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.

Many aspects can be taken into account in order to assess the power and potential of a cognitive architecture. In this paper we argue that ConsScale, a cognitive scale inspired on the development of consciousness, can be used to characterize and evaluate cognitive architectures from the point of view of the effective integration of their cognitive functionalities. Additionally, a graphical characterization of the cognitive power of artificial agents is proposed as a helpful tool for the analysis and comparison of Machine Consciousness implementations. This is illustrated with the application of the scale to a particular problem domain in the context of video game synthetic bots.

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.

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.

Verification that agent communication protocols have desirable properties or do not have undesirable properties is an important issue in agent systems where agents intend to communicate using such protocols. In this paper we explore the use of model checkers to verify properties of agent communication protocols, with these properties expressed as formulae in temporal logic.  We illustrate our approach using a recently-proposed protocol for agent dialogues over commands, a protocol that permits the agents to present questions, challenges and arguments for or against compliance with a command.

We propose a method for learning the intrinsic topology of a point set sampled from a curve embedded in a high-dimensional ambient space. Our approach does not rely on distances in the ambient space, and thus can recover the topology of sparsely sampled curves, a situation where extant manifold learning methods are expected to fail. We formulate a loss function based on the smoothness of a curve, and derive a greedy procedure for minimizing this loss function. We compare the efficacy of our approach with representative manifold learning and hierarchical clustering methods on both real and synthetic data.

Learning about complex and challenging science topics with advanced learning technologies requires students to regulate their learning. The deployment of key cognitive and metacognitive regulatory processes is key to enhancing learning in open-ended learning environments such as hypermedia. In this paper, we propose a metaphor—Computers as MetaCognitive tools—to characterize the complex nature of the learning context, self- regulatory processes, task conditions, and features of advanced learning technologies. We briefly outline the theoretical and conceptual assumptions of self-regulated learning (SRL) underlying MetaTutor, a hypermedia environment designed to train and foster students’ SRL processes in biology. Lastly, we provide preliminary learning outcome and SRL process data on the deployment of SRL processes during learning with MetaTutor.

Today an immense volume of electronic health records (EHRs) is being produced. These health records contain abundant information, in the form of both structured and unstructured data. It is estimated that EHRs contain on average around 60 percent structured information, and 40 percent unstructured information that is mostly free text (Dalianis et al., 2009). A modern health record is very complex and contains a large and diverse amount of data, such as the patient’s chief complaints, diagnoses and treatment, and very often an epicrisis, or discharge letter, together with ICD-10 codes, (ICD-10, 2009). Moreover, the health record also contains information about the patient’s gender, age, times of health care visits, medication, measure values, general condition as well as social situation, drinking and eating habits. Much of this information is written in natural language. All this information in a health record is currently almost never re-used, in particular the parts that are written in free text. We believe that the information contained in EHR data sets is an invaluable source for the development and evaluation of a number of applications, useful both for research purposes as well as health practitioners. For instance, text mining tools for finding new or hidden relations between diagnoses/treatments and social situation, age and gender could be very useful for epidemiological or medical researchers. Moreover, information concerning the health process over time, per patient, clinic or hospital, can be extracted and used for further research. Another application is the use of this data as input for simulation of the health process and for future health needs. Also, such huge health record databases can be used as corpora for the generation of generalized synonyms from specialized medical terminology constitutes another exciting application. We can also foresee a text summarization system applied to an individual patient’s health record, but using knowledge from all text records and conveying the information in the health record at the right level to the specific patient. The data can also be used for developing methods where clinicians in their daily work get automatic assistance and proposals of ICD-10 codes for assigning symptoms or diagnoses, or for validating the already manually assigned ICD-10 codes.

This extended abstract outlines my invited keynote presentation of the recent work on neuromorphic networks ("CrossNets") based on hybrid CMOS/nanoelectronic ("CMOL") circuits, in the space-saving Q/A format.