BibSonomy publications for /group/lkl_kss/AIFri Feb 04 12:44:32 CET 2011Menlo park, CaliforniaProceedings of the First International Conference on Multiagent Systems (ICMAS95)276-282Time and the Prisoner's Dilemma.1995AI agents dilemma gametheory haifa-edtech learning multiagent my myown polonsky prisoner's Fri Feb 04 12:44:20 CET 2011London, UKProceedings of the First International Conference on Practical Applications of Intelligent Agents and Multi-Agents Technology (PAAM96)837-842Courtz: An Agent that Pleases You (Extended Abstract)1996AI agents haifa-edtech my myown search usability Fri Feb 04 12:14:52 CET 2011Master's thesis, Hebrew University, Jerusalem, IsraelComputational approaches to rational choice1996AI agents complexity gametheory haifa-edtech multiagent my myown Fri Feb 04 12:13:37 CET 2011Proceedings of the Practical Application of Knowledge Discovery and Data Mining (PADD97)125--136Relevancy Ranking of Web Pages Using Shallow Parsing1997AI NLP agents haifa-edtech multiagent my myown parsing search web Fri Feb 04 12:13:28 CET 2011Lecture Notes in Artificial Intelligence164-176Learn Your Opponent's Strategy (in Polynomial Time)!10421996AI agents complexity computational gametheory haifa-edtech learning multiagent my myown Agents that interact in a distributed environment might increase their utility by behaving optimally given the strategies of the other agents. To do so, agents need to learn about those with whom they share the same world. This paper examines interactions among agents from a game theoretic perspective. In this context, learning has been assumed as a means to reach equilibrium. We analyze the complexity of this learning process. We start with a restricted two-agent model, in which agents are represented by finite automata, and one of the agents plays a fixed strategy. We show that even with this restrictions, the learning process may be exponential in time. We then suggest a criterion of simplicity, that induces a class of automata that are learnable in polynomial time.Mon Oct 26 20:38:13 CET 2009Proceedings of Tenth International Conference on AI in Education592--594{Building a bridge between intelligent tutoring and collaborative dialogue systems}2001AI AIED ITS analysis collaborative convsation cscl design discourse education language learning postviva social Our research objective is to develop computer tutors that collaborate with students on tasks in simulated environments. Towards this end, we seek to integrate two separate but related research threads: intelligent tutoring systems (ITS) and collaborative dialogue systems (CDS). Research on ITS [10] focuses on computer tutors that adapt to individual students based on the target knowledge the student is expected to learn and the presumed state of the student’s current knowledge. Research on CDS (e.g., [5]), with an equally long history, focuses on computational models of human dialogue for collaborative tasks. Unfortunately, there has been a surprising lack of cross-fertilization between these two research areas. Work on tutorial dialogue for ITS has not leveraged general models of collaborative dialogue. Similarly, research on collaborative dialogues has focused on modeling conversations between peers or between an expert and novice, but has rarely addressed tutorial issues.Mon Aug 10 01:48:32 CEST 2009Lecture Notes in Computer Science73--82{Belief revision process based on trust: Agents evaluating reputation of information sources}22462001AI agents belief multiagent reputation Wed Sep 24 18:34:17 CEST 2008Planning What To Say: Second Order Semantics for Fluid Construction Grammars2005AI agents autonomous fluid grammer language learning multiagent planning Research in the origins and evolution of language has now reached a level where languages with grammatical structures are emerging in computer simulations and robotic experiments based on situated embodied language games played by populations of agents. This paper focuses on some of the technical AI issues related to this research. Specifically, we report on a system for planning complex meanings (IRL) and on their grammatical expression in Fluid Construction GrammarWed Sep 24 18:32:05 CEST 2008Behavioral and Brain Sciences04469-489Coordinating perceptually grounded categories through language: A case study for colour282005AI agents autonomous categorisation colour connectionism cultural dynamics evolution genetic grounding language learning memes naming of origins self-organisation semiotic symbol This article proposes a number of models to examine through which mechanisms a population of autonomous agents could arrive at a repertoire of perceptually grounded categories that is sufficiently shared to allow successful communication. The models are inspired by the main approaches to human categorisation being discussed in the literature: nativism, empiricism, and