Форум: Проблемы искусственного интеллекта

Регистрация | Вход

Все темы | Новая тема  Стр.3 (39) << < Пред. | След. > >>    Поиск:
Автор	Тема: На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 20 авг 09 5:12 ========================= PART 0: I N V I T E D - T A L K S: =012=> 0002p Intelligent Tutoring Systems ( I T S ): New Challenges and Directions, http://ijcai.org/papers09/Abstracts/012.html Cristina Conati ==> Can we devise educational systems that provide individualized instruction tailored to the needs of the individual learners, as many good teachers do? Intelligent Tutoring Systems is the interdisciplinary field that investigates this question by integrating research in Artificial Intelligence, Cognitive Science and Education. Research in this field has successfully delivered techniques and systems that provide adaptive support for student problem solving in variety of domains. There are, however, other educational activities that can benefit from individualized computer-based support, such as studying examples, exploring interactive simulations and playing educational games. Providing individualized support for these activities rises unique challenges, because it requires that an ITS can model and adapt to student behaviors, skills and mental states often not as structured and well-defined as those involved in traditional problem solving. I will present a variety of projects that illustrate some of these challenges, our proposed solutions, and future opportunities. text: http://ijcai.org/papers09/Papers/IJCAI09-012.pdf from Drew (вольно-переведенный абстрактa & some comments): Индивиндуальный подход к каждому студенту - потребность любого продвинутого общества.. но хороших педагогов приемлимой стимости - на всех не напaсешься! Адаптивные Интеллектуальные Обучающие Системы - (Intelligent Tutoring System ==> ITS) - щадящий выход бюджетного образования.. на стыке Ии, Когнитивных и Педогогических наук. Искомая адаптивность к обучаемoму уже продемонстрирована для многих областей знаний.. и сейчас уже имеются результаты и намётки для менее традицинных путей - обучение на примерах, интерактивные иммитаторы и обучающие игры.. Докладчица рассматривает примеры всех имеющихся типов.. PS: саму статью пока не читал - не уверен во-взрослости наличиствующего контенгента или о присутствии в Харьковах-Свердловсках - чего-либо сложнее Доски с мелом.. В Штатах это весьма широкое и прибыльное направление - ибо очное обучение многим не по карману.. А уровень обучающих/ся - различается в-разы! - за счет частных школ, к-е дают фору на всю оставшуюся жизнь.. Конечно вокруг этого дела чудовищно много выбегал.. И ии там часто и не пахнет.. Но допусти меня до этой кормушки - и Экспертые Системы и Распозновани речи - пропесал бы как доктор.. А допустили бы к телу Обамы - предложил бы вместо Тысяч !!! Обучалок - РЯД из 10-12 Шелл-систем - покрывающих 75-95% обучальства.. Типа настраеваемая по результатам ОНТОЛОГИЧЕСКАЯ Модель Студента и Сменная Онтология чему учиться.. География.. или История.. PPS: инвайтед-доклад - обзор! проблемы интеллектуального обучанса - с примерами от прикормленных профессоров.. этот Ии-обучанс прет как на дрожжах.. и поскольку стандартов нет - выбегаллы резвятся вовсю. Самый крутой проэкт ==> у Локхида - тренажер-иммитатор Группового боя с дюжинкой Мигов.. с пониманием Оея-речи и не-менее Шахматного - стратег-такт интеллекта - B Южном НьюДжерси - и - полигон в Аризоне PPS: Собственно 5 стр текста с литературой и заключением - Учиться, учиться ии-Учиться.. оказались недостаточными для сильного углубления Моей и Авторской аннотаций.. Отделяются низменные CAI/CAE от ITS, к-я трактуется как полноценный ИИ, снабженный Базой Знаний о Предмете изучаемого, и База Знаний о ученике и его успехах в познании предмета.. Автор не чурается мета-когнитивной терминологии (thinking about thinking), но и весьма шустер в ии-словечках.. (Artificial Agents, Reasoning..). Видимо имеется и 20 страничная версия доклада, или форумец - автор неосторожно дает мыло.. [Ответ][Цитата]
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 21 авг 09 5:48 ***************************************************************** [Ответ][Цитата]
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 21 авг 09 5:51 ======================== PART 0: I N V I T E D - T A L K S: =013=> 0008p Machine Learning in Ecosystem Informatics and Sustainability, http://ijcai.org/papers09/Abstracts/013.html Thomas G. Dietterich: Ecosystem Informatics brings together mathematical and computational tools to address scientific and policy challenges in the ecosystem sciences. These challenges include novel sensors for collecting data, algorithms for automated data cleaning, learning methods for building statistical models from data and for fitting mechanistic models to data, and algorithms for designing optimal policies for biosphere management. This presentation discusses these challenges and then describes recent work on the first two of these--new methods for automated arthropod population counting and linear Gaussian DBNs for automated cleaning of sensor network data. text: http://ijcai.org/papers09/Papers/IJCAI09-013.pdf from Drew: .. ... ... [Ответ][Цитата]
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 21 авг 09 5:51 ***************************************************************** [Ответ][Цитата]
