eLearning

Engineering Heterogeneous Distributed Learning Environments Using Tuple Spaces as an Architectural Platform

Stefan Weinbrenner; Adam Giemza; H. Ulrich Hoppe Seventh IEEE International Conference on Advanced Learning Technologies (ICALT 2007), 2007

To support the development of distributed learning environments with components programmed in different languages a blackboard architecture based on tuple spaces is proposed. The specific implementation in terms of the "Colmid" middleware supports inter-language communication by adding a Prolog interface to the Java based TSpaces platform. This approach is exemplified by a collaborative discussion environment coupled with an action analyzer ...

Prolog to, "Neuromorphic Electronic Circuits for Building Autonomous Cognitive Systems."

Jim Esch Proceedings of the IEEE, 2014

In the last decade, progress has been made in the construction of simple neuromorphic cognitive systems. These types of circuits are described in the paper, and they are compared to existing solutions. The limitations of such circuits are described, as well as design techniques for constructing larger brain-like systems. The technological building blocks are based on dynamic synapse circuits, hardware ...

A new approach to Kanerva's sparse distributed memory

T. A. Hely; D. J. Willshaw; G. M. Hayes IEEE Transactions on Neural Networks, 1997

The sparse distributed memory (SDM) was originally developed to tackle the problem of storing large binary data patterns. The model succeeded well in storing random input data. However, its efficiency, particularly in handling nonrandom data, was poor. In its original form it is a static and inflexible system. Most of the recent work on the SDM has concentrated on improving ...

Statistical context priming for object detection

A. Torralba; P. Sinha Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, 2001

There is general consensus that context can be a rich source of information about an object's identity, location and scale. However the issue of how to formalize centextual influences is still largely open. Here we introduce a simple probabilistic framework for modeling the relationship between context and object properties. We represent global context information in terms of the spatial layout ...

Towards formal measures of usability for visual interactive systems

P. Bottoni; M. F. Costabile; S. Levialdi; A. Piccinno Proceedings IEEE 2002 Symposia on Human Centric Computing Languages and Environments, 2002

Usability is the most important feature of a computer program from the users point of view. Even if various techniques for evaluating usability have been proposed, formal methods are still lacking. A good indication of program usability is given by the agreement between the mental model of the system, as conceived by the user, and the model of the user, ...

IEEE-USA E-Books

• First Challenge: Large Domains

  In this book we have often presented domain knowledge in a table, neatly arranged to highlight the commonalities and differences between the entities in the domain. But real life is seldom so accommodating: in large domains we often have to work hard to find out how the facts line up.

• Definitions of Rationality in Philosophy, Cognitive Science, and Lay Discourse

  "Rationality" is a torturous and tortured term in intellectual discourse. It is contentious and has a multitude of definitions. The term is claimed by many disciplines and parsed slightly differently by each discipline. Philosophy, economics, decision theory, psychology--all claim the term and have their own definitions.

• Second Challenge: Breakdown of Common Knowledge

  The previous chapter discussed situations in which the hearer is unable to identify the target until he has discovered some new facts about the domain. A different challenge to established accounts of reference and Information Sharing comes from situations in which the speaker is uncertain about the hearer's knowledge.

• Building “Fungus Eaters”: Design Principles of Autonomods Agents

  We describe a set of design principles for building "Fungus Eaters" "Fungus Eaters" are complete autonomous systems. The goal is to extract and describe in a compact way a large part of the insights which have been acquired in the animats field. The principles have been developed from a cognitive science perspective. Although they represent only a very modest beginning, they make immediately clear what sort of ideas about intelligence and cognition they endorse. They all contrast sharply with classical thinking. Moreover, they provide powerful heuristics for design.

• Index

  To communicate, speakers need to make it clear what they are talking about. The act of referring, which anchors words to things, is a fundamental aspect of language. In this book, Kees van Deemter shows that computational models of reference offer attractive tools for capturing the complexity of referring. Indeed, the models van Deemter presents cover many issues beyond the basic idea of referring to an object, including reference to sets, approximate descriptions, descriptions produced under uncertainty concerning the hearer's knowledge, and descriptions that aim to inform or influence the hearer. The book, which can be read as a case study in cognitive science, draws on perspectives from across the cognitive sciences, including philosophy, experimental psychology, formal logic, and computer science. Van Deemter advocates a combination of computational modeling and careful experimentation as the preferred method for expanding these insights. He then shows this method in ac ion, covering a range of algorithms and a variety of methods for testing them. He shows that the method allows us to model logically complicated referring expressions, and demonstrates how we can gain an understanding of reference in situations where the speaker's knowledge is difficult to assess or where the referent resists exact definition. Finally, he proposes a program of research that addresses the open questions that remain in this area, arguing that this program can significantly enhance our understanding of human communication.

• Third Challenge: Approximate Reference

  Most REG algorithms assume that identification of the referent is a requirement. Moreover, they operate on the basis that all distractors should be removed from the hearer's attention, and that one distractor cannot be more important than another. In many situations, however, these assumptions are not justified. Once again, let us reflect on some scenarios.

• References

  In The Geometry of Meaning, Peter G¿¿rdenfors proposes a theory of semantics that bridges cognitive science and linguistics and shows how theories of cognitive processes, in particular concept formation, can be exploited in a general semantic model. He argues that our minds organize the information involved in communicative acts in a format that can be modeled in geometric or topological terms -- in what he terms conceptual spaces, extending the theory he presented in an earlier book by that name. Many semantic theories consider the meanings of words as relatively stable and independent of the communicative context. G¿¿rdenfors focuses instead on how various forms of communication establish a system of meanings that becomes shared between interlocutors. He argues that these "meetings of mind" depend on the underlying geometric structures, and that these structures facilitate language learning. Turning to lexical semantics, G¿¿rdenfors argues that a unified theory of word meaning can be developed by using conceptual spaces. He shows that the meaning of different word classes can be given a cognitive grounding, and offers semantic analyses of nouns, adjectives, verbs, and prepositions. He also presents models of how the meanings of words are composed to form new meanings and of the basic semantic role of sentences. Finally, he considers the future implications of his theory for robot semantics and the Semantic Web.

• Association Lecture

  Attention and Performance XIV, the silver jubilee volume in a renowned series of international symposia on human mental and physical performance, provides a broad, historic, and timely synthesis of the empirical and theoretical ideas on which performance theory now rests.Extending trends set by earlier symposia volumes, the thirty-five contributions treat topics that are central to a scientific understanding of human performance including visual information processing, selective attention, mental chronometry, learning, memory, and motor control - from the interdisciplinary perspectives of experimental psychology, cognitive science, artificial intelligence, and neurophysiology. The assembled tutorials, reviews and previews, new research reports, and critical commentaries ranging from retrospective assessments to forecasts of likely future advances make this major undertaking at once an encyclopedic handbook, memoir, monograph, and text that will serve a multiplicity of needs for workers in a variety of allied disciplines.David E. Meyer and Sylvan Kornblum are Professors of Psychology at the University of Michigan.

• Foundations of Classical Artificial Intelligence and Cognitive Science

  This chapter contains sections titled: Cognitive Science: Preliminaries, The Cognitivistic Paradigm, An Architecture for an Intelligent Agent

• Theories of Reference

  Reference has featured in debates about language at least since Plato's examination of the concept of knowledge and became an area of lively debate around 1900, when Gottlob Frege and Bertrand Russell started to use Formal Logic to shed light on the meaning of natural language.