量化，知识蒸馏和修剪是NLP中神经网络压缩的最流行方法之一。独立地，这些方法降低了模型的大小并可以加速推断，但是尚未严格研究它们的相对益处和组合相互作用。对于这些技术的八个可能子集中的每一个，我们比较了六个BERT体系结构和八个胶水任务的准确性与模型大小的权衡。我们发现量化和蒸馏始终比修剪更大的好处。出乎意料的是，除了将多种方法一起使用多种修剪和量化之外，很少会产生回报的减少。取而代之的是，我们观察到互补和超级义务减少了模型大小。我们的工作定量表明，结合压缩方法可以协同降低模型大小，并且从业者应优先考虑（1）量化，（2）知识蒸馏，（3）修剪以最大程度地提高准确性与模型大小的权衡。

建模是什么使广告有说服力的原因，即引起消费者的所需响应，对于宣传，社会心理学和营销的研究至关重要。尽管其重要性，但计算机视觉中说服力的计算建模仍处于起步阶段，这主要是由于缺乏可以提供与ADS相关的说服力标签的基准数据集。由社会心理学和市场营销中的说服文学的激励，我们引入了广泛的说服策略词汇，并建立了用说服策略注释的第一个AD图像语料库。然后，我们通过多模式学习制定说服策略预测的任务，在该任务中，我们设计了一个多任务注意融合模型，该模型可以利用其他广告理解的任务来预测说服策略。此外，我们对30家财富500家公司的1600个广告活动进行了真实的案例研究，我们使用模型的预测来分析哪些策略与不同的人口统计学（年龄和性别）一起使用。该数据集还提供图像分割掩码，该蒙版在测试拆分上标记了相应的AD图像中的说服力策略。我们公开发布代码和数据集https://midas-research.github.io/persuasion-avertisements/。

在移动设备上的语音模型（在设备个性化）上的个性化是一个活跃的研究领域，但是通常，移动设备比配对的音频文本数据具有更多的仅文本数据。我们探索培训有关仅文本数据的个性化语言模型，该模型在推理期间用于提高该用户的语音识别性能。我们在一个用户群体的Librispeech语料库上进行了实验，并为Gutenberg Project的每个用户提供了个性化的文本数据。我们发布此特定于用户的LibrisPeech（UserLibri）数据集，以帮助未来的个性化研究。LibrisPeech音频转录对分为来自测试清洁数据集的55个用户，另外有52位用户。我们能够降低流媒体和非启动模型中的两个集合中每个用户的平均单词错误率，包括在流式传输时为更难的测试用户组的2.5改进。

目的：尽管机器学习模型有潜力，但缺乏普遍性阻碍了他们在临床实践中的广泛采用。我们研究了三个方法论陷阱：（1）违反独立性假设，（2）具有不适当的性能指标或基线进行比较的模型评估，以及（3）批次效应。材料和方法：使用几个回顾性数据集，我们在有或没有陷阱的情况下实现机器学习模型，以定量说明这些陷阱对模型通用性的影响。结果：更具体地说，违反独立假设，在将数据分别分为火车，验证和测试集中，在预测局部恢复和预测局部恢复和表面上，将数据分别划分为火车，验证和测试集，在将数据分别分为火车，验证和测试集中，在F1分别误导和表面上获得误解和表面收益，从而违反独立假设。预测头颈癌的3年总生存期以及46.0％的总体生存率为5.0％，从而区分肺癌的组织病理学模式。此外，在培训，验证和测试集中为受试者分发数据点导致F1分数的表面增长21.8％。此外，我们展示了绩效指标选择和基线的重要性。在存在批处理效应的情况下，为肺炎检测而建立的模型导致F1得分为98.7％。但是，当将同一模型应用于正常患者的新数据集时，仅正确地将3.86％的样品分类。结论：这些方法上的陷阱无法使用内部模型评估来捕获，这种模型的不准确预测可能会导致错误的结论和解释。因此，对于开发可推广的模型是必要的，理解和避免这些陷阱是必要的。

尿液分析是检测泌尿系统相关问题的标准诊断测试。尿液分析的自动化将降低整体诊断时间。最近的研究使用了尿道显微数据集来设计基于深度学习的算法来分类和检测尿液细胞。但这些数据集没有公开可供进一步研究。为了减轻尿Datsets的需要，我们制备尿泥沉积物微观图像（UMID）数据集，其包含约3700个细胞注释和3类细胞即RBC，PU和上皮细胞。我们讨论了准备数据集和注释所涉及的若干挑战。我们将数据集公开提供。

