The paper suggests a definition of "know who" as a modality using Grove-Halpern semantics of names. It also introduces a logical system that describes the interplay between modalities "knows who", "knows", and "for all agents". The main technical result is a completeness theorem for the proposed system.

Whilst adversarial attack detection has received considerable attention, it remains a fundamentally challenging problem from two perspectives. First, while threat models can be well-defined, attacker strategies may still vary widely within those constraints. Therefore, detection should be considered as an open-set problem, standing in contrast to most current detection strategies. These methods take a closed-set view and train binary detectors, thus biasing detection toward attacks seen during detector training. Second, information is limited at test time and confounded by nuisance factors including the label and underlying content of the image. Many of the current high-performing techniques use training sets for dealing with some of these issues, but can be limited by the overall size and diversity of those sets during the detection step. We address these challenges via a novel strategy based on random subspace analysis. We present a technique that makes use of special properties of random projections, whereby we can characterize the behavior of clean and adversarial examples across a diverse set of subspaces. We then leverage the self-consistency (or inconsistency) of model activations to discern clean from adversarial examples. Performance evaluation demonstrates that our technique outperforms ($>0.92$ AUC) competing state of the art (SOTA) attack strategies, while remaining truly agnostic to the attack method itself. It also requires significantly less training data, composed only of clean examples, when compared to competing SOTA methods, which achieve only chance performance, when evaluated in a more rigorous testing scenario.

Machine learning models have been successfully used in many scientific and engineering fields. However, it remains difficult for a model to simultaneously utilize domain knowledge and experimental observation data. The application of knowledge-based symbolic AI represented by an expert system is limited by the expressive ability of the model, and data-driven connectionism AI represented by neural networks is prone to produce predictions that violate physical mechanisms. In order to fully integrate domain knowledge with observations, and make full use of the prior information and the strong fitting ability of neural networks, this study proposes theory-guided hard constraint projection (HCP). This model converts physical constraints, such as governing equations, into a form that is easy to handle through discretization, and then implements hard constraint optimization through projection. Based on rigorous mathematical proofs, theory-guided HCP can ensure that model predictions strictly conform to physical mechanisms in the constraint patch. The performance of the theory-guided HCP is verified by experiments based on the heterogeneous subsurface flow problem. Due to the application of hard constraints, compared with fully connected neural networks and soft constraint models, such as theory-guided neural networks and physics-informed neural networks, theory-guided HCP requires fewer data, and achieves higher prediction accuracy and stronger robustness to noisy observations.

We consider the problem of generating maximally adversarial disturbances for a given controller assuming only blackbox access to it. We propose an online learning approach to this problem that adaptively generates disturbances based on control inputs chosen by the controller. The goal of the disturbance generator is to minimize regret versus a benchmark disturbance-generating policy class, i.e., to maximize the cost incurred by the controller as well as possible compared to the best possible disturbance generator in hindsight (chosen from a benchmark policy class). In the setting where the dynamics are linear and the costs are quadratic, we formulate our problem as an online trust region (OTR) problem with memory and present a new online learning algorithm (MOTR) for this problem. We prove that this method competes with the best disturbance generator in hindsight (chosen from a rich class of benchmark policies that includes linear-dynamical disturbance generating policies). We demonstrate our approach on two simulated examples: (i) synthetically generated linear systems, and (ii) generating wind disturbances for the popular PX4 controller in the AirSim simulator. On these examples, we demonstrate that our approach outperforms several baseline approaches, including $H_{\infty}$ disturbance generation and gradient-based methods.

We study the estimation of policy gradients for continuous-time systems with known dynamics. By reframing policy learning in continuous-time, we show that it is possible construct a more efficient and accurate gradient estimator. The standard back-propagation through time estimator (BPTT) computes exact gradients for a crude discretization of the continuous-time system. In contrast, we approximate continuous-time gradients in the original system. With the explicit goal of estimating continuous-time gradients, we are able to discretize adaptively and construct a more efficient policy gradient estimator which we call the Continuous-Time Policy Gradient (CTPG). We show that replacing BPTT policy gradients with more efficient CTPG estimates results in faster and more robust learning in a variety of control tasks and simulators.

