Sparse distributed memory is an auto-associative memory system that stores high dimensional Boolean vectors. Here we present an extension of the original SDM, the Integer SDM that uses modular arithmetic integer vectors rather than binary vectors. This extension preserves many of the desirable properties of the original SDM: auto-associativity, content addressability, distributed storage, and robustness over noisy inputs. In addition, it improves the representation capabilities of the memory and is more robust over normalization. It can also be extended to support forgetting and reliable sequence storage.

One of the challenges for artificial agents is managing the complexity of their environment as they learn tasks especially if they are grounded in the physical world. A scalable solution to address the state explosion problem is thus a prerequisite of physically grounded, agentbased systems. This paper presents a framework for developing grounded, symbolic representations aimed at scaling subsequent learning as well as forming a basis for symbolic reasoning. These symbols partition the environment so the agent need only consider an abstract view of the original space when learning new tasks and allows it to apply acquired symbols to novel situations.

In this paper we present a new method for ontology selection in a reuse context. The novel feature of this method is the iterative selection of the reused ontologies. Ontology selection is guided by the user according to his requirements and his perception to the target domain. Starting from a first selected ontology, the concepts with the weakest density are identified then the ontology developer is enabled to choose among them the ones to be refined in order to cover a specific scope of the domain.

Analyzing international political behavior based on similar precedent circumstances is one of the basic techniques that policymakers use to monitor and assess current situations. Our goal is to investigate how to analyze geopolitical conflicts as sequences of events and to determine what probabilistic models are suitable to perform these analyses. In this paper, we evaluate the performance of N-grams models on the problem of forecasting political conflicts from sequences of events. For the current phase of the project, we focused on event data collected from the Balkans war in the 1990's. Our experimental results indicate that N-gram models have impressive results when applied to this data set, with accuracies above 90\% for most configurations.

In this paper, we introduce an admissible heuristic for hybrid planning with preferences. Hybrid planning is the fusion of hierarchical task network (HTN) planning with partial order causal link (POCL) planning. We consider preferences to be soft goals - facts one would like to see satisfied in a goal state, but which do not have to hold necessarily. Our heuristic estimates the best quality of any solution that can be developed from the current plan under consideration. It can thus be used by any branch-and-bound algorithm that performs search in the space of plans to prune suboptimal plans from the search space.

Biologists seek concise, testable models of behavior for the animals they study. We suggest a robot programming paradigm in which animal behaviors are described as robot controllers to support a cycle of hypothesis generation and testing of animal models. In this work we illustrate that approach by modeling the hunting behavior of a captive colony of Aphaenogaster cockerelli , a desert harvester ant. In laboratory animal experiments we introduce live prey (fruit flies) into the foraging arena of the colony. We observe the behavior of the ants, and we measure aspects of their performance in capturing the prey. Based on these observations we create a model of their behavior using Clay, a Java library developed for coding hybrid controllers in a behavior-based manner. We then validate that model in quantitative comparisons with the live animal behavior.

The dynamic between speaker intent and listener perception is played out in the variation of acoustical cues by the speaker that must be interpreted by the listener to determine in an appropriate way. Emotion speech research must rely on either acted intent (i.e., an actor attempting to express an emotion) or listener perception (i.e., listening tests to assign emotional categories to non-acted data) to define ground truth labels for analysis. The emotion labels are described either using emotion dimension or emotion category. This study examines the two emotion characterization strategies dimension and category in communication of emotion embedded in speech as expressed through acted intent and the perception of emotion determined by a group of listeners. The results reveal that, without context information, intended emotion categories could be perceived by listeners with the averaged accuracy rate five times of chance in category. Also, the trend of listener ratings between emotion dimensions (valence/arousal) and emotional word categories was shown to be well correlated. Furthermore, while listeners confused the specific identity of certain emotional expressions, they were generally very accurate at identifying the intended affective space of the actor as determined by intended valence and arousal.

Entity coreference is the process to decide which identifiers (e.g., person names, locations, ontology instances, etc.) refer to the same real world entity. In the Semantic Web, entity coreference can be used to detect equivalence relationships between heterogeneous Semantic Web datasets to explicitly link coreferent ontology instances via the owl:sameAs property. Due to the large scale of Semantic Web data today, we propose two pruning techniques for scalably detecting owl:sameAs links between ontology instances by comparing the similarity of their context graphs. First, a sampling based technique is designed to estimate the potential contribution of each RDF node in the context graph and prune insignificant context. Furthermore, a utility function is defined to reduce the cost of performing such estimations. We evaluate our pruning techniques on three Semantic Web instance categories. We show that the pruning techniques enable the entity coreference system to run 10 to 35 times faster than without them while still maintaining comparably good F1-scores.

Gene selection has become a vital component in the learning process when using high-dimensional gene expression data. Although extensive research has been done towards evaluating the performance of classifiers trained with the selected features, the stability of feature ranking techniques has received relatively little study. This work evaluates the robustness of eleven threshold-based feature selection techniques, examining the impact of data sampling and class noise on the stability of feature selection. To assess the robustness of feature selection techniques, we use four groups of gene expression datasets, employ eleven threshold-based feature rankers, and generate artificial class noise to better simulate real-world datasets. The results demonstrate that although no ranker consistently outperforms the others, MI and Dev show the best stability on average, while GI and PR show the least stability on average. Results also show that trying to balance datasets through data sampling has on average no positive impact on the stability of feature ranking techniques applied to those datasets. In addition, increased feature subset sizes improve stability, but only does so reliably for noisy datasets.

Recommender systems assist users in the daunting task of sifting through large amounts of data in order to select relevant information or items. Common examples include consumer products and services, such as for songs, books, articles, etc. Unfortunately, such systems may be subject to attack by malicious users who want to manipulate the system’s recommendations to suit their needs: to promote their own (or demote a competitor’s) product/service, or to cause disruption in the recommender system. Attacks can cause the recommender system to become unreliable and untrustworthy, resulting in user dissatisfaction. Developers already face tradeoffs in system efficiency and accuracy, and designing for robustness adds an additional dimension for consideration. In this paper, we show how the underlying implementation choices for item-based and user-based Collaborative Filtering recommender systems can affect the accuracy and robustness of recommender systems. We also show how accuracy and robustness can change over a system’s lifetime by analyzing a set of temporal snapshots from system usage over time. Results provide insight into some of the tradeoffs between robustness and accuracy that operators may need to consider in development and evaluation.