Deep Learning methods are known to suffer from calibration issues: they typically produce over-confident estimates. These problems are exacerbated in the low data regime. Although the calibration of probabilistic models is well studied, calibrating extremely over-parametrized models in the low-data regime presents unique challenges. We show that deep-ensembles do not necessarily lead to improved calibration properties. In fact, we show that standard ensembling methods, when used in conjunction with modern techniques such as mixup regularization, can lead to less calibrated models. In this text, we examine the interplay between three of the most simple and commonly used approaches to leverage deep learning when data is scarce: data-augmentation, ensembling, and post-processing calibration methods. We demonstrate that, although standard ensembling techniques certainly help to boost accuracy, the calibration of deep-ensembles relies on subtle trade-offs. Our main finding is that calibration methods such as temperature scaling need to be slightly tweaked when used with deep-ensembles and, crucially, need to be executed after the averaging process. Our simulations indicate that, in the low data regime, this simple strategy can halve the Expected Calibration Error (ECE) on a range of benchmark classification problems when compared to standard deep-ensembles.

Human fascination with robots has long been fused with fear. The first widespread use of the term came a century ago in a Czech play about robots manufactured to serve and work for people. The bots turn on their masters. That plot has played out in fiction countless times since. Meanwhile, the real world has created ever more advanced versions of mechanical servants.

Human fascination with robots has long been fused with fear. The first widespread use of the term came a century ago in a Czech play about robots manufactured to serve and work for people. The bots turn on their masters. That plot has played out in fiction countless times since. Meanwhile, the real world has created ever more advanced versions of mechanical servants.

- It’s not just the U.S., China and Russia who are embedding artificial intelligence into their military systems. - The U.K., Israel, Brazil, Australia, South Korea and Iran are also investing in military AI. - China’s private-public co-operative model is allowing it to take the lead from the U.S. in some key technologies. Think of artificial intelligence, and the mind often goes to industrial robots and benign surveillance systems. Increasingly, though, these are steppingstones for Big Brother to enhance capabilities in domestic security and international military warfare. China has co-opt...

Efforts in contact tracing to try to control the spread of the Covid-19 virus had been going on before Google and Apple in early April announced their partnership on contact tracing technology. However, the two tech giants have proposed a way to share data while keeping user privacy central to the design. Recent news out of Singapore may point the way to how this is likely to go, pointing in the direction of the surveillance state. The pursuit of effective contact tracing embodies a confluence of issues around AI and surveillance, data privacy and public safety, and the roles of government and industry. Most contact tracing apps installed on smartphones use Bluetooth radio technology to record when other phones with the same app are detected nearby When a user shows symptoms or tests positive for Covid-19, alerts can be sent to all those in proximity over the previous week or two, along with suggestions for how to respond.

Applied mathematician Tobin South, the Technical Lead on Clearer Consent, said the goal would be to modify existing chatbot interfaces and off-the-shelf question-answering software to become something fit for purpose on a hospital front line. "A big challenge in healthcare is informed consent, the doctor gives you all these forms, says tick the boxes, don't drive for the next couple of days, but many people don't really understand what's going on," the University of South Australia masters student said. "Lots of people have language barriers to using these forms and there's also cultural considerations that you can't cram onto a one-page form. "The solution involving AI was to develop a way to ask questions in the patient's native language, and have them be able to type their own questions or concerns into the program and have it understand them and give meaningful answers back."

Think of artificial intelligence, and the mind often goes to industrial robots and benign surveillance systems. Increasingly, though, these are steppingstones for Big Brother to enhance capabilities in domestic security and international military warfare. China has co-opted a controversial big data policing program into law enforcement, both for racial profiling of its Uighur minority population and for broader citizen surveillance through facial recognition. Wuhan has an entirely AI-staffed police station. But experts say China's artificial intelligence research is also being adapted for unconventional military warfare in the country's bid to dominate the field over the next decade.

Agent unified modeling languages (AUML) are agent-oriented approaches that supports the specification, design, visualization and documentation of an agent-based system. This paper presents the use of Prometheus AUML approach for the modeling of a Pre-assessment System of five interactive agents. The Pre-assessment System, as previously reported, is a multi-agent based e-learning system that is developed to support the assessment of prior learning skills in students so as to classify their skills and make recommendation for their learning. This paper discusses the detailed design approach of the system in a step-by-step manner; and domain knowledge abstraction and organization in the system. In addition, the analysis of the data collated and models of prediction for future pre-assessment results are also presented.

We are interested in the problem of efficiently determining the data complexity of answering queries mediated by non-Horn description logic ontologies and constructing their optimal rewritings to standard database queries. In general, this problem is known to be extremely complex. In this article, we strip it to the bare bones and focus on conjunctive queries mediated by a simple covering axiom stating that one class is covered by the union of two other classes. We develop a novel technique to prove that, quite surprisingly, deciding first-order rewritability of even such simple ontology-mediated queries is PSpace-hard. The main result of this article is a complete and transparent syntactic AC0/NL/P/coNP tetrachotomy of path queries under the assumption that the covering classes are disjoint. We also obtain a number of syntactic and semantic sufficient conditions (without the path query assumption) for membership in AC0, L, NL, and P.

Since edge device failures (i.e., anomalies) seriously affect the production of industrial products in Industrial IoT (IIoT), accurately and timely detecting anomalies is becoming increasingly important. Furthermore, data collected by the edge device may contain the user's private data, which is challenging the current detection approaches as user privacy is calling for the public concern in recent years. With this focus, this paper proposes a new communication-efficient on-device federated learning (FL)-based deep anomaly detection framework for sensing time-series data in IIoT. Specifically, we first introduce a FL framework to enable decentralized edge devices to collaboratively train an anomaly detection model, which can improve its generalization ability. Second, we propose an Attention Mechanism-based Convolutional Neural Network-Long Short Term Memory (AMCNN-LSTM) model to accurately detect anomalies. The AMCNN-LSTM model uses attention mechanism-based CNN units to capture important fine-grained features, thereby preventing memory loss and gradient dispersion problems. Furthermore, this model retains the advantages of LSTM unit in predicting time series data. Third, to adapt the proposed framework to the timeliness of industrial anomaly detection, we propose a gradient compression mechanism based on Top-\textit{k} selection to improve communication efficiency. Extensive experiment studies on four real-world datasets demonstrate that the proposed framework can accurately and timely detect anomalies and also reduce the communication overhead by 50\% compared to the federated learning framework that does not use a gradient compression scheme.