Existing federated classification algorithms typically assume the local annotations at every client cover the same set of classes. In this paper, we aim to lift such an assumption and focus on a more general yet practical non-IID setting where every client can work on non-identical and even disjoint sets of classes (i.e., client-exclusive classes), and the clients have a common goal which is to build a global classification model to identify the union of these classes. Such heterogeneity in client class sets poses a new challenge: how to ensure different clients are operating in the same latent space so as to avoid the drift after aggregation? We observe that the classes can be described in natural languages (i.e., class names) and these names are typically safe to share with all parties. Thus, we formulate the classification problem as a matching process between data representations and class representations and break the classification model into a data encoder and a label encoder. We leverage the natural-language class names as the common ground to anchor the class representations in the label encoder. In each iteration, the label encoder updates the class representations and regulates the data representations through matching. We further use the updated class representations at each round to annotate data samples for locally-unaware classes according to similarity and distill knowledge to local models. Extensive experiments on four real-world datasets show that the proposed method can outperform various classical and state-of-the-art federated learning methods designed for learning with non-IID data.

The rise in data has led to the need for dimension reduction techniques, especially in the area of non-scalar variables, including time series, natural language processing, and computer vision. In this paper, we specifically investigate dimension reduction for time series through functional data analysis. Current methods for dimension reduction in functional data are functional principal component analysis and functional autoencoders, which are limited to linear mappings or scalar representations for the time series, which is inefficient. In real data applications, the nature of the data is much more complex. We propose a non-linear function-on-function approach, which consists of a functional encoder and a functional decoder, that uses continuous hidden layers consisting of continuous neurons to learn the structure inherent in functional data, which addresses the aforementioned concerns in the existing approaches. Our approach gives a low dimension latent representation by reducing the number of functional features as well as the timepoints at which the functions are observed. The effectiveness of the proposed model is demonstrated through multiple simulations and real data examples.

Landing an unmanned aerial vehicle unmanned aerial vehicle (UAV) on top of an unmanned surface vehicle (USV) in harsh open waters is a challenging problem, owing to forces that can damage the UAV due to a severe roll and/or pitch angle of the USV during touchdown. To tackle this, we propose a novel model predictive control (MPC) approach enabling a UAV to land autonomously on a USV in these harsh conditions. The MPC employs a novel objective function and an online decomposition of the oscillatory motion of the vessel to predict, attempt, and accomplish the landing during near-zero tilt of the landing platform. The nonlinear prediction of the motion of the vessel is performed using visual data from an onboard camera. Therefore, the system does not require any communication with the USV or a control station. The proposed method was analyzed in numerous robotics simulations in harsh and extreme conditions and further validated in various real-world scenarios.

Multiple studies have focused on predicting the prospective popularity of an online document as a whole, without paying attention to the contributions of its individual parts. We introduce the task of proactively forecasting popularities of sentences within online news documents solely utilizing their natural language content. We model sentence-specific popularity forecasting as a sequence regression task. For training our models, we curate InfoPop, the first dataset containing popularity labels for over 1.7 million sentences from over 50,000 online news documents. To the best of our knowledge, this is the first dataset automatically created using streams of incoming search engine queries to generate sentence-level popularity annotations. We propose a novel transfer learning approach involving sentence salience prediction as an auxiliary task. Our proposed technique coupled with a BERT-based neural model exceeds nDCG values of 0.8 for proactive sentence-specific popularity forecasting. Notably, our study presents a non-trivial takeaway: though popularity and salience are different concepts, transfer learning from salience prediction enhances popularity forecasting. We release InfoPop and make our code publicly available: https://github.com/sayarghoshroy/InfoPopularity

The ability for an agent to continuously learn new skills without catastrophically forgetting existing knowledge is of critical importance for the development of generally intelligent agents. Most methods devised to address this problem depend heavily on well-defined task boundaries, and thus depend on human supervision. Our task-agnostic method, Self-Activating Neural Ensembles (SANE), uses a modular architecture designed to avoid catastrophic forgetting without making any such assumptions. At the beginning of each trajectory, a module in the SANE ensemble is activated to determine the agent's next policy. During training, new modules are created as needed and only activated modules are updated to ensure that unused modules remain unchanged. This system enables our method to retain and leverage old skills, while growing and learning new ones. We demonstrate our approach on visually rich procedurally generated environments.