culturalism. Colour is taken as a case study. Although we take no stance on which position is to be accepted as final truth with respect to human categorisation and naming, we do point to theoretical constraints that make each position more or less likely and we make clear suggestions on what the best engineering solution would be. Specifically, we argue that the collective choice of a shared repertoire must integrate multiple constraints, including constraints coming from communication.Wed Sep 24 18:25:04 CEST 2008Connection Science3213-230The emergence and evolution of linguistic structure: from lexical to grammatical communication systems172005AI communication connectionist grammer language learning lexicon linguistics networks neural review The paper discusses efforts to understand the self-organisation and evolution of language from a cognitive modeling point of view. It focuses in particular on efforts that use connectionist components to synthesise some of the major stages in the emergence of language and possible transitions between stages. The paper does not introduce new technical results but discusses a number of dimensions for mapping out the research landscape.Wed Sep 24 18:15:06 CEST 2008Symbols, embodiment and meaning. Academic Press, New HavenThe Symbol Grounding Problem has been solved. So what’s next?2008AI chineseroom embodied language learning meaning review semiotics symols In the nineteen eighties, a lot of ink was spent on the question of symbol grounding, largely triggered by Searle’s Chinese Room story (Searle,1980). Searle’s article had the advantage of stirring up discussion about when and how symbols could be about things in the world, whether intelligence involves representations or not, and what embodiment means and under what conditions cognition is embodied. But almost twenty five years of philosophical discussion have shed little light on the issue, partly because the discussion has been mixed up with emotional arguments whether artificial intelligence is possible or not. However today I believe that sufficient progress has been made in cognitive science and AI so that we can say that the symbol grounding problem has been solved. The paper briefly discusses the issues of symbols, meanings and embodiment, the main themes of the workshop, why I claim the symbol grounding problem has been solved, and what we should do next.Wed Sep 24 17:55:43 CEST 2008Evolution of Communication13-32AIBO’s first words: The social learning of language and meaning42000AI AIBO computaional imported language learning machine meaning social words This paper explores the hypothesis that language communication in its very first stage is bootstrapped in a social learning process under the strong influence of culture. A concrete framework for social learning has been developed based on the notion of a language game. Autonomous robots have been programmed to behave according to this framework. We show experiments that demonstrate why there has to be a causal role of language on category acquisition; partly by showing that it leads effectively to the bootstrapping of communication and partly by showing that other forms of learning do not generate categories usable in communication or make information assumptions which cannot be satisfied.Wed Sep 24 15:04:01 CEST 2008Cognitive Science3307-354Forward models: Supervised learning with a distal teacher161992AI computational learning machine networks neural neuralnetworks supervised teaching theory wleformativeeassessment Internal models of the environment have an important role to play in adaptive systems in general and are of particular importance for the supervised learning paradigm. In this paper we demonstrate that certain classical problems associated with the notion of the "teacher" in supervised learning can be solved by judicious use of learned internal models as components of the adaptive system. In particular, we show how supervised learning algorithms can be utilized in cases in which an unknown dynamical system intervenes between actions and desired outcomes. Our approach applies to any supervised learning algorithm that is capable of learning in multi-layer networks.Tue Sep 16 18:33:29 CEST 2008LECTURE NOTES IN COMPUTER SCIENCE689-698Alternative Views on Knowledge: Presentation of Open Learner Models2004AI AIED ITS artificial education intelligence learning modelling openlearnermodels wleformativeeassessment This paper describes a study in which individual learner models were built for students and presented to them with a choice of view. Students found it useful, and not confusing to be shown multiple representations of their knowledge, and individuals exhibited different preferences for which view they favoured. No link was established between these preferences and the students' learning styles. We describe the implications