In this paper we describe eBird, a citizen-science project that takes advantage of human observational capacity and machine learning methods to explore the synergies between human computation and mechanical computation. We call this model a Human/Computer Learning Network, whose core is an active learning feedback loop between humans and machines that dramatically improves the quality of both, and thereby continually improves the effectiveness of the network as a whole. Human/Computer Learning Networks leverage the contributions of a broad recruitment of human observers and processes their contributed data with Artificial Intelligence algorithms leading to a computational power that far exceeds the sum of the individual parts.

We have developed a method for statistical anomaly detection which has been deployed in a tool for condition monitoring of train fleets. The tool is currently used by several railway operators over the world to inspect and visualize the occurrence of event messages generated on the trains. The anomaly detection component helps the operators to quickly find significant deviations from normal behavior and to detect early indications for possible problems. The savings in maintenance costs comes mainly from avoiding costly breakdowns, and have been estimated to several million Euros per year for the tool. In the long run, it is expected that maintenance costs can be reduced with between 5 and 10 % by using the tool.

Dots-And-Boxes is a well-known and widely-played combinatorial game. While the rules of play are very simple, the state space for even very small games is extremely large, and finding the outcome under optimal play is correspondingly hard. In this paper we introduce a Dots-And-Boxes solver which is significantly faster than the current state-of-the-art: over an order-of-magnitude faster on several large problems. Our approach uses Alpha-Beta search and applies a number of techniques---both problem-specific and general---that reduce the search space to a manageable size. Using these techniques, we have determined for the first time that Dots-And-Boxes on a board of 4 x 5 boxes is a tie given optimal play; this is the largest game solved to date.

In a Smarter City, available resources are harnessed safely, sustainably and efficiently to achieve positive, measurable economic and societal outcomes. Data and information from people, systems and things is the single most scalable resource available to city stakeholders but difficult to publish, organize, discover and consume, especially in a real-time context. Enabling city information as a utility, through a robust (expressive, dynamic, scalable) and (critically) a sustainable technology and socially synergistic ecosystem, could drive significant benefits and opportunities. In the context of stream data (as real-time, gigantic, noisy and private data), this paper targets research issues we identify as important to harness the fused information resources of cities, Citizens and Stakeholders to reach the concept of Smarter Cities.

The aims of this workshop are to (1) Draw the attention of the AI community to the research challenges and opportunities in semantic cities. (2) Draw the attention on the multidisciplinary dimension and its impact on semantic cities such as transportation, energy, water management. (3) Identify unique issues of this domain and what new techniques may be needed. As example, since governments and citizens are involved data security and privacy are first-class concerns (4) Promoting more cities to become semantic cities (5) Elaborating a (semantic data) benchmark for testing AI techniques on semantic cities. (6) Provide a platform for sharing best-practices and discussion.

Refining a network topology is an important network management technique. Nevertheless, determining the appropriate steps to transform a network from one topology to another, in a way that minimizes service disruptions, has received little attention. This is a critical problem since service disruptions can be particularly harmful and costly for networks hosting mission-critical services. In this paper, we introduce the incremental network transformation (INT) problem and explore this problem in the context of automated planning. We define two metrics to measure the quality of generated transformation plans, one of which is amenable to classical propositional planning. We find that while state-of-the-art domain-independent planning techniques are effective at finding high-quality solutions for small problem instances, they cannot scale to solve realistically sized INT instances. To address the shortcomings of existing approaches, we developed a number of domain-dependent planners that use novel domain-specific heuristics. We empirically evaluated our planners on a wide range of synthetic network topologies. Our results illustrate that our automated planning inspired techniques are effective on realistically sized INT problems. We envision that our approach could eventually provide a compelling addition to the arsenal of techniques employed by network practitioners to support network refinement with minimal disruption to running services.

We present the domain-independent HRFF algorithm, which solves goal-oriented HMDPs by incrementally aggregating plans generated by the Metric-FF planner into a policy defined over discrete and continuous state variables. HRFF takes into account non-monotonic state variables, and complex combinations of many discrete and continuous probability distributions. We introduce new data structures and algorithmic paradigms to deal with continuous state spaces: hybrid hierarchical hash tables, domain determinization based on dynamic domain sampling or on static computation of probability distributions' modes, optimization settings under Metric-FF based on plan probability and length. We compare with HAO* on the Rover domain and show that HRFF outperforms HAO* by many order of magnitudes in terms of computation time and memory usage. We also experiment challenging and combinatorial HMDP versions of benchmarks from numeric classical planning, with continuous dead-ends and non-monotonic continuous state variables.

Neurules are a type of neuro-symbolic rules integrating neurocomputing and production rules. Each neurule is represented as an adaline unit. Neurules exhibit characteristics such as modularity, naturalness and ability to perform interactive and integrated inferences. One way of producing a neurule base is through conversion of an existing symbolic rule base yielding an equivalent but more compact rule base. The conversion process merges symbolic rules having the same conclusion into one or more neurules. Due to the inability of the adaline unit to handle inseparability, more than one neurule for each conclusion may be produced. In this paper, we define criteria concerning the ability or inability to convert a rule set into a single neurule. Definition of criteria determining whether a set of symbolic rules can (or cannot) be converted into a single, equivalent but more compact rule is of general representational interest. With application of such criteria, the conversion process of symbolic rules into neurules becomes more time- and space-efficient by omitting useless trainings. Experimental results are promising.

The DARPA Mind’s Eye program seeks to develop in machines a capability that currently exists only in animals: visual intelligence. This paper describes a Neural-Symbolic Cognitive Agent that integrates neural learning, symbolic knowledge representation and temporal reasoning in a visual intelligent system that can reason about actions of entities observed in video. Results have shown that the system is able to learn and represent the underlying semantics of the actions from observation and use this for several visual intelligent tasks, like recognition, description, anomaly detection and gap-filling.

Optimal solutions for multi-agent pathfinding problems are often too expensive to compute. For this reason, suboptimal approaches have been widely studied in the literature. Specifically, in recent years a number of efficient suboptimal algorithms that are complete for certain subclasses have been proposed at highly-rated robotics and AI conferences. However, it turns out that the problem of non-optimal multi-agent pathfinding has already been completely solved in another research community in the 1980s. In this paper, we would like to bring this earlier related work to the attention of the robotics and AI communities.