AAAI 2009 Fall Registration Symposium Descriptions
For registration information, please see the main 2009 Fall Symposium page.
Biologically Inspired Cognitive Architectures
The challenge of designing a human-level learner is central to creating a computational equivalent of the human mind in its higher cognitive abilities. It demands the level of robustness and flexibility of learning that today is available in biological systems only. Therefore, it is essential that we better understand at a computational level how biological systems naturally develop their cognitive and learning functions. In recent years, biologically inspired cognitive architectures (BICA) have emerged as a powerful new approach toward gaining this kind of understanding. The impressive success of BICA-2008 was clear evidence of this trend. As the second event in the series, BICA-2009 continues our attack on the challenge, with the overall atmosphere of excitement and potential, brainstorming and collaboration.
Topics
- Bridging the gap between natural and artificial intelligence: robustness, flexibility, integrity
- Models of natural cognitive growth: self-regulation, bootstrapping, metalearning
- Critical components of humanlike learning that enable transformative cognitive growth
- Vital biological constraints informed by neuroscience and their leverage in learning systems
- Cognitive versus subcognitive forms of learning: scalability laws and metrics for growing BICA
- Physical support of conscious experience: the emergent self and self-awareness in artifacts
- Formal theory of cognitive and metacognitive architectures and their natural development
- Language acquisition, symbol grounding, and the critical mass of a universal learner
- Reading and measuring minds of machines and humans: the second cognitive revolution
- The origin and the function of emotional feelings and values in humans and in artifacts
Speakers
Key speakers include Igor Aleksander (Imperial College), Ronald Arkin (Georgia Tech), Bernard Baars (NSI), Kenneth De Jong (GMU), Stan Franklin (University of Memphis), Stephen Grossberg (Boston University), Christof Koch (CalTech), Benjamin Kuipers (University of Michigan), Chris Lebiere (Carnegie Mellon University), Konstantin Likharev (Stony Brook University), Carol O'Donnell (DOE IES NCER), Jim Reggia (UMD), Frank Ritter (Penn State University), Stuart Shapiro (University of Buffalo), Hans-George Stork (European Commission).
Format
The symposium format is a one-track session including several discussion panels and a poster review session. A joint session with MCES-2009 on the Future Funding of Research in Learning Technologies will also include a joint discussion panel. Notification of the intent to participate with name, affiliation, address, phone and fax sent by e-mail to samsonovich@cox.net is strongly encouraged.
Organizing Committee
Alexei Samsonovich, chair (GMU), Igor Aleksander (Imperial College), Antonio Chella (University of Palermo), Stan Franklin (University of Memphis), Christian Lebiere (CMU), Shane Mueller (Klein/ARA), David Noelle (University of California Merced), Lokendra Shastri (Infosys).
Program Committee
Samuel Adams (IBM), James Albus (NIST), Jason Augustyn (CIV USA AMC), Wei Chen (CMU), Son Dao (HRL), John Gero (GMU), Eva Hudlicka (Psychometrix), Neil Jacobstein (Stanford University), Deepak Khosla (HRL), Murray Shanahan (Imperial College), Narayan Srinivasa (HRL), Brian Tsou (AFRL), Pei Wang (Temple University), John Weng (Michigan State University).
For more information about the symposium, see the supplementary symposium web site.
Cognitive and Metacognitive Educational Systems (MCES 2009)
Computer-based learning environments are designed to support learning processes to facilitate acquisition, development, use, and transfer of knowledge and strategies required to solve complex tasks. These systems have to interact with different users, and support them with decisional processes that are sensitive to individual differences. A primary concern is self-regulation, which is important for developing independent learners. Traditional intelligent (that is, rational) systems have limitations in achieving all these goals. Systems in support of education have to be cognitive. A (meta)cognitive system is self-aware — it can adapt to the user, and may propose self-regulation strategies to help the user learn and deploy self-regulatory processes and facilitate dynamic adaptivity during learning. This sort of cognitive push-pull can be enabled via multi-modal interaction, and through the possibility to define a system's "mental state." MCES 2009 is aimed to stimulate the creation of a dedicated research community about the definition of what is a (meta)cognitive educational system. What aspects of cognition, metacognition, affect, and motivation have to be explored and integrated to achieve the goal of a new generation of metacognitive tools for enhancing learning with understanding and transfer in metacognitive educational systems?