of these results for intelligent tutoring systems where interaction with the open learner model is individualised. Sat Sep 06 03:37:49 CEST 2008Journal of Computer Assisted Learning4305-315An enhanced Bayesian model to detect students' learning styles in Web-based courses242008AI artificial assesment bayesian eassessment elearning intelligence its learning modelling styles web wleformativeeassessment Abstract Students acquire and process information in different ways depending on their learning styles. To be effective, Web-based courses should guarantee that all the students learn despite their different learning styles. To achieve this goal, we have to detect how students learn: reflecting or acting; steadily or in fits and starts; intuitively or sensitively. In a previous work, we have presented an approach that uses Bayesian networks to detect a student's learning style in Web-based courses. In this work, we present an enhanced Bayesian model designed after the analysis of the results obtained when evaluating the approach in the context of an Artificial Intelligence course. We evaluated the precision of our Bayesian approach to infer students' learning styles from the observation of their actions with a Web-based education system during three semesters. We show how the results from one semester enabled us to adjust our initial model and helped teachers improve the content of the course for the following semester, enhancing in this way students' learning process. We obtained higher precision values when inferring the learning styles with the enhanced model.Fri May 30 05:57:10 CEST 2008Narrative Intelligence: Papers from the 1999 AAAI Fall Symposium, (5-7 November 1999 - North Falmouth, Massachusetts)101-104Narrative for Artifacts: Transcending Context and Self1999agents ai artificial design hci ijce ijceell06 intelligence interface mythesis narrative Fri May 30 05:27:16 CEST 2008Evanston, ILTell Me a Story: Narrative and Intelligence1995AI CiHB IJCEELL artificial cerme6 intelligence jime08 knowledge learning mythesis narrative How are our memories, our narratives, and our intelligence interrelated? What can artificial intelligence and narratology say to each other? In this pathbreaking study by an expert on learning and computers, Roger C. Schank argues that artificial intelligence must be based on real human intelligence, which consists largely of applying old situations, and our narratives of them, to new situations in less than obvious ways.Fri May 30 01:21:02 CEST 2008Dordrect, NLInternational Handbook of Mathematics Education469-504Computer-Based Learning Environments in Mathematics1996CnE07 ILE ai algebra arithmetic artificial calculus collaborative computation computers curriculum distance education geometrystatistics gmx intelligencemodeling learning mathematics mathgamespatterns microworlds mythesis proof review tel transposition Computer-Based Learning Environments in Mathematics Nicolas Balacheff \& James J. Kaput This chapter attempts to set a perspective on where interactive technologies have taken us and where they seem to be headed. After briefly reviewing their impact in different mathematical domains, including arithmetic, algebra, geometry, statistics, and calculus, we examine what we believe to be the sources of technology's power, which we feel is primarily epistemological. While technology's impact on daily practice has yet to match expectations from two or three decades ago, it's epistemological impact is deeper than expected. This impact is based in a reification of mathematical objects and relations that students can use to act more directly on these objects and relations than ever before. This new mathematical realism, when coupled with the fact that the computer becomes a new partner in the didactical contract, forces us to extend the didactical transposition of mathematics to a computational transposition. This new realism also drives ever deeper changes in the curriculum, and it challenges widely held assumptions about what mathematics is learnable by which students, and when they may learn it. We also examine the limits of Artificial Intelligence and microworlds and how these may be changing. We close by considering the newer possibilities offered by the internet and its dramatic impact on connections among learners, teachers, and the immense resources that are becoming available to both. Our conclusion is that we are very early in the technological transformation and that we desperately need research in all aspects of teaching and learning with technology.Tue May 27 23:37:06 CEST 2008Social Ontology: Some Basic Principles2004AI artificial intelligence ontology social Tue May 27 23:36:06 CEST 2008New YorkSpeech Acts: Syntax and Semantics Volume 359--82Indirect Speech Acts1975AI acts artificial intelligence language learning natural processing semantics speech syntax