This paper presents a methodology to acquire new knowledge in TutorJ using external information sources. TutorJ is an ITS whose architecture is inspired to the HIPM cognitive model, while meta-cognition principles have been used to design the knowledge acquisition process. The system behavior is intended to increase its own knowledge as a consequence of the interaction with users. The implemented methodology uses external links and services to capture new knowledge from contents related to discussion topics and transforms these contents into structured knowledge that is stored inside an ontology. The purpose of the proposed methodology is to lower the effort of system scaffolding creation and to increase the level of interaction with users. The focus is on self-regulated learners while meta-cognitive strategies have to bee defined to adapt and to increase the effectiveness of tutoring actions.

In this paper, we present a cognitive model of frequency-based decision-making applied to the task of landmine detection. The model is implemented in the ACT-R cognitive architecture and is strongly constrained by the cognitive primitives of the architecture. We then generalize the model to another task in the domain of macroeconomic decision-making using the same architecture, pursuing theoretical parsimony. We describe each model's representation requirements, assess their fits to the data, and analyze their performance scaling as a function of task and architectural parameters. Efforts to generalize the landmine detection model to macroeconomic decision making showed that reasonable fits to the macro-economic performance data could be achieved by models based either on procedural knowledge or declarative knowledge. This finding underscores the importance of distinguishing between processing strategies employed to execute tasks. Such detail appears needed to understand the neural foundations of frequency-based decision-making.

This paper argues that supervised cognitive growth in artifacts will be very difficult to achieve without detailed knowledge about systems’ internal states. Physical information is too low level to provide a useful understanding of a system’s behavior, and it is more pragmatically useful to take a mental stance towards an artificial system and interpret its actions in terms of mental states. This mental stance is similar to Dennett’s intentional stance, except the ascription of beliefs and rationality in the intentional stance is replaced by the attribution of low level mental states in the mental stance. In some cases it might also be useful to take a conscious stance towards an artificial system that interprets its behavior as the outcome of a conscious decision making process. Since most artifacts lack language, automatic analysis techniques have to be used to identify the contents of their minds, and the second half of this paper suggests how some of the earlier work of Aleksander and Atlas can be applied in this area.

In many spatial problems, it can be difficult to create a state representation that is abstract enough so that irrelevant details are ignored, but also accurate enough so that important states of the problem can be differentiated. This is especially difficult for agents that address a variety of problems. A potential way to resolve this difficulty is by using two representations of the spatial state of the problem: one abstract and one concrete, along with internal (imagery) operations that modify the concrete representation based on the contents of the abstract representation. In this paper, we argue that such a system can allow plans and policies to be expressed that can better solve a wider class of problems than would otherwise be possible. An example of such a plan is described. The theoretical aspects of what imagery is, how it differs from other techniques, and why it provides a benefit are explored.

Modern mobile robots navigate uncertain environments using complex compositions of camera, laser, and sonar sensor data. Manual calibration of these sensors is a tedious process that involves determining sensor behavior, geometry and location through model specification and system identification. Instead, we seek to automate the construction of sensor model geometry by mining uninterpreted sensor streams for regularities. Manifold learning methods are powerful techniques for deriving sensor structure from streams of sensor data. In recent years, the proliferation of manifold learning algorithms has led to a variety of choices for autonomously generating models of sensor geometry. We present a series of comparisons between different manifold learning methods for discovering sensor geometry for the specific case of a mobile robot with a variety of sensors. We also explore the effect of control laws and sensor boundary size on the efficacy of manifold learning approaches. We find that "motor babbling" control laws generate better geometric sensor maps than mid-line or wall following control laws and identify a novel method for distinguishing boundary sensor elements. We also present a new learning method, sensorimotor embedding, that takes advantage of the controllable nature of robots to build sensor maps.

