Machine learning (ML) is increasingly being used to support high-stakes decisions, a trend owed in part to its promise of superior predictive power relative to human assessment. However, there is frequently a gap between decision objectives and what is captured in the observed outcomes used as labels to train ML models. As a result, machine learning models may fail to capture important dimensions of decision criteria, hampering their utility for decision support. In this work, we explore the use of historical expert decisions as a rich -- yet imperfect -- source of information that is commonly available in organizational information systems, and show that it can be leveraged to bridge the gap between decision objectives and algorithm objectives. We consider the problem of estimating expert consistency indirectly when each case in the data is assessed by a single expert, and propose influence function-based methodology as a solution to this problem. We then incorporate the estimated expert consistency into a predictive model through a training-time label amalgamation approach. This approach allows ML models to learn from experts when there is inferred expert consistency, and from observed labels otherwise. We also propose alternative ways of leveraging inferred consistency via hybrid and deferral models. In our empirical evaluation, focused on the context of child maltreatment hotline screenings, we show that (1) there are high-risk cases whose risk is considered by the experts but not wholly captured in the target labels used to train a deployed model, and (2) the proposed approach significantly improves precision for these cases.

Gold mining is one of the very oldest human occupations. The earliest known underground gold mine, in what is now the country of Georgia, dates back at least 5,000 years, when people were just starting to develop written language. Over the centuries, a number of innovations have emerged that disrupted and forever changed how we explore and mine for gold and other metals. Think dynamite, or the steam engine. Lately, however, innovation has slowed.

Wearable robotic devices have potential to assist and protect their users. Toward design of a Smart Helmet, this article examines the effectiveness of audio and visual warnings to help participants brace for impacts. A user study examines different warnings and impacts applied to users while running. Perturbation forces scaled to user mass are applied from different directions and user displacement is measured to characterize effectiveness of the warning. This is accomplished using the TreadPort Active Wind Tunnel adapted to deliver forward, rearward, right, or left perturbation forces at precise moments during the locomotor cycle. The article presents an overview of the system and demonstrates the ability to precisely deliver consistent warnings and perturbations during gait. User study results highlight effectiveness of visual and audio warnings to help users brace for impact, resulting in guidelines that will inform future human-robot warning systems.

Uncertainty quantification is one of the central challenges for machine learning in real-world applications. In reinforcement learning, an agent confronts two kinds of uncertainty, called epistemic uncertainty and aleatoric uncertainty. Disentangling and evaluating these uncertainties simultaneously stands a chance of improving the agent's final performance, accelerating training, and facilitating quality assurance after deployment. In this work, we propose an uncertainty-aware reinforcement learning algorithm for continuous control tasks that extends the Deep Deterministic Policy Gradient algorithm (DDPG). It exploits epistemic uncertainty to accelerate exploration and aleatoric uncertainty to learn a risk-sensitive policy. We conduct numerical experiments showing that our variant of DDPG outperforms vanilla DDPG without uncertainty estimation in benchmark tasks on robotic control and power-grid optimization.

Hyperparameter optimization constitutes a large part of typical modern machine learning workflows. This arises from the fact that machine learning methods and corresponding preprocessing steps often only yield optimal performance when hyperparameters are properly tuned. But in many applications, we are not only interested in optimizing ML pipelines solely for predictive accuracy; additional metrics or constraints must be considered when determining an optimal configuration, resulting in a multi-objective optimization problem. This is often neglected in practice, due to a lack of knowledge and readily available software implementations for multi-objective hyperparameter optimization. In this work, we introduce the reader to the basics of multi-objective hyperparameter optimization and motivate its usefulness in applied ML. Furthermore, we provide an extensive survey of existing optimization strategies, both from the domain of evolutionary algorithms and Bayesian optimization. We illustrate the utility of MOO in several specific ML applications, considering objectives such as operating conditions, prediction time, sparseness, fairness, interpretability and robustness.

