Building trustworthy, effective, and responsible machine learning systems hinges on understanding how differences in training data and modeling decisions interact to impact predictive performance. In this work, we seek to better understand how we might characterize, detect, and design for data-model synergies. We focus on a particular type of data-model inefficiency, in which adding training data from some sources can actually lower performance evaluated on key sub-groups of the population, a phenomenon we refer to as negative data externalities on group performance. Such externalities can arise in standard learning settings and can manifest differently depending on conditions between training set size and model size. Data externalities directly imply a lower bound on feasible model improvements, yet improving models efficiently requires understanding the underlying data-model tensions. From a broader perspective, our results indicate that data-efficiency is a key component of both accurate and trustworthy machine learning.

基于图神经网络（GNN）方法已饱和推荐系统的领域。这些系统的收益很大，显示了通过网络结构解释数据的优势。但是，尽管在建议任务中使用图形结构有明显的好处，但这种表示形式也带来了新的挑战，这些挑战加剧了缓解算法偏见的复杂性。当将GNN集成到下游任务中时，例如建议，缓解偏差可能会变得更加困难。此外，将现有的公平促进方法应用于大型现实世界数据集的棘手性对缓解尝试更加严重的限制。我们的工作着手通过采用现有方法来促进图形上的个人公平性并将其扩展以支持Mini批次或基于子样本的培训，从而填补了这一空白下游建议任务。我们评估了两种流行的GNN方法：图形卷积网络（GCN），该方法在整个图上进行训练，以及使用概率随机步行的图形，以创建用于迷你批次训练的子图，并评估子采样对个人公平性的影响。我们实施了一个由Dong等人提出的称为\ textit {redress}的个人公平概念，该概念使用等级优化来学习单个公平节点或项目，嵌入。我们在两个现实世界数据集上进行了经验证明，图形不仅能够达到可比的精度，而且与GCN模型相比，还可以提高公平性。这些发现对个人的公平促进，GNN和下游形式产生了影响，推荐系统，表明小批量培训通过允许当地的细微努力指导代表性学习中的公平促进过程来促进个人公平促进。

现代机器学习系统越来越多地以广泛的个人数据收集为特征，尽管回报降低并增加了这种做法的社会成本。然而，数据最小化是欧盟一般数据保护法规（'GDPR'）中列出的核心数据保护原则之一，并要求仅处理足够，相关且仅限于必要物品的个人数据。但是，由于缺乏技术解释，该原则的采用有限。在这项工作中，我们以机器学习和法律的文献为基础提出FIDO，这是抑制数据过度收集的框架。 Fido学会了基于与系统性能相关的数据最小化的解释来限制数据收集。具体而言，Fido通过迭代更新性能曲线的估计值或数据集大小和性能之间的关系，从而提供了数据收集，以停止标准。 FIDO通过分段功率定律技术估算性能曲线，该技术在整个数据收集过程中分别对算法性能的不同阶段进行建模。经验实验表明，该框架会产生准确的性能曲线和数据收集，从而在数据集中停止标准并功能采集算法。我们进一步证明，许多其他曲线家庭系统地高估了其他数据的回报。在设计数据最小化框架时，我们的调查结果和分析提供了对相关考虑因素的更深入的见解，包括主动功能获取对单个用户的影响以及用户特定数据最小化的可行性。我们以实施数据最小化的实用建议得出结论。

Advances in computer vision and machine learning techniques have led to significant development in 2D and 3D human pose estimation from RGB cameras, LiDAR, and radars. However, human pose estimation from images is adversely affected by occlusion and lighting, which are common in many scenarios of interest. Radar and LiDAR technologies, on the other hand, need specialized hardware that is expensive and power-intensive. Furthermore, placing these sensors in non-public areas raises significant privacy concerns. To address these limitations, recent research has explored the use of WiFi antennas (1D sensors) for body segmentation and key-point body detection. This paper further expands on the use of the WiFi signal in combination with deep learning architectures, commonly used in computer vision, to estimate dense human pose correspondence. We developed a deep neural network that maps the phase and amplitude of WiFi signals to UV coordinates within 24 human regions. The results of the study reveal that our model can estimate the dense pose of multiple subjects, with comparable performance to image-based approaches, by utilizing WiFi signals as the only input. This paves the way for low-cost, broadly accessible, and privacy-preserving algorithms for human sensing.