I propose a new tool to characterize the resolution of uncertainty around FOMC press conferences. It relies on the construction of a measure capturing the level of discussion complexity between the Fed Chair and reporters during the Q&A sessions. I show that complex discussions are associated with higher equity returns and a drop in realized volatility. The method creates an attention score by quantifying how much the Chair needs to rely on reading internal documents to be able to answer a question. This is accomplished by building a novel dataset of video images of the press conferences and leveraging recent deep learning algorithms from computer vision. This alternative data provides new information on nonverbal communication that cannot be extracted from the widely analyzed FOMC transcripts. This paper can be seen as a proof of concept that certain videos contain valuable information for the study of financial markets.

The UK has been at the cutting edge of artificial intelligence (AI) innovation, from Alan Turing, the pioneering mathematician and computer visionary, who launched the field, to DeepMind's AlphaGo, the first computer program to defeat a professional Go player in 2015. Several pioneering AI companies were founded in the UK, including DeepMind, SwiftKey and Magic Pony, all of which were acquired by US companies – Google, Microsoft and Twitter – for $500 million, $250 million and $150 million, respectively. Over the last few years, the UK government has launched its Office for AI and Centre for Data Ethics and Innovation. But is the UK still an AI leader? In 2019, McKinsey Global Institute placed the UK in the top quartile for "AI readiness".

Verdict lists the top five terms tweeted on robotics in November 2020, based on data from GlobalData's Influencer Platform. The top tweeted terms are the trending industry discussions happening on Twitter by key individuals (influencers) as tracked by the platform. The role of artificial intelligence (AI) in solving all human problems, its application in chemical research and how it is driving new business models and productivity potential were popularly discussed in November. According to an article shared by Spiros Margaris, a venture capitalist, AI can help solve the world's most challenging problems right from using it to create diagnostic equipment to building unmanned aerial vehicles. The article noted that although some fear that AI and robotics will usurp all human jobs, it is the basis for all technological innovations such as driverless cars, smart personal agents, and autonomous drones, among others.

Former CIA director, author of the book'Undaunted,' John Brennan provides insight on'Fox News Sunday.' The U.S. military flew a pair of B-52 bombers to the Middle East Thursday from Barksdale AFB in Louisiana the second deterrence mission against Iran in recent weeks and comes on the same day U.S. drones attacked al-Qaeda-linked'explosives experts' in Somalia. "We have seen some indications of increased attack planning by Iranian-linked forces inside Iraq" said one U.S. military official who declined to be identified to discuss the sensitive nature of the information. "Presidential transitions are normally a time when our adversaries try to test us," the official added. U.S. military forces are drawing down to 2,500 in Iraq and Afghanistan before January 20th.

The fate of a set of sweeping police reforms debated in the Legislature for more than seven months is in jeopardy if lawmakers -- who lack a veto-proof majority -- refuse to compromise on a number of amendments Gov. Charlie Baker has added to the bill. The Republican governor sent the bill back to the Legislature today with amendments making changes to portions of the legislation dealing with facial recognition technology and police training. In a Thursday afternoon memo to lawmakers, Baker agreed the bill "overall… promotes improved police accountability" but nixed a number of provisions he said "introduce barriers to effective administration and the protection of public safety." In no uncertain terms, Baker said he would not sign a bill that bans police from using facial recognition systems to solve crimes or leaves the development of training programs for police to a civilian-controlled commission. "This is about making compromise and I'm ready to do that on almost everything with respect to improving accountability for law enforcement. But there are parts of this bill that were never part of that conversation about accountability that I can't support," Baker told the State House News Service.