Topics
- Theoretical foundations of cognitive and metacognitive systems
- Psychological aspects of the learning process
- New educational paradigms to be addressed with a cognitive system
- Cognitive architectures for education
- Knowledge management and representation, skill acquisition
- Novel interaction modalities for educational purposes
- Linguistic interaction in MCESs
- Modelling metacognitive skills and pedagogical interactions
- Social and cultural aspects of learning
- Support for knowledge building communities, and for networked communication
- Student modelling and cognitive diagnosis
- New software architectures (agent based systems, distributed systems ...) for MCESs
- Virtual learning environments
- Web-based systems for education
Speakers
Key speakers and panelists include Michael Cox, Stephen Grossberg, Carol O'Donnell, Hans-George Stork, Elizabeth Albro.
Format
The symposium format is a one-track session including several discussion panels and a poster review session. A joint session with BICA-2009 on the Future Funding of Research in Learning Technologies will also include a joint discussion panel. Notification of the intent to participate with name, affiliation, address, phone and fax sent by email to mces2009-info@dinfo.unipa.it or via the symposium website is strongly encouraged.
Organizing Committee
Roberto Pirrone, Cochair (University of Palermo, Italy), Roger Azevedo, Cochair (University of Memphis), Gautam Biswas, Cochair (Vanderbilt University)
Program Committee
Philip Winne (Simon Fraser University), James Lester (North Carolina State University), Susanne Lajoie (McGill University), Valerie Shute (Florida State University), Amy Baylor (National Science Foundation)
For more information about the symposium see the supplementary symposium web site.
Complex Adaptive Systems and the Threshold Effect: Views from the Natural and Social Sciences
Most interesting phenomena in natural and social systems include transitions and oscillations among their various phases. Companies, societies, markets, and humans rarely stay in a stable, predictable state for long. Randomness, power laws, and human behavior ensure that the future is both unknown and challenging. How do events unfold? When do they take hold? Why do some initial events cause an avalanche while others do not? What are the characteristics of these threshold phenomena that differentiate a sea change from a nonevent?
Complex adaptive systems (CAS) and related technologies have proven to be powerful tools for exploring threshold phenomena. We characterize a general CAS model as having a significant number of self-similar agents that utilize one or more levels of feedback; exhibit emergent properties and self-organization; produce nonlinear dynamic behavior.
Advances in modeling and computing technology, including CAS, have led to a deeper understanding of complex systems in many fields in the natural, physical, and social sciences. These developments have raised the possibility that similar fundamental principles may be at work across these systems, even though the underlying principles may manifest themselves in different ways. We therefore invite participation from researchers across a wide range of disciplines, in the belief that a deep understanding in one domain may lead to greater insight into others.
Format
Our symposium will have invited talks from leaders in the field, as well as paper presentations on both completed and speculative work. Due to the nature and the novelty of the theme, it is essential to allow ample time for both open-ended and targeted discussions; as such, we will hold panel discussions and smaller break-out groups to allow for a spirited interaction among participants.
Organizing Committee
Mirsad Hadzikadic, Chair (University of North Carolina, Charlotte), Ted Carmichael, cochair (University of North Carolina Charlotte), Didier Dréau (University of North Carolina Charlotte), Jim Walsh (University of North Carolina Charlotte), Thom McLean (Georgia Tech), Cathy Zanbaka (BAE Systems), Marvin Croy (University of North Carolina Charlotte), Aaron Frank (BAE Systems), John Hummel (Argonne National Laboratory), Charles Macal (Argonne National Laboratory), John Stamper (University of North Carolina Charlotte), Alfred Hubler (University of Illinois, Urbana-Champagne), Russ Abbott (California State University), Patrick Grim (SUNY Stony Brook), Andrea Jones-Rooy (University of Michigan), Scott Demarchi (Duke University), Bill Rand (University of Maryland), Bob Reynolds (Wayne State University), Anne-Marie Grisogono (Defense Science and Technology Organisation, Australia), Tony Beavers (University of Evansville), Eunice Santos (Virginia Tech).