Periocular refers to the region of the face that surrounds the eye socket. This is a feature-rich area that can be used by itself to determine the identity of an individual. It is especially useful when the iris or the face cannot be reliably acquired. This can be the case of unconstrained or uncooperative scenarios, where the face may appear partially occluded, or the subject-to-camera distance may be high. However, it has received revived attention during the pandemic due to masked faces, leaving the ocular region as the only visible facial area, even in controlled scenarios. This paper discusses the state-of-the-art of periocular biometrics, giving an overall framework of its most significant research aspects.

Traditionally, data analysis and theory have been viewed as separate disciplines, each feeding into fundamentally different types of models. Modern deep learning technology is beginning to unify these two disciplines and will produce a new class of predictively powerful space weather models that combine the physical insights gained by data and theory. We call on NASA to invest in the research and infrastructure necessary for the heliophysics' community to take advantage of these advances.

Multi-class ensemble classification remains a popular focus of investigation within the research community. The popularization of cloud services has sped up their adoption due to the ease of deploying large-scale machine-learning models. It has also drawn the attention of the industrial sector because of its ability to identify common problems in production. However, there are challenges to conform an ensemble classifier, namely a proper selection and effective training of the pool of classifiers, the definition of a proper architecture for multi-class classification, and uncertainty quantification of the ensemble classifier. The robustness and effectiveness of the ensemble classifier lie in the selection of the pool of classifiers, as well as in the learning process. Hence, the selection and the training procedure of the pool of classifiers play a crucial role. An (ensemble) classifier learns to detect the classes that were used during the supervised training. However, when injecting data with unknown conditions, the trained classifier will intend to predict the classes learned during the training. To this end, the uncertainty of the individual and ensemble classifier could be used to assess the learning capability. We present a novel approach for novel detection using ensemble classification and evidence theory. A pool selection strategy is presented to build a solid ensemble classifier. We present an architecture for multi-class ensemble classification and an approach to quantify the uncertainty of the individual classifiers and the ensemble classifier. We use uncertainty for the anomaly detection approach. Finally, we use the benchmark Tennessee Eastman to perform experiments to test the ensemble classifier's prediction and anomaly detection capabilities.

This paper is about the design of an automated machine to cut turbot fish specimens. Machine vision is a key part of this project as it is used to compute a cutting curve for the specimen head. This task is impossible to be carried out by mechanical means. Machine vision is used to detect head boundary and a robot is used to cut the head. Binarization and mathematical morphology are used to detect fish boundary and this boundary is subsequently analyzed (using Hough transform and convex hull) to detect key points and thus defining the cutting curve. Afterwards, mechanical systems are used to slice fish to get an easy presentation for end consumer (as fish fillets than can be easily marketed and consumed).

The study aims the development of a wearable device to combat the onslaught of covid-19. Likewise, to enhance the regular face shield available in the market. Furthermore, to raise awareness of the health and safety protocols initiated by the government and its affiliates in the enforcement of social distancing with the integration of computer vision algorithms. The wearable device was composed of various hardware and software components such as a transparent polycarbonate face shield, microprocessor, sensors, camera, thin-film transistor on-screen display, jumper wires, power bank, and python programming language. The algorithm incorporated in the study was object detection under computer vision machine learning. The front camera with OpenCV technology determines the distance of a person in front of the user. Utilizing TensorFlow, the target object identifies and detects the image or live feed to get its bounding boxes. The focal length lens requires the determination of the distance from the camera to the target object. To get the focal length, multiply the pixel width by the known distance and divide it by the known width (Rosebrock, 2020). The deployment of unit testing ensures that the parameters are valid in terms of design and specifications.

Chatbots are expected to be knowledgeable across multiple domains, e.g. for daily chit-chat, exchange of information, and grounding in emotional situations. To effectively measure the quality of such conversational agents, a model-based automatic dialogue evaluation metric (ADEM) is expected to perform well across multiple domains. Despite significant progress, an ADEM that works well in one domain does not necessarily generalize to another. This calls for a dedicated network architecture for domain generalization. To tackle the multi-domain dialogue evaluation task, we propose a Panel of Experts (PoE), a multitask network that consists of a shared transformer encoder and a collection of lightweight adapters. The shared encoder captures the general knowledge of dialogues across domains, while each adapter specializes in one specific domain and serves as a domain expert. To validate the idea, we construct a high-quality multi-domain dialogue dataset leveraging data augmentation and pseudo-labeling. The PoE network is comprehensively assessed on 16 dialogue evaluation datasets spanning a wide range of dialogue domains. It achieves state-of-the-art performance in terms of mean Spearman correlation over all the evaluation datasets. It exhibits better zero-shot generalization than existing state-of-the-art ADEMs and the ability to easily adapt to new domains with few-shot transfer learning.