限制，Covid $ 19 $流行的情况进一步加剧了这一点。如今，Coursera和Udemy等在线MOOCS平台已成为多种技能开发的最有效培训形式。但是，在线口头资源很少，因为创建这样的资源是一个广泛的过程，需要数月的手动努力来记录雇用的演员。由于手动管道，此类平台也受到词汇，支持语言，口音和扬声器的限制，并且使用成本很高。在这项工作中，我们研究了用合成生成的视频代替真实的人说话视频的可能性。合成数据可用于轻松合并更大的词汇，口音甚至本地语言以及许多说话者。我们提出了一条端到端的自动管道，以使用最先进的通话标题视频发电机网络，文本到语音的模型和计算机视觉技术来开发这样的平台。然后，我们使用仔细考虑的口头练习进行了广泛的人类评估，以验证我们设计平台针对现有的唇读平台的质量。我们的研究具体地指出了我们方法开发大规模唇读MOOC平台的潜力，该平台可能会影响数百万听力损失的人。