For more information about the symposium see the supplementary symposium web site.
Manifold Learning and Its Applications
In recent years, an impressive number of methods have been proposed for manifold learning and nonlinear dimensionality reduction. This fact illustrates both the growing interest in the area and the myriad of possible approaches to the problem. These methods vary, for example, in terms of the preservation of global or local properties of the data, regularization methods or the application of probabilistic or geometric constraints to the embedding.
The resulting theory and methods of manifold learning can be applied to many areas. For example, in computer vision, most data sets are comprised of sparse, high dimensional data (for example, hundreds of images where each image contains millions of pixels). Manifold learning has been used to facilitate common computer vision tasks such as video content analysis, pose estimation, image or video segmentation, and object tracking. Similarly, applications of manifold learning are abundant in bioinformatics, natural language processing, and robotics.
The goal of this symposium is to identify the overlap of theory and uses of manifold across the disciplines, which both produce and consume these methods in order to consolidate the knowledge on this topic, discuss the achievements in the area, and figure out the common open problems. Topics of the program include the following:
Theory of Manifold Learning
- Distance metrics
- Laplace operators, harmonic analysis
- Dimensionality estimation
- Regression and classification
- Sparsity and compressive sensing
- Approximation of manifolds
- Parameterizations and embeddings Manifold Learning and Graph-Based Methods
- Kernel, spectral, topological, and probabilistic methods
- Method taxonomies Applications of Manifold Learning
- AI, bioinformatics, computer vision, NLP, robotics, social networks
Format
The symposium format is a one-track session, which will be organized into the following topic clusters: foundations, algorithms, representations, applications, and future challenges. Each cluster will consist of an invited talk, presentation of submitted work as short talks or posters, and a panel discussion.
Organizing Committee
Mikhail Belkin (The Ohio State University), Mauro Maggioni (Duke University), Sridhar Mahadevan (University of Massachusetts), Richard Souvenir (University of North Carolina at Charlotte), Jerry Zhu (University of Wisconsin – Madison)
For more information about the symposium see the supplementary symposium web site.
Multi-Representational Architectures for Human-Level Intelligence
A multiplicity of representational frameworks has been proposed for explaining and creating human-level intelligence. Each has been proven useful or effective for some class of problems, but not across the board. This fact has led researchers to propose that perhaps the underlying design of cognition is multi-representational, or hybrid, and made up of subsystems with different representations and processes interacting to produce the complexity of cognition. Recent work in cognitive architectures has explored the design and use of such systems in high-level cognition. The main aim of this symposium is to bring together researchers who work on systems utilizing different types of representations to explore a range of questions about the theoretical framework and applications of such systems.
The symposium will be a mixture of invited talks, refereed full and position papers, expert panels and discussion sessions. The first session on each day will feature invited talks from experts in the field. The second and fourth sessions on Thursday and Friday (and the second session on Saturday) will be devoted to paper presentations. The exact length of time reserved for each presentation will be determined according to the number of number of papers accepted and will include time for answering questions. Time will also be reserved at the end of each paper session for an expert panel formed from the presenters of that session. More general questions that focus on areas common to the presentations or those that compare and contrast the various approaches discussed in that session will be the focus of these discussions. The third session on Thursday and Friday will be devoted to discussion groups. There will be between four and six groups devoted to various theoretical and application-oriented topics. Symposium participants will be able to select their group of choice. The end of these discussion sessions will include a 20-30 minute meeting where various groups will present their summary of the individual discussions.
Organizing Committee
Unmesh Kurup, Chair (Rensselaer Polytechnic Institute, USA), B. Chandrasekaran (The Ohio State University, USA), Bonny Banerjee (Securboration, USA), John Laird (University of Michigan, USA), Scott Lathrop (United States Military Academy, USA), Marvin Minsky (MIT Media Lab, USA), Luis Pineda (Universidad Nacional Autónoma de México, Mexico), Samuel Wintermute (University of Michigan, USA)
For more information about the symposium see the supplementary symposium web site.