In the recent years, social media has grown to become a major source of information for many online users. This has given rise to the spread of misinformation through deepfakes. Deepfakes are videos or images that replace one persons face with another computer-generated face, often a more recognizable person in society. With the recent advances in technology, a person with little technological experience can generate these videos. This enables them to mimic a power figure in society, such as a president or celebrity, creating the potential danger of spreading misinformation and other nefarious uses of deepfakes. To combat this online threat, researchers have developed models that are designed to detect deepfakes. This study looks at various deepfake detection models that use deep learning algorithms to combat this looming threat. This survey focuses on providing a comprehensive overview of the current state of deepfake detection models and the unique approaches many researchers take to solving this problem. The benefits, limitations, and suggestions for future work will be thoroughly discussed throughout this paper.

Indeed, commercial task-oriented dialog systems in the form of smart devices like Amazon's Alexa are used by millions of people every day. Within the academic research community, however, task-oriented dialog system models are often benchmarked on relatively few evaluation datasets. This is in spite of the fact that the past few years have seen a substantial growth in the number of available datasets for building and evaluating intent classification and slot-filling models for task-oriented dialog systems. Thus, the goal of this survey is to catalog these intent classification and slot-filling datasets to help facilitate their use in building and evaluating dialog systems and beyond. Other surveys have discussed dialog datasets in depth (Serban et al. 2018), but exclude almost all intent classification and slot-filling datasets, and model-focused surveys on dialog systems mostly focus on models and pay much less attention to datasets.

Small object detection (SOD) in optical images and videos is a challenging problem that even state-of-the-art generic object detection methods fail to accurately localize and identify such objects. Typically, small objects appear in real-world due to large camera-object distance. Because small objects occupy only a small area in the input image (e.g., less than 10%), the information extracted from such a small area is not always rich enough to support decision making. Multidisciplinary strategies are being developed by researchers working at the interface of deep learning and computer vision to enhance the performance of SOD deep learning based methods. In this paper, we provide a comprehensive review of over 160 research papers published between 2017 and 2022 in order to survey this growing subject. This paper summarizes the existing literature and provide a taxonomy that illustrates the broad picture of current research. We investigate how to improve the performance of small object detection in maritime environments, where increasing performance is critical. By establishing a connection between generic and maritime SOD research, future directions have been identified. In addition, the popular datasets that have been used for SOD for generic and maritime applications are discussed, and also well-known evaluation metrics for the state-of-the-art methods on some of the datasets are provided.

In modern dynamic constantly developing society, more and more people suffer from chronic and serious diseases and doctors and patients need special and sophisticated medical and health support. Accordingly, prominent health stakeholders have recognized the importance of development of such services to make patients' life easier. Such support requires the collection of: huge amount of patients' complex data (clinical, environmental, nutritional, daily activities), variety of data from smart wearable devices, data from clothing equipped with sensors etc. Holistic patient's data must be properly aggregated, processed, analyzed, and presented to the doctors/caregivers to recommend adequate treatment and actions to improve patient's health related parameters and general wellbeing. Advanced artificial intelligence techniques offer the opportunity to analyze such big data, consume them, and derive new knowledge to support (personalized) medical decisions. New approaches like those based on advanced machine/deep learning, federated learning, transfer learning, explainable artificial intelligence open new paths for more quality use of health and medical data in future. In this paper, we will present some crucial aspects and characteristic examples in the area of application of a range of artificial intelligence approaches in (personalized) medical decisions.

The global markets provide enterprises with selling opportunities and challenges in stabilizing operational strategies. From the perspective of production management, it is important to improve the profitability of an enterprise by exploiting the different timing of the selling season in different markets to develop an operational strategy that is optimized and configured on a global scale. This paper examines the above issue with an insightful model of selling the product to two markets (a primary and a secondary market) with multiple risks of changes in the market environment and nonoverlapping selling seasons. We refer to this problem as the "global robust newsvendor" problem. We provide closed-form solutions of the optimal operation strategy for demand-independent and demand-related scenarios for the above two market stochastic systems. The closed-form solutions fully reflect the influence of the relationship between supply and demand on strategy selection. We find that the demand correlation and the lack of demand information will not substantially affect the operation strategy, and the enterprise's industrial chain and supply chain remain stable. However, the reduction of inter-market tariffs or logistics costs will cause changes, and the existence of the secondary market will lead to more capacity planning in the primary market. In addition, our model explicitly considers the impact of exchange rate uncertainty on operating strategies.