In data containing heterogeneous subpopulations, classification performance benefits from incorporating the knowledge of cluster structure in the classifier. Previous methods for such combined clustering and classification either 1) are classifier-specific and not generic, or 2) independently perform clustering and classifier training, which may not form clusters that can potentially benefit classifier performance. The question of how to perform clustering to improve the performance of classifiers trained on the clusters has received scant attention in previous literature, despite its importance in several real-world applications. In this paper, first, we theoretically analyze the generalization performance of classifiers trained on clustered data and find conditions under which clustering can potentially aid classification. This motivates the design of a simple k-means-based classification algorithm called Clustering Aware Classification (CAC) and its neural variant {DeepCAC}. DeepCAC effectively leverages deep representation learning to learn latent embeddings and finds clusters in a manner that make the clustered data suitable for training classifiers for each underlying subpopulation. Our experiments on synthetic and real benchmark datasets demonstrate the efficacy of DeepCAC over previous methods for combined clustering and classification.

迭代线性二次调节器（ILQR）在解决非线性系统模型的轨迹优化问题方面已广泛普及。但是，作为一种基于模型的拍摄方法，它在很大程度上依赖于准确的系统模型来更新最佳控制动作和通过正向集成确定的轨迹，从而变得容易受到不可避免的模型的影响。最近，针对最佳控制问题的基于学习的方法进行的大量研究工作在解决未知系统模型方面已经取得了显着发展，尤其是当系统与环境具有复杂的相互作用时。然而，通常需要一个深层的神经网络来拟合大量的采样数据。在这项工作中，我们提出了神经-ILQR，这是一种在不受约束的控制空间上进行学习的拍摄方法，其中使用简单结构的神经网络代表局部系统模型。在此框架中，通过同时完善最佳策略和神经网络迭代，可以实现轨迹优化任务，而无需依靠系统模型的先验知识。通过对两项说明性控制任务的全面评估，在系统模型中存在不准确性的情况下，提出的方法显示出胜过常规ILQR。

在自主驾驶的背景下，已知迭代线性二次调节器（ILQR）是在运动计划问题中处理非线性车辆模型的有效方法。特别是，受约束的ILQR算法在不同类型的一般限制下实现运动计划任务方面表现出了值得注意的计算效率结果。但是，受约束的ILQR方法需要在使用对数屏障函数时在第一次迭代时作为先决条件进行可行的轨迹。同样，该方法为纳入快速，高效和有效的优化方法开辟了可能性，以进一步加快优化过程，从而可以成功地满足实时实施的要求。在本文中，定义明确的运动计划问题是在非线性车辆动力学和各种约束下提出的，并利用了乘数的交替方向方法来确定利用ILQR的最佳控制动作。该方法能够在第一次迭代时规避轨迹的可行性要求。然后研究了自动驾驶汽车运动计划的说明性示例。拟议的开发实现了高度计算效率的值得注意的成就。与基于对数屏障函数的约束ILQR算法进行比较，我们提出的方法在三种驾驶场景中，平均计算时间降低了31.93％，38.52％和44.57％；与优化求解器IPOPT相比，我们提出的方法将平均计算时间降低了46.02％，53.26％和88.43％。结果，可以通过我们提出的框架实现实时计算和实施，因此它为公路驾驶任务提供了额外的安全性。

物理学的美在于，通常在变化的系统（称为运动常数）中保守数量。找到运动的常数对于理解系统的动力学很重要，但通常需要数学水平和手动分析工作。在本文中，我们提出了一个神经网络，该网络可以同时了解系统的动力学和来自数据的运动常数。通过利用发现的运动常数，它可以对动态产生更好的预测，并且可以比基于哈密顿的神经网络在更广泛的系统上工作。此外，我们方法的训练进展可以用作系统中运动常数数量的指示，该系统可用于研究新型物理系统。

能量保护是许多物理现象和动态系统的核心。在过去的几年中，有大量作品旨在预测使用神经网络的动力系统运动轨迹，同时遵守能源保护法。这些作品中的大多数受到古典力学的启发，例如哈密顿和拉格朗日力学以及神经普通微分方程。尽管这些作品已被证明在特定领域中分别很好地工作，但缺乏统一的方法，该方法通常不适用，而无需对神经网络体系结构进行重大更改。在这项工作中，我们旨在通过提供一种简单的方法来解决此问题，该方法不仅可以应用于能源持持势的系统，还可以应用于耗散系统，通过在不同情况下以不同的情况在不同情况下以正规化术语形式包括不同的归纳偏见。损失功能。所提出的方法不需要更改神经网络体系结构，并且可以构成验证新思想的基础，因此表明有望在这个方向上加速研究。

