When you engage in international travel, you may one day find yourself face-to-face with border security that is polite, bilingual and responsive--and robotic. The Automated Virtual Agent for Truth Assessments in Real Time (AVATAR) is currently being tested in conjunction with the Canadian Border Services Agency (CBSA) to help border security agents determine whether travelers coming into Canada may have undisclosed motives for entering the country. "AVATAR is a kiosk, much like an airport check-in or grocery store self-checkout kiosk," said San Diego State University management information systems professor Aaron Elkins. "However, this kiosk has a face on the screen that asks questions of travelers and can detect changes in physiology and behavior during the interview. The system can detect changes in the eyes, voice, gestures and posture to determine potential risk. It can even tell when you're curling your toes."

Hierarchy Of Multi-label classifiers (HOMER) is a multi-label learning algorithm that breaks the initial learning task to several, easier sub-tasks by first constructing a hierarchy of labels from a given label set and secondly employing a given base multi-label classifier (MLC) to the resulting sub-problems. The primary goal is to effectively address class imbalance and scalability issues that often arise in real-world multi-label classification problems. In this work, we present the general setup for a HOMER model and a simple extension of the algorithm that is suited for MLCs that output rankings. Furthermore, we provide a detailed analysis of the properties of the algorithm, both from an aspect of effectiveness and computational complexity. A secondary contribution involves the presentation of a balanced variant of the k means algorithm, which serves in the first step of the label hierarchy construction. We conduct extensive experiments on six real-world datasets, studying empirically HOMER's parameters and providing examples of instantiations of the algorithm with different clustering approaches and MLCs, The empirical results demonstrate a significant improvement over the given base MLC.

Machines are crucial with how consumers interact with businesses, not just through purchases but also through enquiries. It's thought that machine learning will not only radically alter the customer service industry, but all industries. Thinking about it in terms of pervious technology revolutions, the age of steam created the industrial revolution by replacing man with coal, the age of robotics also moved the manufacturing industry's dependency on mankind and in the future, artificial intelligence and machine learning holds the potential to replace cognitive functions of the human mind. But what does this really mean and how will it change the way that businesses interact with their customers? Customers today demand access to immediate information and want issues to be solved instantly at the click of a button. As a result, more businesses are now tracking a customer's engagement history with a brand through a range of data sources such as social media, purchase history and customer support tickets, to provide a personalised experience in a shorter timeframe.

As packages continue to arrive from this year's record-breaking Black Friday weekend, it's no doubt you're seeing Amazon packages complete with front-and-center ads for Amazon's Echo and Dot devices. You may even be one of the reported millions that ordered one that weekend. These are more than just devices -- they are Alexa-enabled and are helping Alexa further integrate into consumers' lives. And Alexa isn't alone: from Alexa to Google Now to Microsoft's Cortana to Apple's Siri, we have a budding class of intelligent agents (IAs) on the rise. In 2015, 45% of US online adults used at least one.

Coalition formation typically involves the coming together of multiple, heterogeneous, agents to achieve both their individual and collective goals. In this paper, we focus on a special case of coalition formation known as Graph-Constrained Coalition Formation (GCCF) whereby a network connecting the agents constrains the formation of coalitions. We focus on this type of problem given that in many real-world applications, agents may be connected by a communication network or only trust certain peers in their social network. We propose a novel representation of this problem based on the concept of edge contraction, which allows us to model the search space induced by the GCCF problem as a rooted tree. Then, we propose an anytime solution algorithm (CFSS), which is particularly efficient when applied to a general class of characteristic functions called $m+a$ functions. Moreover, we show how CFSS can be efficiently parallelised to solve GCCF using a non-redundant partition of the search space. We benchmark CFSS on both synthetic and realistic scenarios, using a real-world dataset consisting of the energy consumption of a large number of households in the UK. Our results show that, in the best case, the serial version of CFSS is 4 orders of magnitude faster than the state of the art, while the parallel version is 9.44 times faster than the serial version on a 12-core machine. Moreover, CFSS is the first approach to provide anytime approximate solutions with quality guarantees for very large systems of agents (i.e., with more than 2700 agents).

