Goal-driven automated composition of software components is an important problem with applications in Web service composition and stream processing systems. The popular approach to address this problem is to build the composition automatically using Artificial Intelligence planning. However, it is shown that some of these popular planning approaches may neither be feasible nor scalable for many real large-scale flow-based applications. Recent advances have proven that the automated composition problem can take advantage of expert knowledge restricting the ways in which different reusable components can be composed. This knowledge can be represented using an extensible composition template or pattern. In prior work, a flow pattern language called Cascade and its corresponding specialized planner have shown the best performance in these domains. In this paper, we propose to address this problem using Hierarchical Task Network (HTN) planning. To this end, we propose an automated approach of creating an HTN-based problem from the Cascade representation of the flow patterns. The resulting technique not only allows us to use the HTN planning paradigm and its many advantages including added expressivity but also enables optimization and customization of composition with respect to preferences and constraints. Further, we propose and develop a lookahead heuristic and show that it significantly reduces the planning time. We have performed extensive experimentation in the context of the stream processing application and evaluated applicability and performance of our approach.

This paper presents a prototype system called SFplanner which uses an automated planning technique to generate workflows for reconfiguring a computing infrastructure. The system allows an administrator to specify a configuration task which consists of current state, desired state and global constraints. This task is compiled to a grounded finite-domain representation as the input for the standard (unmodified) Fast-Downward planner in order to automatically generate a workflow. The execution of the workflow will bring the system into the desired state, preserving the global constraints at every stage of the workflow.

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 neural basis of speech recognition and, more generally, sound processing is not well understood. A simple subset of the task of speech recognition, learning to categorise vowel sounds, provides some insights into the more general problems. A simulated neural system that performs this task is described. The system is based on relatively accurate fatiguing leaky integrate and fire neurons, and learns to categorise three categories of vowel sounds. The input to the system is in the form of neural stimulation that relatively accurately reflects the response of biological neurons in the ear to auditory input. The system correctly categorises 91.71% of the vowel sounds using a five-fold test. The system is a sound model of the neuropsychological task of phoneme categorisation, all be it a far from perfect model. As such, it provides an entry into a better understanding of the neuro-psychological mechanisms behind sound processing.

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.

For nearly 25 years my research group has investigated the use of domain knowledge, expressed in some version of mathematical logic, that is refined or exploited by numeric-based learning algorithms. These include what we called knowledge-based neural networks and knowledge-based support vector machines. I will cover the key ideas of these methods, as well as the behind-the-scenes motivations that lead to them. I will also describe why we switched from using the phrase 'prior knowledge' to using 'advice.' Finally, I will cover some of our recent work on fast learning and inference for Markov Logic Networks (which can be viewed as a knowledge-based graphical model).

Artificial intelligence (AI) researchers continue to face large challenges in their quest to develop truly intelligent systems. Topics of interest at the workshop include the representation of symbolic knowledge by connectionist systems; integrated neural-symbolic learning approaches; extraction of symbolic knowledge from trained neural networks; integrated neural-symbolic reasoning; biologically-inspired neural-symbolic integration; integration of logic and probabilities in neural networks; structured learning and relational learning in neural networks; applications in robotics, simulation, fraud prevention, semantic web, soware engineering, fault diagnosis, bioinformatics, visual intelligence, and so on.

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.

Several variants of A* have been recently proposed for find-ing optimal solutions for the multi-agent pathfinding (MAPF)problem. However, these variants have not been deeply com-pared either quantitatively or qualitatively. In this paper weaim to fill this gap. In addition to obtaining a deeper under-standing of the existing algorithms, we describe in detail theapplication of the new enhanced partial-expansion techniqueto MAPF and show how pattern databases can be applied ontop of this technique.

In our ongoing work, we aim to control a team of agents soas to achieve a prescribed goal state while being confidentthat collisions with other agents are avoided. Each agent isassociated with a feedback controlled plant, whose continu-ous state trajectories follow some stochastic differential dy-namics. To this end we describe a collision-detection modulebased on a distribution-independent probabilistic bound andemploy a fixed priority method to resolve collisions. Dueto their practical importance, multi-agent collision avoid-ance and control have been extensively studied across differ-ent communities including AI, robotics and control. How-ever, these works typically assume linear and discrete dy-namic models; by contrast, our work intends to overcomethese limitations and to present solutions for continuousstate space. While our current experiments were conductedwith linear stochastic differential equation (SDE) modelswith state-independent noise (yielding Gaussian processes)we believe that our approach could also be applicable to non-Gaussian cases with state-dependent uncertainties.