We present a cognitive design assistance system equipped with analytical capabilities aimed at anticipating architectural building design performance with respect to people-centred functional design goals. The paper focuses on the system capability to generate "narratives of visuo-locomotive user experience" from digital computer-aided architecture design (CAAD) models. The system is based on an underlying declarative narrative representation and computation framework pertaining to conceptual, geometric, and qualitative spatial knowledge. The semantics of the declarative narrative model, i.e., the overall   representation and computation model, is founded on: (a). conceptual knowledge formalised in an OWL ontology; (b). a general spatial representation and reasoning engine implemented in constraint logic programming; and (c). a declaratively encoded (narrative) construction process (based on search over graph structures) implemented in answer-set programming. We emphasise and demonstrate: complete system implementation, scalability, and robust performance & integration with industry-scale architecture industry tools (e.g., Revit, ArchiCAD) & standards (BIM, IFC).

We study finite model reasoning in expressive Horn description logics (DLs), starting with a reduction of finite ABox consistency to unrestricted ABox consistency. The reduction relies on reversing certain cycles in the TBox, an approach that originated in database theory, was later adapted to the inexpressive DL DL-Lite_F , and is shown here to extend to the expressive Horn DL Horn-ALCFI . The model construction used to establish correctness makes the structure of finite models more explicit than existing approaches to finite model reasoning in expressive DLs that rely on solving systems of inequations over the integers. Since the reduction incurs an exponential blow-up, we then develop a dedicated consequence-based algorithm for finite ABox consistency in Horn-ALCFI that implements the reduction on-the-fly rather than executing it up-front. The algorithm has optimal worst-case complexity and provides a promising foundation for implementations. We next show that our approach can be adapted to finite (positive existential) query answering relative to Horn-ALCFI TBoxes, proving that this problem is EXPTIME-complete in combined complexity and PTIME-complete in data complexity. For finite satisfiability and subsumption, we also show that our techniques extend to Horn-SHIQ.

We study disambiguating of pronoun references in Winograd Schemas, which are part of the Winograd Schema Challenge, a proposed replacement for the Turing test. In particular we consider sentences where the pronoun can be resolved to both antecedents without semantic violations in world knowledge, that means for both readings of the sentence there is a possible consistent world. Nevertheless humans will strongly prefer one answer, which can be explained by pragmatic effects described in Relevance Theory. We state formal optimization criteria based on principles of Relevance Theory in a simplification of Roger Schank’s graph framework for natural language understanding. We perform experiments using Answer Set Programming and report the usefulness of our criteria for disambiguation and their sensitivity to parameter variations.

Tackling large approximate dynamic programming or reinforcement learning problems requires methods that can exploit regularities, or intrinsic structure, of the problem in hand. Most current methods are geared towards exploiting the regularities of either the value function or the policy. We introduce a general classification-based approximate policy iteration (CAPI) framework, which encompasses a large class of algorithms that can exploit regularities of both the value function and the policy space, depending on what is advantageous. This framework has two main components: a generic value function estimator and a classifier that learns a policy based on the estimated value function. We establish theoretical guarantees for the sample complexity of CAPI-style algorithms, which allow the policy evaluation step to be performed by a wide variety of algorithms (including temporal-difference-style methods), and can handle nonparametric representations of policies. Our bounds on the estimation error of the performance loss are tighter than existing results. We also illustrate this approach empirically on several problems, including a large HIV control task.

The learning with privileged information setting has recently attracted a lot of attention within the machine learning community, as it allows the integration of additional knowledge into the training process of a classifier, even when this comes in the form of a data modality that is not available at test time. Here, we show that privileged information can naturally be treated as noise in the latent function of a Gaussian Process classifier (GPC). That is, in contrast to the standard GPC setting, the latent function is not just a nuisance but a feature: it becomes a natural measure of confidence about the training data by modulating the slope of the GPC sigmoid likelihood function. Extensive experiments on public datasets show that the proposed GPC method using privileged noise, called GPC+, improves over a standard GPC without privileged knowledge, and also over the current state-of-the-art SVM-based method, SVM+. Moreover, we show that advanced neural networks and deep learning methods can be compressed as privileged information.

Nearest neighbor methods are a popular class of nonparametric estimators with several desirable properties, such as adaptivity to different distance scales in different regions of space. Prior work on convergence rates for nearest neighbor classification has not fully reflected these subtle properties. We analyze the behavior of these estimators in metric spaces and provide finite-sample, distribution-dependent rates of convergence under minimal assumptions. As a by-product, we are able to establish the universal consistency of nearest neighbor in a broader range of data spaces than was previously known. We illustrate our upper and lower bounds by introducing smoothness classes that are customized for nearest neighbor classification.

Golog and ConGolog are languages defined in the situation calculus for cognitive robotics. Given a Golog program \delta, its semantics is defined by a macro Do(\delta,s,s') that expands to a logical sentence that captures the conditions under which performing \delta in s can terminate in s'. A similarmacro is defined for ConGolog programs. In general, the logical sentences that these macros expand to are second-order, and in the case of ConGolog, may involve quantification over programs. In this paper, we show that by making use of the foundational axioms in the situation calculus, in particular, the second-order closure axiom about the space of situations, these macro expressions can actually be defined using first-order sentences.

Golog and ConGolog are languages defined in the situation calculus for cognitive robotics. Given a Golog program \delta, its semantics is defined by a macro Do(\delta,s,s') that expands to a logical sentence that captures the conditions under which performing \delta in s can terminate in s'. A similarmacro is defined for ConGolog programs. In general, the logical sentences that these macros expand to are second-order, and in the case of ConGolog, may involve quantification over programs. In this paper, we show that by making use of the foundational axioms in the situation calculus, in particular, the second-order closure axiom about the space of situations, these macro expressions can actually be defined using first-order sentences.

Golog and ConGolog are languages defined in the situation calculus for cognitive robotics. Given a Golog program \delta, its semantics is defined by a macro Do(\delta,s,s') that expands to a logical sentence that captures the conditions under which performing \delta in s can terminate in s'. A similarmacro is defined for ConGolog programs. In general, the logical sentences that these macros expand to are second-order, and in the case of ConGolog, may involve quantification over programs. In this paper, we show that by making use of the foundational axioms in the situation calculus, in particular, the second-order closure axiom about the space of situations, these macro expressions can actually be defined using first-order sentences.

Golog and ConGolog are languages defined in the situation calculus for cognitive robotics. Given a Golog program \delta, its semantics is defined by a macro Do(\delta,s,s') that expands to a logical sentence that captures the conditions under which performing \delta in s can terminate in s'. A similarmacro is defined for ConGolog programs. In general, the logical sentences that these macros expand to are second-order, and in the case of ConGolog, may involve quantification over programs. In this paper, we show that by making use of the foundational axioms in the situation calculus, in particular, the second-order closure axiom about the space of situations, these macro expressions can actually be defined using first-order sentences.