常规的识别抑郁症的方法无法扩展，公众对心理健康的认识有限，尤其是在发展中国家。从最近的研究中可以明显看出，社交媒体有可能更涉及心理健康筛查。按时间顺序排列的大量第一人称叙事帖子可以在一段时间内为人们的思想，感觉，行为或情绪提供见解，从而更好地理解在线空间中反映的抑郁症状。在本文中，我们提出了SERCNN，该文章通过（1）从不同域中堆叠两个预处理的嵌入方式以及（2）将嵌入环境重新引入MLP分类器来改善用户表示。我们的Sercnn在最先进的基线和其他基线方面表现出色，在5倍的交叉验证设置中达到93.7％的精度。由于并非所有用户都共享相同级别的在线活动，因此我们介绍了固定观察窗口的概念，该窗口量化了预定义的帖子中的观察期。 Sercnn的精度非常出色，其精度与BERT模型相当，而参数数量却少98％，Sercnn的表现出色，其精度非常出色。我们的发现为在社交媒体上检测抑郁症的方向开辟了一个有希望的方向，并较少的推断帖子，以为具有成本效益和及时干预的解决方案。我们希望我们的工作能够使该研究领域在现有临床实践中更接近现实世界的采用。

基于深度学习的模型越来越多地用于模拟科学模拟以加速科学研究。然而，准确，监督的深度学习模型需要大量的标记数据，并且通常成为采用神经网络的瓶颈。在这项工作中，我们利用了一个名为Core-Set选择的主动学习方法，以便根据预定义预算主动选择数据，以标记为培训。为了进一步提高模型性能并降低培训成本，我们也温暖开始使用缩小和扰动技巧进行培训。我们在不同领域的两种情况下测试了两种情况，即血浆物理学中的天体物理学和X射线发射光谱中的Galaxy Halo职业分布模型，结果是有前途的：与使用随机抽样基线相比，我们实现了竞争性的整体性能，更重要的是，成功降低了较大的绝对损失，即损耗分布的长尾，几乎没有开销成本。

In this paper, we propose a deep learning-based beam tracking method for millimeter-wave (mmWave)communications. Beam tracking is employed for transmitting the known symbols using the sounding beams and tracking time-varying channels to maintain a reliable communication link. When the pose of a user equipment (UE) device varies rapidly, the mmWave channels also tend to vary fast, which hinders seamless communication. Thus, models that can capture temporal behavior of mmWave channels caused by the motion of the device are required, to cope with this problem. Accordingly, we employa deep neural network to analyze the temporal structure and patterns underlying in the time-varying channels and the signals acquired by inertial sensors. We propose a model based on long short termmemory (LSTM) that predicts the distribution of the future channel behavior based on a sequence of input signals available at the UE. This channel distribution is used to 1) control the sounding beams adaptively for the future channel state and 2) update the channel estimate through the measurement update step under a sequential Bayesian estimation framework. Our experimental results demonstrate that the proposed method achieves a significant performance gain over the conventional beam tracking methods under various mobility scenarios.

Weakly-supervised object localization aims to indicate the category as well as the scope of an object in an image given only the image-level labels. Most of the existing works are based on Class Activation Mapping (CAM) and endeavor to enlarge the discriminative area inside the activation map to perceive the whole object, yet ignore the co-occurrence confounder of the object and context (e.g., fish and water), which makes the model inspection hard to distinguish object boundaries. Besides, the use of CAM also brings a dilemma problem that the classification and localization always suffer from a performance gap and can not reach their highest accuracy simultaneously. In this paper, we propose a casual knowledge distillation method, dubbed KD-CI-CAM, to address these two under-explored issues in one go. More specifically, we tackle the co-occurrence context confounder problem via causal intervention (CI), which explores the causalities among image features, contexts, and categories to eliminate the biased object-context entanglement in the class activation maps. Based on the de-biased object feature, we additionally propose a multi-teacher causal distillation framework to balance the absorption of classification knowledge and localization knowledge during model training. Extensive experiments on several benchmarks demonstrate the effectiveness of KD-CI-CAM in learning clear object boundaries from confounding contexts and addressing the dilemma problem between classification and localization performance.

Face Anti-spoofing (FAS) is essential to secure face recognition systems from various physical attacks. However, recent research generally focuses on short-distance applications (i.e., phone unlocking) while lacking consideration of long-distance scenes (i.e., surveillance security checks). In order to promote relevant research and fill this gap in the community, we collect a large-scale Surveillance High-Fidelity Mask (SuHiFiMask) dataset captured under 40 surveillance scenes, which has 101 subjects from different age groups with 232 3D attacks (high-fidelity masks), 200 2D attacks (posters, portraits, and screens), and 2 adversarial attacks. In this scene, low image resolution and noise interference are new challenges faced in surveillance FAS. Together with the SuHiFiMask dataset, we propose a Contrastive Quality-Invariance Learning (CQIL) network to alleviate the performance degradation caused by image quality from three aspects: (1) An Image Quality Variable module (IQV) is introduced to recover image information associated with discrimination by combining the super-resolution network. (2) Using generated sample pairs to simulate quality variance distributions to help contrastive learning strategies obtain robust feature representation under quality variation. (3) A Separate Quality Network (SQN) is designed to learn discriminative features independent of image quality. Finally, a large number of experiments verify the quality of the SuHiFiMask dataset and the superiority of the proposed CQIL.