Based on a typology of five basic forms of abduction, I propose a new definition of abductive insight that empha sizes in particular the inferential structure of a belief system that is able to explain a phenomenon after a new, abductive ly created component has been added to this system or the entire system has been abductively restructured. My thesis is, first, that the argumentative structure of the pursued problem solution guides abductive creativity and, second, that diagrammatic reasoning—if conceptualized according to the requirements defined by Charles Peirce—can support this guidance. This support is mainly possible based on the normative power of the system of representation that has to be used to construct diagrams and to perform experiments with them.

The social and collaborative nature of dialogue challenges A spoken dialogue system (SDS) has a social role: it supposedly an SDS in many ways. The spontaneity of dialogue gives allows people to communicate with a computer in rise to disfluencies, where a person repeats or interrupts ordinary language. A robust SDS should support coherent herself, produces filled pauses or false starts and selfrepairs. Disfluencies play a fundamental role in dialogue, and habitable dialogue, even when it confronts situations as signals for turn-taking (Gravano, 2009; Sacks, Schegloff for which it has no explicit pre-specified behavior. To ensure robust task completion, however, SDS designers typically and Jefferson, 1974) and for grounding to establish shared produce systems that make a sequence of rigid demands beliefs about the current state of mutual understanding on the user, and thereby lose any semblance of natural (Clark and Schaefer, 1989). Most SDSs handle the content dialogue. The thesis of our work is that a dialogue of the user's utterances, but do not fully integrate the way they address utterance meaning, disfluencies, turn-taking should evolve as a set of agreements that arise from joint and the collaborative nature of grounding.

Early detection of cognitive impairment can prevent or delay the progress of cognitive dysfunction. In the field of neurology, the Clock Drawing Test (CDT) is one of the most popular instruments for detecting cognitive impairment. This paper presents the development of the ClockReader system, a computerized Clock Drawing Test. The main function of the system is to automate error handling in handwriting recognition. Since the ClockReader is a screening tool for dementia, it is not desirable to ask the users to fix their input errors in the drawing of either numbers or characters. Therefore, we propose a simple machine learning technique, context-bounded refinement filter algorithm. With trial experiments, we prove that this simple algorithm improves the recognizer accuracy of handwriting in clock drawings up to 88%.

We present a formal approach for combining programming by demonstration (PbD) with programming by instruction (PbI) — a largely unsolved problem. Our solution is based on the integration of two successful formalisms: version space algebras and the logic programming language Golog. Version space algebras have been successfully applied to programming by demonstration. Intuitively, a version space describes a set of candidate procedures and a learner filters this space as necessary to be consistent with all given demonstrations of the target procedure. Golog, on the other hand, is a logical programming language defined in the situation calculus that allows for the specification of non-deterministic programs. While Golog was originally proposed as a means for integrating programming and automated planning, we show that it serves equally well as a formal framework for integrating PbD and PbI. Our approach is the result of two key insights: (a) Golog programs can be used to define version spaces, and (b) with only a minor augmentation, the existing Golog semantics readily provides the update-function for such version spaces, given demonstrations. Moreover, as we will show, two or more programs can be symbolically synchronized, resulting in the intersection of two, possibly infinite, version spaces. The framework thus allows for a rather flexible integration of PbD and PbI, and in addition establishes a new connection between two active research areas, enabling cross-fertilization.

A new method is proposed for compiling causal independencies into Markov logic networks. A Markov logic network can be viewed as compactly representing a factorization of a joint probability into the multiplication of a set of factors guided by logical formulas. We present a notion of causal independence that enables one to further factorize the factors into a combination of even smaller factors and consequently obtain a finer-grain factorization of the joint probability. The causal independence lets us specify the factor in terms of weighted, directed clauses and an associative and commutative operator, such as "or", "sum" or "max", on the contribution of the variables involved in the factors, hence combining both undirected and directed knowledge.