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 21 авг 09 5:51 ======================== PART 0: I N V I T E D - T A L K S: =014=> 0014p How Experience of the Body Shapes Language about Space, http://ijcai.org/papers09/Abstracts/014.html Luc Steels, Michael Spranger: Open-ended language communication remains an enormous challenge for autonomous robots. This paper argues that the notion of a language strategy is the appropriate vehicle for addressing this challenge. A language strategy packages all the procedures that are necessary for playing a language game. We present a specific example of a language strategy for playing an Action Game in which one robot asks another robot to take on a body posture (such as stand or sit), and show how it effectively allows a population of agents to self-organise a perceptually grounded ontology and a lexicon from scratch, without any human intervention. Next, we show how a new language strategy can arise by exaptation from an existing one, concretely, how the body posture strategy can be exapted to a strategy for playing language games about the spatial position of objects (as in "the bottle stands on the table"). text: http://ijcai.org/papers09/Papers/IJCAI09-014.pdf from Drew: .. ... ... [Ответ][Цитата]
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 21 авг 09 5:52 ***************************************************************** [Ответ][Цитата]
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 21 авг 09 5:52 ======================== PART 0: I N V I T E D - T A L K S: =015=> 0020p Activity Recognition: Linking Low-level Sensors to High-level Intelligence, http://ijcai.org/papers09/Abstracts/015.html Qiang Yang: Sensors provide computer systems with a window to the outside world. Activity recognition "sees" what is in the window to predict the locations, trajectories, actions, goals and plans of humans and objects. Building an activity recognition system requires a full range of interaction from statistical inference on lower level sensor data to symbolic AI at higher levels, where prediction results and acquired knowledge are passed up each level to form a knowledge food chain. In this article, I will give an overview of some of the current activity recognition research works and explore a life-cycle of learning and inference that allows the lowest-level radio-frequency signals to be transformed into symbolic logical representations for AI planning, which in turn controls the robots or guides human users through a sensor network, thus completing a full life-cycle of knowledge. text: http://ijcai.org/papers09/Papers/IJCAI09-015.pdf from Drew: .. ... ... [Ответ][Цитата]
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 21 авг 09 5:52 ***************************************************************** [Ответ][Цитата]
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 21 авг 09 6:27 =========== PART-1: AGENT-BASED and MULTI-AGENT SYSTEMS =========== ===> 0027 - 0379 pp [Ответ][Цитата]
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 21 авг 09 6:27 PART-1: AGENT-BASED and MULTI-AGENT SYSTEMS: =016=> 0027p Nonmanipulable Selections from a Tournament, Alon Altman, Ariel D. Procaccia, Moshe Tennenholtz, http://ijcai.org/papers09/Abstracts/016.html abstract: A tournament is a binary dominance relation on a set of alternatives. Tournaments arise in many contexts that are relevant to AI, most notably in voting (as a method to aggregate the preferences of agents). There are many works that deal with choice rules that select a desirable alternative from a tournament, but very few of them deal directly with incentive issues, despite the fact that game-theoretic considerations are crucial with respect to systems populated by selfish agents.We deal with the problem of the manipulation of choice rules by considering two types of manipulation. We say that a choice rule is monotonic if an alternative cannot get itself selected by losing on purpose, and pairwise nonmanipulable if a pair of alternatives cannot make one of them the winner by reversing the outcome of the match between them. Our main result is a combinatorial construction of a choice rule that is monotonic, pairwise nonmanipulable, and onto the set of alternatives, for any number of alternatives besides three. text: http://ijcai.org/papers09/Abstracts/016.html [Ответ][Цитата]
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 21 авг 09 6:37 PART-1: AGENT-BASED and MULTI-AGENT SYSTEMS: =017=> 0033p Using Reasoning Patterns to Helps Humans Solve Complex Games, Dimitrios Antos, Avi Pfeffer http://ijcai.org/papers09/Abstracts/017.html We propose a novel method for helping humans make good decisions in complex games, for which common equilibrium solutions may be too difficult to compute or not relevant. Our method leverages and augments humans' natural use of arguments in the decision making process. We believe that, if computers were capable of generating similar arguments from the mathematical description of a game, and presented those to a human decision maker, the synergies would result in better performance overall. The theory of reasoning patterns naturally lends itself to such a use. We use reasoning patterns to derive localized evaluation functions for each decision in a game, then present their output to humans. We have implemented this approach in a repeated principal-agent game, and used it to generate advice given to subjects. Experimental results show that humans who received advice performed better than those who did not. text: http://ijcai.org/papers09/Papers/IJCAI09-017.pdf [Ответ][Цитата]
