The Weak Completion Semantics (WCS) is a computational cognitive theory that has shown to be successful in modeling episodes of human reasoning. As the WCS is a recently developed logic programming approach, this paper investigates the correspondence of the WCS with respect to the well-established Answer Set Semantics (ASP). The underlying three-valued logic of both semantics is different and their models are evaluated with respect to different program transformations. We first illustrate these differences by the formal representation of some examples of a well-known psychological experiment, the suppression task. After that, we will provide a translation from logic programs understood under the WCS into logic programs understood under the ASP. In particular, we will show that logic programs under the WCS can be represented as logic programs under the ASP by means of a definition completion, where all defined atoms in a program must be false when their definitions are false.

Applying causal inference models in areas such as economics, healthcare and marketing receives great interest from the machine learning community. In particular, estimating the individual-treatment-effect (ITE) in settings such as precision medicine and targeted advertising has peaked in application. Optimising this ITE under the strong-ignorability-assumption -- meaning all confounders expressing influence on the outcome of a treatment are registered in the data -- is often referred to as uplift modeling (UM). While these techniques have proven useful in many settings, they suffer vividly in a dynamic environment due to concept drift. Take for example the negative influence on a marketing campaign when a competitor product is released. To counter this, we propose the uplifted contextual multi-armed bandit (U-CMAB), a novel approach to optimise the ITE by drawing upon bandit literature. Experiments on real and simulated data indicate that our proposed approach compares favourably against the state-of-the-art. All our code can be found online at https://github.com/vub-dl/u-cmab.

This paper considers the scheduling of job families on parallel machines with time constraints on machine qualifications. In this problem, each job belongs to a family and a family can only be executed on a subset of qualified machines. In addition, machines can lose their qualifications during the schedule. Indeed, if no job of a family is scheduled on a machine during a given amount of time, the machine loses its qualification for this family. The goal is to minimize the sum of job completion times, i.e. the flow time, while maximizing the number of qualifications at the end of the schedule. The paper presents a new Constraint Programming (CP) model taking more advantages of the CP feature to model machine disqualifications. This model is compared with two existing models: an Integer Linear Programming (ILP) model and a Constraint Programming model. The experiments show that the new CP model outperforms the other model when the priority is given to the number of disqualifications objective. Furthermore, it is competitive with the other model when the flow time objective is prioritized.

Infinite horizon off-policy policy evaluation is a highly challenging task due to the excessively large variance of typical importance sampling (IS) estimators. Recently, Liu et al. (2018a) proposed an approach that significantly reduces the variance of infinite-horizon off-policy evaluation by estimating the stationary density ratio, but at the cost of introducing potentially high biases due to the error in density ratio estimation. In this paper, we develop a bias-reduced augmentation of their method, which can take advantage of a learned value function to obtain higher accuracy. Our method is doubly robust in that the bias vanishes when either the density ratio or the value function estimation is perfect. In general, when either of them is accurate, the bias can also be reduced. Both theoretical and empirical results show that our method yields significant advantages over previous methods.

We propose a novel algorithm for learning fair representations that can simultaneously mitigate two notions of disparity among different demographic subgroups. Two key components underpinning the design of our algorithm are balanced error rate and conditional alignment of representations. In settings that have historically had discrimination, we are interested in defining fairness with respect to a protected group, the group which has historically been disadvantaged. Among many recent attempts to achieve algorithmic fairness (Dwork et al., 2012; Hardt et al., 2016; Zemel et al., 2013; Zafar et al., 2015), learning fair representations has attracted increasing attention However, it has long been empirically observed (Calders et al., 2009) and recently been proved (Zhao Part of this work was done when Han Zhao was visiting the V ector Institute, Toronto. In this work, we provide an affirmative answer to the above question by proposing an algorithm to align the conditional distributions (on the target variable) of representations across different demographic subgroups.

Across the world, governments are investing in machines that they hope will run their social security systems and other services more cheaply and effectively than humans. The Guardian's Automating Poverty series includes reports from the US, Australia and India as well as the UK. The roles played by technology in these countries are all different. But taken together, the articles reveal how automation, machine learning and artificial intelligence are extending their reach into people's lives through the delivery of public services. As with all automation processes, speed and efficiency provide the rationale.

Hewlett Packard Enterprise Tuesday unveiled a new version of its Aruba Central network management platform outfitted with artificial intelligence-based analytics. "This is a breakthrough with artificial intelligence-based analytics being integrated into Aruba Central for the first time," said Hewlett Packard Enterprise Vice President Dr. Tom Bradicich, HPE Fellow and global head of IoT and Edge Center of Excellence and Labs. "The impact this is going to have on customers is tremendous because these analytics are no longer on a separate tool, program or screen." The new Aruba Central capabilities for the first time allows partners to proactively optimize an SD-WAN rollout based on the AI based analytics from Aruba Central. Aruba Central now includes branch management capabilities with a new SD-WAN Orchestrator that makes it easier for partners to deploy what HPE calls a "large scale edge infrastructure connecting thousands of branch locations with multiple data centers."

The interview took place at the American Water Works Association ACE19 in Denver, Colorado. Nobel Systems' advancement into the digitization and management of water utilities with smart applications using AI and GIS (geographic information systems) fit well with the event's theme, Innovating the Future of Water. Samuel explains how Nobel's new machine learning algorithm predicts the likelihood of pipe ruptures and system failures. Click the play button above to listen.

For a factory where robots toil around the clock to build a rocket with almost no human labor, the sound of grunts echoing across the parking lot make for a jarring contrast. "That's Keanu Reeves' stunt gym," says Tim Ellis, the chief executive and cofounder of Relativity Space, a startup that wants to combine 3D printing and artificial intelligence to do for the rocket what Henry Ford did for the automobile. As we walk among the robots occupying Relativity's factory, he points out the just-completed upper stage of the company's rocket, which will soon be shipped to Mississippi for its first tests. Across the way, he says, gesturing to the outside world, is a recording studio run by Snoop Dogg. Neither of those A-listers have paid a visit to Relativity's rocket factory, but the presence of these unlikely neighbors seems to underscore the company's main talking point: It can make rockets anywhere. In an ideal cosmos, though, its neighbors will be even more alien than Snoop Dogg.

IBM wants to keep its employees from quitting. And it's using artificial intelligence to do it. In a recent CNBC interview, CEO Ginni Rometty said that thanks to AI, the tech and consulting giant can now predict with 95% accuracy which employees are likely to leave in the next six months. The "proactive retention" tool -- which IBM uses internally but is also selling to clients -- analyzes thousands of pieces of data and then nudges managers toward which employees may be on their way out, telling them to "do something now so it never enters their mind," Rometty said. IBM's efforts to use AI to learn which employees might quit is one of the more high-profile recent examples of the way data science, "deep learning" and "predictive analytics" are increasingly infiltrating the traditionally low-tech human-resources department, arming personnel chiefs with more rigorous tools and hard data around the tricky art of managing people.