In this paper we apply a Monte-Carlo Tree Search implementation that is boosted with domain knowledge to the game of poker. More specifically, we integrate an opponent model in the Monte-Carlo Tree Search algorithm to produce a strong poker playing program. Opponent models allow the search algorithm to focus on relevant parts of the game-tree. We use an opponent modelling approach that starts from a (learned) prior, i.e., general expectations about opponent behavior, and then learns a relational regression tree-function that adapts these priors to specific opponents. Our modelling approach can generate detailed game features or relations on-the-fly. Additionally, using a prior we can already make reasonable predictions even when limited experience is available for a particular player. We show that Monte-Carlo Tree Search with integrated opponent models performs well against state-of-the-art poker programs.

In this paper we study the sequential strategic interactive setting of two-person, two-stage, seller-offers bargaining under uncertainty. We model the epistemology of the problem in a finite interactive decision-theoretic framework and solve it for three types of agents of successively increasing (epistemological) sophistication (or, capacity to represent and reason with higher orders of beliefs). In particular, we remove common knowledge assumptions about the agents' epistemology which, if made, would be sufficient to imply the existence of a, possibly unique, game-theoretic equilibrium solution. In this context, we present a characterization of a monotonic relationship between an agent's optimal behavior and its beliefs under a particular moment-based ordering. Further, based on this characterization, we present the \emph{spread-accumulate} sampling technique -- a method of sampling an agent's higher order belief by generating ``evenly dispersed" beliefs for which we (pre)compute offline solutions. Then, we present a method for approximating higher order prior belief update to arbitrary precision by identifying a (previously solved) belief ``closest" to the true belief. In addition, these methods directly suggest a mechanism for achieving a balance between efficiency and the quality of the approximation -- either by generating a large number of offline solutions or by allowing the agent to search online for a ``closer" belief in the vicinity of best current solution.

The most common solution concept for a strategic interaction situation is the Nash equilibrium, in which no agent can do better by deviating unilaterally. However, the Nash equilibrium underlays on the assumption of common information that is hardly verified in many practical situations. When information is not common, rational agents are assumed to learn from their observations to derive beliefs over their opponents' play and payoffs. In these situations, there are steady states composed of beliefs and strategies in which the strategies do not constitute a Nash equilibrium. These stable states are called in the game theory literature self-confirming equilibria. They are such that every agent plays the best response to her beliefs and these are correct on the equilibrium path, while off the equilibrium path they may be incorrect. We present some mathematical programming formulations for computing self-confirming equilibria and its refinements in two-player extensive-form games and we study their properties.

One major challenge of implementing a metacognitive architecture lies in its scalability and flexibility. We postulate that the difference between a reasoner and a metareasoner need not extend beyond what inputs they take, and we envision a network made of many instances of a few types of simple but powerful reasoning units to serve both roles. In this paper, we present a vision and motivation for such a framework with reusable, robust, and scalable components. This framework, called Scruffy Metacognition , is built on a symbolic representation that lends itself to processing using dimensionality reduction and principal component analysis. We discuss the components of such as system and how they work together for metacognitive reasoning. Additionally, we discuss evaluative tasks for our system focusing on social agent role-playing and object classification.

Traditionally, in the fields of artificial intelligence and robotics, representations of the self have been conspicuously absent. Capabilities of systems are listed explicitly by developers during construction and choices between behavioral options are decided based on search, inference, and planning. In robotics, while knowledge of the external world has often been acquired through experience, knowledge about the robot itself has generally been built in by the designer. Built-in models of the robot's kinematics, physical and sensory capabilities, and other equipment have stood in the place of self-knowledge, but none of these representations offer the flexibility, robustness, and functionality that are present in people. In this work, we seek to emulate forms of self-awareness developed during human infancy in our humanoid robot, Nico. In particular, we are interested in the ability to reason about the robot's embodiment and physical capabilities, with the robot building a model of itself through its experiences.