The field of Artificial Intelligence has, for a long time, neglected the role of emotions in human cognition, with few but notable exceptions. This has been motivated in part by the assumption that the emulation of human rationality by a machine is sufficient for attaining general human-level intelligence. This paper reviews neuroscientific results showing empirical evidence, consistently for over a decade, sustaining that emotion mechanisms in the brain play a fundamental role in decision making processes, as well as in cognitive regulation. Moreover, this role takes place regardless of whether the subject is aware of any emotion. These mechanisms are particularly important in social contexts. Lesions in the pathways supporting these mechanisms provoke serious impairments on social behavior. For instance, subjects with lesions in the pathways between the orbitofrontal cortex and the amygdala are no longer able to sustain an healthy social live, despite their intact intellectual capabilities. Strikingly, these patients are even able to verbally describe what would be the proper social behavior, although are unable to follow it. One important mechanism in social contexts is empathy, fundamental for proper social relations. It has been proposed that empathy is founded on mechanisms analogous to the mirror neurons.

We study the dynamics and patterns of adoption of two competing technologies as well as the effectiveness and optimal- ity of viral pricing strategies by a technology seller. Our model considers two incompatible technologies of differing quality and a market in which user valuations are heterogeneous and subject to network effects. Taking the perspec- tive of a seller of the higher quality technology with imperfect information about user preferences, we investigate the problem of predicting market equilibrium outcomes. We provide partial characterization results about the structure and robustness of equilibria and give conditions under which the higher quality technology purveyor can make significant inroads into the competitor’s market share. We then show that myopic best-response dynamics in our setting are monotonic and convergent, and propose two pricing mechanisms that use this insight to help the entrant technology seller tip the market in its favor. Comparable implementations of both mechanisms reveals that the nondiscriminatory strategy, based on a calculated public price subsidy, is less costly and just as effective as a discriminatory policy. Additionally, we study discriminatory and nondiscriminatory price mechanisms in the context of profit maximization and show that problem is NP-Hard under uncertainty for both regimes. Finally, we use simulations to analyze a game in which the pricing decisions of both competing sellers are endogenous and now show, in contrast to our analytical results with exogenous prices, that a higher quality technology consistently holds a competitive advantage over the lower quality competitor, irrespective of its market share.

We have developed computer environments that support learning by teaching and the use of self regulated learning (SRL) skills through interactions with virtual agents. More specifically, students teach a computer agent, Betty, and can monitor her progress by asking her questions and getting her to take quizzes. The system provides SRL support via dialog-embedded prompts by Betty, the teachable agent, and Mr. Davis, the mentor agent. Our primary goals have been to support learning in complex science domains and facilitate development of metacognitive skills. More recently, we have also employed sequence analysis schemes and hidden Markov model (HMM) methods for assigning context to and deriving aggregated student behavior sequences from activity data. These techniques allow us to go beyond analyses of individual behaviors, instead examining how these behaviors cohere in larger patterns. We discuss the information derived from these models, and draw inferences on students’ use of self-regulated learning strategies.

Argumentation is now a very fertile area of research in Artificial Intelligence. Yet, most approaches to reasoning with arguments in AI are based on a normative perspective, relying on intuition as to what constitutes correct reasoning, sometimes aided by purpose-built hypothetical examples. For these models to be useful in agent-human argumentation, they can benefit from an alternative, positivist perspective that takes into account the empirical reality of human reasoning. To give a flavour of the kinds of lessons that this methodology can provide, we report on a psychological study exploring simple reinstatement in argumentation semantics. Empirical results show that while reinstatement is cognitively plausible in principle, it does not yield full recovery of the argument status, a notion not captured in Dung's classical model. This result suggests some possible avenues for research relevant to making formal models of argument more useful.

This paper advocates the use of a portfolio of representations for problem solving in complex domains. It describes an approach that decouples efficient storage mechanisms called descriptives from the decision-making procedures that employ them. An architecture that takes this approach can learn which representations are appropriate for a given problem class. Examples of search with a portfolio of representations are drawn from a broad set of domains.