Like superheroes capable of seeing through obstacles, environmental regulators may soon wield the power of all-seeing eyes that can identify violators anywhere at any time, according to a new Stanford University-led study. The paper, published the week of April 19 in Proceedings of the National Academy of Sciences (PNAS), demonstrates how artificial intelligence combined with satellite imagery can provide a low-cost, scalable method for locating and monitoring otherwise hard-to-regulate industries. "Brick kilns have proliferated across Bangladesh to supply the growing economy with construction materials, which makes it really hard for regulators to keep up with new kilns that are constructed," said co-lead author Nina Brooks, a postdoctoral associate at the University of Minnesota's Institute for Social Research and Data Innovation who did the research while a Ph.D. student at Stanford. While previous research has shown the potential to use machine learning and satellite observations for environmental regulation, most studies have focused on wealthy countries with dependable data on industrial locations and activities. To explore the feasibility in developing countries, the Stanford-led research focused on Bangladesh, where government regulators struggle to locate highly pollutive informal brick kilns, let alone enforce rules.

Police in Texas investigating a Tesla car crash in which two men died will serve search warrants on the company to ascertain if the vehicle's autopilot mode was engaged at the time of the incident. However Tesla's CEO, Elon Musk, has said the self-driving feature was not being used, based on an internal probe by the company. In the incident, two men, both in their 50s, were killed after their 2019 Tesla Model S crashed into a tree and caught fire. According to police reports, the car was travelling at a high speed and failed to negotiate a curve in the road. Texas police noted that nobody was at the driving seat at the time of impact, raising doubts about the involvement of the car's autopilot mode.

In this article we will explain what index data structures are and introduce you to some popular structures. In today's world, ever-increasing amounts of data are being processed. The data can be used to derive business strategies in a commercial context, but also to gain valuable information about all scientific disciplines. The data obtained must be saved, ideally as raw data, and stored for future analysis. At the time of creation, it is not yet possible to estimate what information might be valuable at some point.

When Microsoft spends $19.7 billion on a company whose specialties included voice recognition and artificial intelligence (AI) as part of its health sector strategy, you know that AI in the medical field is here to stay. It only makes sense, then, that regulations regarding the technology would not be far behind. Thanks to a leaked document first reported by Politico, we now have our first look at what such regulations might look like in the European Union. The regulation document largely concerns "high-risk" usages of AI. That's not surprising, as the European Commission originally published a whitepaper in February 2020 outlining ideas for regulating such uses of the technology.

As more and more robots are envisioned to cooperate with humans sharing the same space, it is desired for robots to be able to predict others' trajectories to navigate in a safe and self-explanatory way. We propose a Convolutional Neural Network-based approach to learn, detect, and extract patterns in sequential trajectory data, known here as Social Pattern Extraction Convolution (Social-PEC). A set of experiments carried out on the human trajectory prediction problem shows that our model performs comparably to the state of the art and outperforms in some cases. More importantly, the proposed approach unveils the obscurity in the previous use of a pooling layer, presenting a way to intuitively explain the decision-making process.

We establish a link between multiwinner elections and apportionment problems by showing how approval-based multiwinner election rules can be interpreted as methods of apportionment. We consider several multiwinner rules and observe that they induce apportionment methods that are well-established in the literature on proportional representation. For instance, we show that Proportional Approval Voting induces the D'Hondt method and that Monroe's rule induces the largest reminder method. We also consider properties of apportionment methods and exhibit multiwinner rules that induce apportionment methods satisfying these properties.

In this paper, we introduce and prove asymptotic normality for a new nonparametric estimator of continuous treatment effects. Specifically, we estimate the average dose-response function - the expected value of an outcome of interest at a particular level of the treatment level. We utilize tools from both the double debiased machine learning (DML) and the automatic double machine learning (ADML) literatures to construct our estimator. Our estimator utilizes a novel debiasing method that leads to nice theoretical stability and balancing properties. In simulations our estimator performs well compared to current methods.

Subset selection is a valuable tool for interpretable learning, scientific discovery, and data compression. However, classical subset selection is often eschewed due to selection instability, computational bottlenecks, and lack of post-selection inference. We address these challenges from a Bayesian perspective. Given any Bayesian predictive model $\mathcal{M}$, we elicit predictively-competitive subsets using linear decision analysis. The approach is customizable for (local) prediction or classification and provides interpretable summaries of $\mathcal{M}$. A key quantity is the acceptable family of subsets, which leverages the predictive distribution from $\mathcal{M}$ to identify subsets that offer nearly-optimal prediction. The acceptable family spawns new (co-) variable importance metrics based on whether variables (co-) appear in all, some, or no acceptable subsets. Crucially, the linear coefficients for any subset inherit regularization and predictive uncertainty quantification via $\mathcal{M}$. The proposed approach exhibits excellent prediction, interval estimation, and variable selection for simulated data, including $p=400 > n$. These tools are applied to a large education dataset with highly correlated covariates, where the acceptable family is especially useful. Our analysis provides unique insights into the combination of environmental, socioeconomic, and demographic factors that predict educational outcomes, and features highly competitive prediction with remarkable stability.

When a suspicious event decision manifolds in cyber threat hunting. is detected in the monitoring data, the conventional course of action is to generate an intrusion alert in order to To better characterize the dynamics of advanced cyber notify a security analyst about a potential threat. In threats, this paper formalizes a cyber reasoning framework response to the incident, the analyst correlates the alert based on multi-functors that define structure-preserving to different sources of intelligence (both internal and mappings (a.k.a.

Research seeks to apply Artificial Intelligence (AI) to scale and extend the capabilities of human operators to defend networks. A fundamental problem that hinders the generalization of successful AI approaches -- i.e., beating humans at playing games -- is that network defense cannot be defined as a single game with a fixed set of rules. Our position is that network defense is better characterized as a collection of games with uncertain and possibly drifting rules. Hence, we propose to define network defense tasks as distributions of network environments, to: (i) enable research to apply modern AI techniques, such as unsupervised curriculum learning and reinforcement learning for network defense; and, (ii) facilitate the design of well-defined challenges that can be used to compare approaches for autonomous cyberdefense. To demonstrate that an approach for autonomous network defense is practical it is important to be able to reason about the boundaries of its applicability. Hence, we need to be able to define network defense tasks that capture sets of adversarial tactics, techniques, and procedures (TTPs); quality of service (QoS) requirements; and TTPs available to defenders. Furthermore, the abstractions to define these tasks must be extensible; must be backed by well-defined semantics that allow us to reason about distributions of environments; and should enable the generation of data and experiences from which an agent can learn. Our approach named Network Environment Design for Autonomous Cyberdefense inspired the architecture of FARLAND, a Framework for Advanced Reinforcement Learning for Autonomous Network Defense, which we use at MITRE to develop RL network defenders that perform blue actions from the MITRE Shield matrix against attackers with TTPs that drift from MITRE ATT&CK TTPs.