A key requirement for the current generation of artificial decision-makers is that they should adapt well to changes in unexpected situations. This paper addresses the situation in which an AI for aerial dog fighting, with tunable parameters that govern its behavior, must optimize behavior with respect to an objective function that is evaluated and learned through simulations. Bayesian optimization with a Gaussian Process surrogate is used as the method for investigating the objective function. One key benefit is that during optimization, the Gaussian Process learns a global estimate of the true objective function, with predicted outcomes and a statistical measure of confidence in areas that haven't been investigated yet. Having a model of the objective function is important for being able to understand possible outcomes in the decision space; for example this is crucial for training and providing feedback to human pilots. However, standard Bayesian optimization does not perform consistently or provide an accurate Gaussian Process surrogate function for highly volatile objective functions. We treat these problems by introducing a novel sampling technique called Hybrid Repeat/Multi-point Sampling. This technique gives the AI ability to learn optimum behaviors in a highly uncertain environment. More importantly, it not only improves the reliability of the optimization, but also creates a better model of the entire objective surface. With this improved model the agent is equipped to more accurately/efficiently predict performance in unexplored scenarios.

I had an interesting chat with Michael Fauscette, the chief research officer for G2 Crowd, a site that focuses on reviewing business software and services. His research identified a major trend, the application of artificial intelligence (AI) for HR. I have a degree in this area, and my first career path, which didn't survive college, was supposed to be in HR so the topic interested me. As we chatted it became clear that Michael and I were in agreement about the future of AI. We both believe that soon we'll be up to our armpits in AI agents in virtually every area of business operations, and IT shops should be at the very least anticipate the possibility that robots may start replacing employees.

In multiagent systems, social choice functions can help aggregate the distinct preferences that agents have over alternatives, enabling them to settle on a single choice. Despite the basic manipulability of all reasonable voting systems, it would still be desirable to find ways to reach plausible outcomes, which are stable states, i.e., a situation where no agent would wish to change its vote. One possibility is an iterative process in which, after everyone initially votes, participants may change their votes, one voter at a time. This technique, explored in previous work, converges to a Nash equilibrium when Plurality voting is used, along with a tie-breaking rule that chooses a winner according to a linear order of preferences over candidates. In this paper, we both consider limitations of the iterative voting method, as well as expanding upon it. We demonstrate the significance of tie-breaking rules, showing that no iterative scoring rule converges for all tie-breaking. However, using a restricted tie-breaking rule (such as the linear order rule used in previous work) does not by itself ensure convergence. We prove that in addition to plurality, the veto voting rule converges as well using a linear order tie-breaking rule. However, we show that these two voting rules are the only scoring rules that converge, regardless of tie-breaking mechanism.

Delegates at an event hosted by Accenture last month in the Conrad Hotel in lower Manhattan were welcomed and registered by a smiling Amelia. But Amelia does not work only in events. She is a hologram -- a cognitive agent who can take on a wide variety of service desk roles, emulating human intelligence and capable of natural interaction with people. The age of automation and artificial intelligence (AI) has been predicted for decades -- and it may finally be arriving, thanks to the explosion in data, the fuel that powers the AI machines. Consulting firms are not only implementing automation and AI for clients but also using it to transform their own back-office functions and operations.

Hoping to teach AI agents the common sense they need to solve arbitrary tasks without specific training, OpenAI on Monday will introduce Universe, a collection of virtualized video games, browser interfaces, and applications that serve as a training ground for code-based decision making. Universe is open-source middleware that supports Gym, the organization's toolkit for developing and evaluating reinforcement learning (RL) algorithms. RL is used to train software perform specific actions, such as playing a videogame or making a 3D model walk, under a framework that prioritizes actions through a reward scheme. Universe aims to accelerate the education of AI agents by broadening the number of available training resources. Previously, according to OpenAI, the largest RL resource consisted of 55 Atari games, the Atari Learning Environment.