Script knowledge consists of detailed information on everyday activities. Such information is often taken for granted in text and needs to be inferred by readers. Therefore, script knowledge is a central component to language comprehension. Previous work on representing scripts is mostly based on extensive manual work or limited to scenarios that can be found with sufficient redundancy in large corpora. We introduce the task of scenario detection, in which we identify references to scripts. In this task, we address a wide range of different scripts (200 scenarios) and we attempt to identify all references to them in a collection of narrative texts. We present a first benchmark data set and a baseline model that tackles scenario detection using techniques from topic segmentation and text classification.

At the 2017 Artificial and Computational Intelligence in Games meeting at Dagstuhl, Julian Togelius asked how to make spaces where every way of filling in the details yielded a good game. This study examines the possibility of enriching search spaces so that they contain very high rates of interesting objects, specifically game elements. While we do not answer the full challenge of finding good games throughout the space, this study highlights a number of potential avenues. These include naturally rich spaces, a simple technique for modifying a representation to search only rich parts of a larger search space, and representations that are highly expressive and so exhibit highly restricted and consequently enriched search spaces.

Although peer prediction markets are widely used in crowdsourcing to aggregate information from agents, they often fail to reward the participating agents equitably. Honest agents can be wrongly penalized if randomly paired with dishonest ones. In this work, we introduce \emph{selective} and \emph{cumulative} fairness. We characterize a mechanism as fair if it satisfies both notions and present FaRM, a representative mechanism we designed. FaRM is a Nash incentive mechanism that focuses on information aggregation for spontaneous local activities which are accessible to a limited number of agents without assuming any prior knowledge of the event. All the agents in the vicinity observe the same information. FaRM uses \textit{(i)} a \emph{report strength score} to remove the risk of random pairing with dishonest reporters, \textit{(ii)} a \emph{consistency score} to measure an agent's history of accurate reports and distinguish valuable reports, \textit{(iii)} a \emph{reliability score} to estimate the probability of an agent to collude with nearby agents and prevents agents from getting swayed, and \textit{(iv)} a \emph{location robustness score} to filter agents who try to participate without being present in the considered setting. Together, report strength, consistency, and reliability represent a fair reward given to agents based on their reports.

In multi-agent planning, preserving the agents' privacy has become an increasingly popular research topic. For preserving the agents' privacy, agents jointly compute a plan that achieves mutual goals by keeping certain information private to the individual agents. Unfortunately, this can severely restrict the accuracy of the heuristic functions used while searching for solutions. It has been recently shown that, for centralized planning, the performance of goal oriented search can be improved by combining goal oriented search and width-based search. The combination of these techniques has been called best-first width search. In this paper, we investigate the usage of best-first width search in the context of (decentralised) multi-agent privacy-preserving planning, addressing the challenges related to the agents' privacy and performance. In particular, we show that best-first width search is a very effective approach over several benchmark domains, even when the search is driven by heuristics that roughly estimate the distance from goal states, computed without using the private information of other agents. An experimental study analyses the effectiveness of our techniques and compares them with the state-of-the-art.

As machine learning is increasingly used to make real-world decisions, recent research efforts aim to define and ensure fairness in algorithmic decision making. Existing methods often assume a fixed set of observable features to define individuals, but lack a discussion of certain features not being observed at test time. In this paper, we study fairness of naive Bayes classifiers, which allow partial observations. In particular, we introduce the notion of a discrimination pattern, which refers to an individual receiving different classifications depending on whether some sensitive attributes were observed. Then a model is considered fair if it has no such pattern. We propose an algorithm to discover and mine for discrimination patterns in a naive Bayes classifier, and show how to learn maximum-likelihood parameters subject to these fairness constraints. Our approach iteratively discovers and eliminates discrimination patterns until a fair model is learned. An empirical evaluation on three real-world datasets demonstrates that we can remove exponentially many discrimination patterns by only adding a small fraction of them as constraints.

A significant part of the literature in deontic logic revolves around the discussions of puzzles and paradoxes which show that certain logical systems are not acceptable--typically, this happens with deontic KD, i.e., Standard Deontic Logic (SDL)--or which suggest that obligations and permissions should enjoy some desirable properties. One well-known puzzle is the the so-called Free Choice Permission paradox, which was originated by the following remark by von Wright in [23, p. 21]: "On an ordinary understanding of the phrase'it is permitted that', the formula'P(p q)' seems to entail'Pp Pq'. If I say to somebody'you may work or relax' I normally mean that the person addressed has my permission to work and also my permission to relax. It is up to him to choose between the two alternatives." Usually, this intuition is formalised by the following schema: P(p q) (Pp Pq) (FCP) Many problems have been discussed in the literature around FCP: for a comprehensive overview, discussion, and some solutions, see [11, 14, 20]. Three basic difficulties can be identified, among the others [11, p. 43]: - Problem 1: Permission Explosion Problem - "That if anything is permissible, then everything is, and thus it would also be a theorem that nothing is obligatory," [20], for example "If you may order a soup, then it is not true that you ought to pay the bill" [6];

We've read the stories about how artificial intelligence (AI) and machine learning are transforming the way companies approach marketing. But what if the true game-changer in consumer insights will be driven by our own brainwaves? Although it may sound like science fiction, the technology has been around for several years, and some companies are finding ways to use brain data to drive product development and market research. In fact, neuromarketing--which uses brain research to reveal a consumer's subconscious decision-making processes--has been in use for more than a decade. In 2009, PepsiCo's Cheetos used EEGs from the brain to measure consumer response to a "prank" type ad, and learned its focus group wasn't quite forthcoming with its written responses.

Artificial intelligence is quickly becoming a part of daily life. Enterprise implementations of AI-based technologies tripled in 2018, according to Gartner. At the same time, it's reaching ubiquity in consumer-facing applications, helping us write our emails, discover new music, and get on-demand customer support. At every touchpoint, our data is being collected and used to make machines faster and smarter, and that's driving calls for regulation from global citizens, governments, and companies who want to ensure deployments of machine and deep learning algorithms are safe and ethical. While implementing laws to protect consumers from "AI-gone-wild" may seem like a reasonable proposition, it's one that's doomed to fail.

Which Way Next? is a Singularity University webcast series of monthly roundtable discussions on exponential technologies with leaders in industry, science and technology. This is a recording of our live premiere episode with Dr. Sebastian Thrun, PhD, research professor and executive director of the Artificial Intelligence Lab at Stanford University and Google Fellow on Tuesday, Dec. 6, 2011. On this episode, he joined SU Chairman & Co-Founder Dr. Peter Diamandis, MD in a discussion on artificial intelligence and the Google autonomous Car. Earlier this year, Fast Company honored Dr. Thrun with the title of "fifth most creative person in the world." About Singularity University: Singularity University is a benefit corporation headquartered at NASA's research campus in Silicon Valley.

Powered by a pair of photovoltaic panels and designed to linger in the forest canopy continuously for months, SlothBot moves only when it must to measure environmental changes -- such as weather and chemical factors in the environment -- that can be observed only with a long-term presence. The proof-of-concept hyper-efficient robot, described May 21 at the International Conference on Robotics and Automation (ICRA) in Montreal, may soon be hanging out among treetop cables in the Atlanta Botanical Garden. "In robotics, it seems we are always pushing for faster, more agile and more extreme robots," said Magnus Egerstedt, the Steve W. Chaddick School Chair of the School of Electrical and Computer Engineering at the Georgia Institute of Technology and principal investigator for Slothbot. "But there are many applications where there is no need to be fast. You just have to be out there persistently over long periods of time, observing what's going on."