The Uses of Computational Argumentation
Argumentation is a form of reasoning in which explicit attention is paid to the reasons for the conclusions that are drawn and how conflicts between reasons are resolved. Explicit consideration of the support for conclusions provides a mechanism, for example, to handle inconsistent and uncertain information. Argumentation has been studied both at the logical level, as a way of modelling defeasible inference, and at the dialogical level, as a form of agent interaction. Argumentation has long been studied in disciplines such as philosophy, and one can find approaches in computer science from the 1970s onwards that clearly owe something to the notion of an argument. Work on computational argumentation, where arguments are explicitly constructed and compared as a means of solving problems on a computer, first started appearing in the second half of the 1980s, and argumentation is now well established as an important sub-field within artificial intelligence.
There is now a good understanding of the basic requirements of argumentation systems, and there are several theoretical models that have been widely studied by researchers. There are one or two robust implementations, and the first software systems built around argumentation are beginning to appear. This, therefore, is an appropriate time to consider what these models and implementations might be used for. This symposium will provide a forum for wide-ranging discussion of the possible applications of techniques from computational argumentation. It will give special focus to strongly innovative ideas, ideas that can engage current researchers in the area and can inspire others to become researchers in the area.
Organizing Committee
Simon Parsons, Chair (Brooklyn College, City University of New York), Pietro Baroni (University of Brescia, Italy), Trevor Bench-Capon (University of Liverpool, UK), Nancy Green (University of North Carolina Greensboro, USA), Henry Prakken (Utrecht University, The Netherlands)
For more information about the symposium see the supplementary symposium web site.
Virtual Healthcare Interaction
Interaction between healthcare providers and consumers has a central role in consumer satisfaction and successful health outcomes. The healthcare consumer, facing increasing responsibility for healthcare decisions, may turn to electronic resources to supplement the information given by his healthcare provider. Here intelligent systems can assist in retrieval and summarization of relevant and trustworthy information, in tailoring the information so that it is comprehensible, and in making it accessible to computer users with disabilities. Furthermore, intelligent systems are beginning to appear that provide virtual healthcare services to the patient: for example, monitoring the patient’s health, reminding him to take his medicine, and encouraging him to exercise or eat a healthy diet. On the health care provider’s side, artificial intelligence can provide virtual patients for training providers to diagnose, care for, or communicate with clients.
Topics
This symposium will focus on virtual healthcare interaction (VHI): use of artificial intelligence in interaction traditionally occurring between healthcare providers and consumers. Topics of interest include the following:
- Virtual healthcare providers (such as medication advising, counseling)
- Games, conversational agents, and dialogue systems for healthy behavior promotion (such as STD prevention, personal exercise trainer)
- Virtual patients for training providers to diagnose, care for, or communicate with clients (such as virtual psychiatric patient)
- Decision support for healthcare clients (such as for cancer treatment)
- Explanation for informed consent
- Healthcare interventions (such as cognitive prostheses, speech therapy, virtual or robotic companions)
- Tailoring health information or risk communication to patients, including low-literacy, low-numeracy, or under-served audiences
- Intelligent retrieval and summarization of healthcare information tailored for patients
- Tailored access to medical record supporting both providers and consumers
- Intelligent interfaces supporting access to healthcare services for people with HCI limitations (such as motor, vision, hearing, cognitive).
In addition to AI researchers, the symposium invites participants from healthcare-related fields with an interest in these issues. The symposium format will consist of presentations on work in progress and mature work, demonstrations of implemented systems, invited expert presentations, and small group discussions.
Organizing Committee
Nancy Green, cochair (University of North Carolina Greensboro), Donia Scott, cochair (Open University), Tim Bickmore (Northeastern University), Giuseppe Carenini (University of British Columbia), Floriana Grasso (University of Liverpool), Curry Guinn (University of North Carolina Wilmington), Kathy McCoy (University of Delaware), Cecile Paris (CSIRO ICT Centre, Australia), Yan Qu, Ehud Reiter (University of Aberdeen)
For more information about the symposium see the supplementary symposium web site.