We present a new framework for semi-supervised learning with sparse eigenfunction bases of kernel matrices. It turns out that when the cluster assumption holds, that is, when the high density regions are sufficiently separated by low density valleys, each high density area corresponds to a unique representative eigenvector. Linear combination of such eigenvectors (or, more precisely, of their Nystrom extensions) provide good candidates for good classification functions. By first choosing an appropriate basis of these eigenvectors from unlabeled data and then using labeled data with Lasso to select a classifier in the span of these eigenvectors, we obtain a classifier, which has a very sparse representation in this basis. Importantly, the sparsity appears naturally from the cluster assumption. Experimental results on a number of real-world datasets show that our method is competitive with the state of the art semi-supervised learning algorithms and out-performs the natural base-line algorithm (Lasso in the Kernel PCA basis).

GLAIR (Grounded Layered Architecture with Integrated Reasoning) is a multi-layered cognitive architecture for embodied agents operating in real,virtual, or simulated environments containing other agents. The highest layer of the GLAIR Architecture, the Knowledge Layer (KL), contains the beliefs of the agent, and is the layer in which conscious reasoning, planning, and act selection is performed. The lowest layer of the GLAIR Architecture, the Sensori-Actuator Layer (SAL), contains the controllers of the sensors and effectors of the hardware or software robot. Between the KL and the SAL is the Perceptuo-Motor Layer (PML), which grounds the KL symbols in perceptual structures and subconscious actions, contains various registers for providing the agent's sense of situatedness in the environment, and handles translation and communication between the KL and the SAL. The motivation for the development of GLAIR has been "Computational Philosophy", the computational understanding and implementation of human-level intelligent behavior without necessarily being bound by the actual implementation of the human mind. Nevertheless, the approach has been inspired by human psychology and biology.

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.

The Laplacian Eigenmap is a popular method for non-linear dimension reduction and data representation. This graph based method uses a Graph Laplacian matrix that closely approximates the Laplace-Beltrami operator which has properties that help to learn the structure of data lying on Riemaniann manifolds. However, the Graph Laplacian used in this method is derived from an intermediate graph that is built using local neighborhood information. In this paper we show that it possible to encapsulate global information represented by a Minimum Spanning Tree on the data set and use it for effective dimension reduction when local information is limited. The ability of MSTs to capture intrinsic dimension and intrinsic entropy of manifolds has been shown in a recent study. Based on that result we show that the use of local neighborhood and global graph can preserve the locality of the manifold. The experimental results validate the simultaneous use of local and global information for non-linear dimension reduction.

Formal and computational models of argument are ideally suited for education in ill-defined domains such as law, public policy, and science.  Open-ended arguments play a central role in these areas but students of the domains may not have been taught an explicit model of argument.  Computational models of argument may be ideally suited to act as argument tutors guiding students in the formation of arguments and argument analysis according to an explicit model.  In order to achieve this it is important to establish that the models can be understood and evaluated reliably, an empirical question.  In this paper we report ongoing work on the diagnostic utility of argument diagrams produced in the LARGO tutoring system.

The propagation of blood flow along the fetoplacental arterial system has been hypothesized to have a compensatory response to placental anomalies that may result in fetal stress. When the placenta generates increased resistance, the umbilical artery blood flow would decrease and in the worst scenario become absent, which will lead to fetal asphyxia and hypoxia. To compensate for the decreased oxygen supply from maternal placenta, the fetal middle cerebral arteries would become dilated leading to an increased diastolic flow, hence more oxygen. This compensatory phase , however, only lasts for a certain period of time, after which the hypoxia may lead to fetal demise or long term irreversible organ damages. In high-risk pregnancies, Doppler ultrasound technology is commonly used to monitor the fetoplacental arterial blood flow to assess fetal well being. If the anomalies occur prior to the end of the 40-week of gestation, surgical or aggressive medical intervention might be necessary to save the fetal life. Timing this intervention, however, is complex due to the fine balancing act to minimize potential risks from prematurity and organ damage vs. rescuing a fetal life through cesarean section or aggressive medical treatment or natural delivery at the earliest possible gestational age. A reasonable goal is to allow the pregnancy to continue to the point just before fetal damage occurs. To achieve that goal, various testing criteria, e.g. venous Doppler and fetal heart rate, have been used to identify de-compensation. In this work, we conducted computer simulation of the fetoplacental arterial blood flow of a Systemic Lupus Erythematosus (SLE) pregnancy based on Doppler blood flow readings taken during the 10-day period prior to the delivery. The simulation suggests that timing the delivery based on either Doppler waveform readings or fetal heart rates give similar pregnancy outcome.

We are working on a temporal reasoning web tool for 7-11 olds. The acquisition of temporal relations and reasoning with them depends on age and experience, as well as linguistic factors. We conducted a preliminary evaluation with 6–8 olds in order to assess whether and how they would visually represent “while” temporal relations of a story. In this paper, we present and discuss our experimental evaluation, which paves the way for the visual representation of such relations in our e-tool.

The web forum is a key tool in the building of new knowledge among students in Learning Management Systems. Students’ posted messages, in fact, build up a relationship network which supports a collaborative reflection about the forum topic. In this network two interaction levels can be distinguished. The former is the interaction between peers (the students), the latter between students and instructors (teachers and tutors). The role of the second interaction is particularly important as a feedback mechanism in the discussion dynamic but it is subjected to two kinds of limitations. The first one is the huge number of messages that makes difficult, for tutors and teachers, to quickly evaluate the progress of their students and the second one is the subjective bias of the tutors that influence the evaluation. In order to limit these two inefficiencies a multiagent system can be used to monitor such evolution and recognize the state in which the forum is. Such system is based on metrics derived from the textual and social network analysis that, feeding a rule engine, gives the instructor a more objective view of the forum evolution.

Inconsistency management policies allow a relational database user to express customized ways for managing inconsistency according to his need. For each functional dependency, a user has a library of applicable policies, each of them with constraints, requirements, and preferences for their application, that can contradict each other. The problem that we address in this work is that of determining a subset of these policies that are suitable for application w.r.t. the set of constraints and user preferences. We propose a classical logic argumentation-based solution, which is a natural approach given that integrity constraints in databases and data instances are, in general, expressed in first order logic (FOL). An automatic argumentation-based selection process allows to retain some of the characteristics of the kind of reasoning that a human would perform in this situation.

A neural cognitive architecture would be an architecture based on simulated neurons, that provided a set of mechanisms for all cognitive behaviour. Moreover, this would be compatible with biological neural behaviour. As a result, such architectures can both form the basis of a fully-fledged AI and help to explain how cognition emerges from a collection of neurons in the human brain. The development of such a neural cognitive architecture is in its infancy, but a proto-architecture in the form of behaving agents entirely based on simulated neurons is described. These agents take natural language commands, view the environment, plan and act. The development of these agents has led to a series of questions that need to be addressed to advance the development of neural cognitive architectures. These questions include long posed ones where progress has been made, such as the binding and symbol grounding problems; issues about biological architectures including neural models and brain topology; issues of emergent behaviour such as short and long-term Cell Assembly dynamics; and issues of learning such as the stability-plasticity dilemma. These questions can act as a road map for the development of neural cognitive architectures and AIs based on them.