Unification in Description Logics (DLs) has been proposed as an inference service that can, for example, be used to detect redundancies in ontologies. The inexpressive Description Logic EL is of particular interest in this context since, on the one hand, several large biomedical ontologies are defined using EL. On the other hand, unification in EL has recently been shown to be NP-complete, and thus of significantly lower complexity than unification in other DLs of similarly restricted expressive power. However, the unification algorithms for EL developed so far cannot deal with general concept inclusion axioms (GCIs). This paper makes a considerable step towards addressing this problem, but the GCIs our new unification algorithm can deal with still need to satisfy a certain cycle restriction.

Storing a new pattern in a palimpsest memory system comes at the cost of interfering with the memory traces of previously stored items. Knowing the age of a pattern thus becomes critical for recalling it faithfully. This implies that there should be a tight coupling between estimates of age, as a form of familiarity, and the neural dynamics of recollection, something which current theories omit. Using a normative model of autoassociative memory, we show that a dual memory system, consisting of two interacting modules for familiarity and recollection, has best performance for both recollection and recognition. This finding provides a new window onto actively contentious psychological and neural aspects of recognition memory.

In this work we use Branch-and-Bound (BB) to efficiently detect objects with deformable part models. Instead of evaluating the classifier score exhaustively over image locations and scales, we use BB to focus on promising image locations. The core problem is to compute bounds that accommodate part deformations; for this we adapt the Dual Trees data structure to our problem. We evaluate our approach using Mixture-of-Deformable Part Models. We obtain exactly the same results but are 10-20 times faster on average. We also develop a multiple-object detection variation of the system, where hypotheses for 20 categories are inserted in a common priority queue. For the problem of finding the strongest category in an image this results in up to a 100-fold speedup.

Given one feature of a novel animal, humans readily make inferences about other features of the animal. For example, winged creatures often fly, and creatures that eat fish often live in the water. We explore the knowledge that supports these inferences and compare two approaches. The first approach proposes that humans rely on abstract representations of dependency relationships between features, and is formalized here as a graphical model. The second approach proposes that humans rely on specific knowledge of previously encountered animals, and is formalized here as a family of exemplar models. We evaluate these models using a task where participants reason about chimeras, or animals with pairs of features that have not previously been observed to co-occur. The results support the hypothesis that humans rely on explicit representations of relationships between features.

This work introduces Divide-Factor-Combine (DFC), a parallel divide-and-conquer framework for noisy matrix factorization. DFC divides a large-scale matrix factorization task into smaller subproblems, solves each subproblem in parallel using an arbitrary base matrix factorization algorithm, and combines the subproblem solutions using techniques from randomized matrix approximation. Our experiments with collaborative filtering, video background modeling, and simulated data demonstrate the near-linear to super-linear speed-ups attainable with this approach. Moreover, our analysis shows that DFC enjoys high-probability recovery guarantees comparable to those of its base algorithm.

This work presents Drake, a dynamic executive for temporal plans with choice. Dynamic plan execution strategies allow an autonomous agent to react quickly to unfolding events, improving the robustness of the agent. Prior work developed methods for dynamically dispatching Simple Temporal Networks, and further research enriched the expressiveness of the plans executives could handle, including discrete choices, which are the focus of this work. However, in some approaches to date, these additional choices induce significant storage or latency requirements to make flexible execution possible. Drake is designed to leverage the low latency made possible by a preprocessing step called compilation, while avoiding high memory costs through a compact representation. We leverage the concepts of labels and environments, taken from prior work in Assumption-based Truth Maintenance Systems (ATMS), to concisely record the implications of the discrete choices, exploiting the structure of the plan to avoid redundant reasoning or storage. Our labeling and maintenance scheme, called the Labeled Value Set Maintenance System, is distinguished by its focus on properties fundamental to temporal problems, and, more generally, weighted graph algorithms. In particular, the maintenance system focuses on maintaining a minimal representation of non-dominated constraints. We benchmark Drake's performance on random structured problems, and find that Drake reduces the size of the compiled representation by a factor of over 500 for large problems, while incurring only a modest increase in run-time latency, compared to prior work in compiled executives for temporal plans with discrete choices.

A critical prerequisite for human-level cognitive systems is having a rich conceptual understanding of the world. We describe a system that learns conceptual knowledge by deep understanding of WordNet glosses. While WordNet is often criticized for having a too fine-grained approach to word senses, the set of glosses do generally capture useful knowledge about the world and encode a substantial knowledge base about everyday concepts. Unlike previous approaches that have built ontologies of atomic concepts from the provided WordNet hierarchies, we construct complex concepts compositionally using description logic and perform reasoning to derive the best classification of knowledge. We view this work as simultaneously accomplishing two goals: building a rich semantic lexicon useful for natural language processing, and building a knowledge base that encodes common-sense knowledge.

Cognitive systems with human-level intelligence must dis­play a wide range of abilities, including reasoning about the beliefs of others, hypothetical and future situations, quanti­fiers, probabilities, and counterfactuals. While each of these deals in some way with reasoning about alternative states of reality, no single knowledge representation framework deals with them in a unified and scalable manner. As a conse­quence it is difficult to build cognitive systems for domains that require each of these abilities to be used together. To enable this integration we propose a representational framework based on synchronizing beliefs between worlds. Using this framework, each of these tasks can be reformu­lated into a reasoning problem involving worlds. This demonstrates that the notions of worlds and inheritance can bring significant parsimony and broad new abilities to knowledge representation.

Scone is a knowledge-base system developed specifically to support human-like common-sense reasoning and the understanding of human language. One of the unusual features of Scone is its multiple-context system. Each context represents a distinct world-model, but a context can inherit most of the knowledge of another context, explicitly representing just the differences. We explore how this multiple-context mechanism can be used to emulate some aspects of human mental behavior that are difficult or impossible to emulate in other representational formalisms. These include reasoning about hypothetical or counter-factual situations; understanding how the world model changes over time due to specific actions or spontaneous changes; and reasoning about the knowledge and beliefs of other agents, and how their mental state may affect the actions of those agents.

In this paper, we address the problem of communicating, interpreting,and executing complex yet abstract instructions to a robot teammember. This requires specifying the tasks in an unambiguous manner,translating them into operational procedures, and carrying outthose procedures in a persistent yet reactive manner. We reportour response to these issues, after which we demonstrate theircombined use in controlling a mobile robot in a multi-room officesetting on tasks similar to those in search-and-rescue operations.We conclude by discussing related research and suggesting directionsfor future work.