While it may be some time before we commute to work in flying cars or seek a transfer to our company's lunar outpost, another concept once thought outside the realm of modern reality is now increasingly ordinary in the contemporary workplace: working side-by-side with robots and machines capable of artificial intelligence. This article provides an overview of some of the ways in which these once-futuristic technologies are being integrated in today's work environment, and offers best practice suggestions for human resources professionals and in-house counsel adapting to these developments. We have reached the point of "minimum viability" when it comes to artificial intelligence (AI) – we can now count on the reliable use of AI products to perform meaningful work. Long past are the days when AI was little more than a novelty (remember asking iPhone's Siri whether it was raining outside?). The technology to integrate AI into necessary functions is now available, the data needed to power AI has been accumulated, and investors are pouring money into AI systems to make them a worthwhile part of everyday life. Having reached minimum viability, we now stand on the cusp of revolution.

Before the giant E3 video game exhibition takes place every year, it is proceeded by a series of vast press events, where publishers hope to snag just a little of the world's attention with their latest mega releases. Filling huge venues and live-streamed to a global audience of millions, these one-hour hype-fests can make all the difference between blockbusting success and ignoble failure. Here, then, are our 17 favourite announcements, culled from all the pre-E3 shows. We've stuck to games that were either revealed for the first time on stage, or were finally confirmed after months of gossip, leaks and rumours. These are the titles we want to discover more about at the show, and over the months to come.

When Swedbank customers face a problem, they reach out to Nina, the bank's virtual assistant. Visitors to Mizuho Bank are greeted by Pepper, a humanoid robot standing four feet tall. Santander allows payments to be activated by voice, and JP Morgan Chase now uses machine learning to review commercial loan agreements in seconds, a task that used to take 3,60,000 manhours every year. Wherever you look in the world of financial services, you will find some form of artificial intelligence (AI) at work. AI technologies such as machine learning and speech recognition are quietly working behind the scenes to improve lending decisions and prevent fraud.

We present a probabilistic framework for overlapping community discovery and link prediction for relational data, given as a graph. The proposed framework has: (1) a deep architecture which enables us to infer multiple layers of latent features/communities for each node, providing superior link prediction performance on more complex networks and better interpretability of the latent features; and (2) a regression model which allows directly conditioning the node latent features on the side information available in form of node attributes. Our framework handles both (1) and (2) via a clean, unified model, which enjoys full local conjugacy via data augmentation, and facilitates efficient inference via closed form Gibbs sampling. Moreover, inference cost scales in the number of edges which is attractive for massive but sparse networks. Our framework is also easily extendable to model weighted networks with count-valued edges. We compare with various state-of-the-art methods and report results, both quantitative and qualitative, on several benchmark data sets.

A little striped fish that lives among rocks in Lake Tanganyika in East Africa has the unexpected ability to recognise individual faces, which it uses to keep menacing strangers in sight. The cichlid (Julidochromis transcriptus) identifies unfamiliar individuals by looking at the pattern around their eyes rather than at other body parts such as their fins or trunk, researchers have discovered. While facial recognition has been tested in some mammals, including apes, and in birds, animals such as fish or wasps were erroneously thought to have brains too simple for the task. After recent research showed that aquarium fish can be thought to identify the faces of their human owners, the Tanganyikan cichlid has now demonstrated how facial recognition is used in the wild. Because the fish lives in rock crevices hidden by vegetation on the lakebed, only a small part of its body tends to be visible at any given time.

Machine learning is going to alter our world fundamentally for the better, improving healthcare and the manufacturing industry, and assisting in the prediction of supply and demand levels across a range of industries. For those who are into science-fiction, the term "machine learning" immediately conjures up images of computers taking over the world, either to send murderous terminators from the future to our present or to place us all inside the Matrix as living power batteries. Fortunately, the truth about machine learning is not only far more prosaic, but also much more promising for the future of the human race. Basically, machine learning uses algorithms that iteratively learn from data, meaning that it enables computers to find hidden insights without being explicitly programmed where to look. The iterative aspect is especially important, as it means that as the computer is exposed to new data, it is able to adapt independently.

Recent work in multi-agent path planning has provided a number of optimal and suboptimal solvers that can efficiently find solutions to problems of growing complexity. Solvers based on Conflict-Based Search (CBS) combine single-agent solvers with shared constraints between agents to find feasible solutions. Suboptimal variants of CBS introduce alternate heuristics to avoid conflicts. In this paper we study the multi-agent planning problem in the context of non-holonomic vehicles planning on a lattice. We propose that in addition to using heuristics to avoid conflicts, we can plan using a hierarchy of movement constraints to efficiently avoid conflicts. We develop a new extension to the CBS algorithm, CBS with constraint layering (CBS+CL), which iteratively applies different movement constraint models during the CBS planning process. Our results show that this approach allows us to solve for about 2.4 times more agents in the same amount of time when compared to regular CBS without using a constraint hierarchy.

One of the most successful approaches to automated planning is the translation to propositional satisfiability (SA T). We employ incremental SA T solving to increase the capabilities of several modern encodings for SA T based planning. Experiments based on benchmarks from the 2014 International Planning Competition show that an incremental approach significantly outperforms non incremental solving. Although we are using sequential scheduling of makespans, we can outperform the state-of-the-art SA T based planning system Madagascar in the number of solved instances.

In this paper we study bidirectional state space search with consistent heuristics, with a focus on obtaining sufficient conditions for node expansion, that is, conditions characterizing nodes that must be expanded by any admissible bidirectional search algorithm. We provide such conditions for front-to-front and front-to-end bidirectional search. The sufficient conditions are used to prove that the front-to-front bidirectional search algorithm BDS1 is optimally efficient, in terms of node expansion, among a broad class of bidirectional search algorithms, for a specific class of problem instances. Dechter and Pearl's well-known result on sufficient conditions for node expansion by unidirectional algorithms such as A* is shown to be a special case of our results.

Plan-Verification is the task of determining whether a plan is a solution to a given planning problem. Any plan verifier has, apart from showing that verifying plans is possible in practice, a wide range of possible applications. These include mixed-initiative planning, where a user is integrated into the planning process, and local search, e.g., for post-optimising plans or for plan repair. In addition to its practical interest, plan verification is also a problem worth investigating for theoretical reasons. Recent work showed plan verification for hierarchical planning problems to be NP-complete, as opposed to classical planning where it is in P. As such, plan verification for hierarchical planning problem was — until now — not possible. We describe the first plan verifier for hierarchical planning. It uses a translation of the problem into a SAT formula. Further we conduct an empirical evaluation, showing that the correct output is produced within acceptable time.