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 21 авг 09 6:37 PART-1: AGENT-BASED and MULTI-AGENT SYSTEMS: =018=> 0040p UCT for Tactical Assault Planning in Real-Time Strategy Games, Radha-Krishna Balla, Alan Fern, http://ijcai.org/papers09/Abstracts/018.html We consider the problem of tactical assault planning in real-time strategy games where a team of friendly agents must launch an assault on an enemy. This problem offers many challenges including a highly dynamic and uncertain environment, multiple agents, durative actions, numeric attributes, and different optimization objectives. While the dynamics of this problem are quite complex, it is often possible to provide or learn a coarse simulation-based model of a tactical domain, which makes Monte-Carlo planning an attractive approach. In this paper, we investigate the use of UCT, a recent Monte-Carlo planning algorithm for this problem. UCT has recently shown impressive successes in the area of games, particularly Go, but has not yet been considered in the context of multi-agent tactical planning. We discuss the challenges of adapting UCT to our domain and an implementation which allows for the optimization of user specified objective functions. We present an evaluation of our approach on a range of tactical assault problems with different objectives in the RTS game Wargus. The results indicate that our planner is able to generate superior plans compared to several baselines and a human player. text: http://ijcai.org/papers09/Papers/IJCAI09-018.pdf [Ответ][Цитата]
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 21 авг 09 6:38 PART-1: AGENT-BASED and MULTI-AGENT SYSTEMS: =019=> 0046p Methodology for Designing Reasonably Expressive Mechanisms with Application to Ad Auctions, Michael Benisch, Norman Sadeh, Tuomas Sandholm, http://ijcai.org/papers09/Abstracts/019.html Mechanisms (especially on the Internet) have begun allowing people or organizations to express richer preferences in order to provide for greater levels of overall satisfaction. In this paper, we develop an operational methodology for quantifying the expected gains in economic efficiency associated with different forms of expressiveness. We begin by proving that the sponsored search mechanism (GSP) used by Google, Yahoo!, MSN, etc. can be arbitrarily inefficient. We then experimentally compare its efficiency to a slightly more expressive variant (PGSP), which solicits an extra bid for a premium class of positions. We generate random preference distributions based on published industry knowledge. We determine ideal strategies for the agents using a custom tree search technique, and we also benchmark using straightforward heuristic bidding strategies. The GSP's efficiency loss is greatest in the practical case where some advertisers ("brand advertisers") prefer top positions while others ("value advertisers") prefer middle positions, and that loss can be dramatic. It is also worst when agents have small profit margins. While the PGSP is only slightly more expressive (and thus not much more cumbersome), it removes almost all of the efficiency loss in all of the settings we study. text: http://ijcai.org/papers09/Abstracts/019.html [Ответ][Цитата]
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 21 авг 09 6:38 PART-1: AGENT-BASED and MULTI-AGENT SYSTEMS: =020=> 0053p A Multivariate Complexity Analysis of Determining Possible Winners Given Incomplete Votes, Nadja Betzler, S.Hemmann, R.Niedermeier, http://ijcai.org/papers09/Abstracts/020.html The Possible Winner problem asks whether some distinguished candidate may become the winner of an election when the given incomplete votes are extended into complete ones in a favorable way. Possible Winner is NP-complete for common voting rules such as Borda, many other positional scoring rules, Bucklin, Copeland etc. We investigate how three different parameterizations influence the computational complexity of Possible Winner for a number of voting rules. We show fixed-parameter tractability results with respect to the parameter "number of candidates" but intractability results with respect to the parameter "number of votes". Finally, we derive fixed-parameter tractability results with respect to the parameter "total number of undetermined candidate pairs" and identify an interesting polynomial-time solvable special case for Borda. text: http://ijcai.org/papers09/Papers/IJCAI09-020.pdf [Ответ][Цитата]
Capt.Drew Сообщений: 4179	На: Ai Drew :: IJCAI 09 :: Междунар. ии конфа: Позднее лето-2009 - Коротко о Главном Добавлено: 21 авг 09 6:38 PART-1: AGENT-BASED and MULTI-AGENT SYSTEMS: =021=> 0059p Algorithms and Complexity Results for Pursuit-Evasion Problems, Richard Borie, Craig Tovey, Sven Koenig, http://ijcai.org/papers09/Abstracts/021.html We study pursuit-evasion problems where a number of pursuers have to clear a given graph. We study when polynomial-time algorithms exist to determine how many pursuers are needed to clear a given graph and how a given number of pursuers should move on the graph to clear it with either a minimum sum of their travel distances or minimum task-completion time. We generalize prior work to both unit-width arbitrary-length and unit-length arbitrary-width graphs and derive both algorithms and complexity results for a variety of graph topologies. In this context, we describe a polynomial-time algorithm, called CLEARTHETREE, that is much shorter and algorithmically simpler than the state-of-the-art algorithm for the minimum pursuer problem on trees. Our theoretical research lays a firm theoretical foundation for pursuit evasion on graphs and informs practitioners about which problems are easy and which ones are hard. text: http://ijcai.org/papers09/Papers/IJCAI09-021.pdf [Ответ][Цитата]
Стр.3 (39): 1  2  [3]  4  5  6  7  ...  39 << < Пред. | След. > >>