AAAI 2015 Spring Symposia
March 23–25, 2015
Sponsored by the Association for the Advancement of Artificial Intelligence
In cooperation with the Stanford University Computer Science Department
- Ambient Intelligence for Health and Cognitive Enhancement
- Applied Computational Game Theory
- Foundations of Autonomy and Its (Cyber) Threats: From Individuals to Interdependence
- Knowledge Representation and Reasoning: Integrating Symbolic and Neural Approaches
- Logical Formalizations of Commonsense Reasoning
- Socio-Technical Behavior Mining: From Data to Decisions
- Structured Data for Humanitarian Technologies: Perfect Fit or Overkill?
- Turn-Taking and Coordination in Human-Machine Interaction
Aims and New Challenges Ambient intelligence (that is, intelligence embedded in environment) is a system and an information technology that can adapt to human activities in living environment. As the characteristics of ambient intelligence, its system or information technology (1) is embedded into the environment; (2) can recognize the situational context of subject; (3) can be personalized to subject; (4) can change in response to subject; and (5) can anticipate desires of subject.
One of potential applications in ambient intelligence is healthcare. For example, the health monitoring system embedded in the environment is useful for aged persons to check their health without entering a hospital, which contributes to health enhancement by controlling their health conditions. Another important potential of ambient intelligence from the viewpoint of healthcare enhances our cognitive capability by using many sensors. For example, many vital data from many sensors recognize health conditions more accurately than a single vital data, which contributes to cognitive enhancement. These aspects suggest that ambient intelligence contributes to our health and cognitive enhancement.
This symposium is aimed at sharing latest progress, current challenges and potential applications for our health and cognitive enhancement in the context of ambient intelligence. The improvement of human health and understanding of human cognition from the viewpoint of ambient intelligence is also welcome.
The following outstanding challenges should be tackled: (1) how to quantify our health and cognitive performance; (2) how to analyze the health and cognitive data for discovering the new meanings; and (3) how to design our health and cognitive enhancement space. This symposium seeks to explore the methods and/or methodologies for above three questions. This symposium will bring together an interdisciplinary group of researchers to discuss possible solutions for our health and cognitive enhancement by focusing on AI techniques.
Background and Previous Symposium We organized the 2014 AAAI Spring symposium Big Data Becomes Personal: Knowledge into Meaning. The symposium was successful in inspiring new ideas from diverse fields of participants (about 50 participants), and the participants expressed the desire to continue this initiative in further events. We extend our scope by incorporating the new ideas of ambient intelligence for health and cognitive enhancement. Our new challenge includes how we can create ambient intelligence and enhance our health and cognitive performance by integrating and mining our personal big data, such as personal genome, brain data, biomedical data, health-care data, life-logs. This symposium will present important interdisciplinary challenges for guiding future advances in AI community.
The following topics are the scope of our interests, but the topic list is not exhaustive:
How to quantify our health and cognitive performance: sleep monitoring, diet monitoring, vital data, diabetes monitoring, running/sport calorie monitoring, personal genome, personal medicine, new type of self-tracking device, portable mobile tools, health data collection, quantified self tools, experiments, affective computing, Weables and cognition, brain fitness and training, learning enhancement strategies, sleep, dreaming, relaxation, meditation, yoga, physiology, nutrition, chemicals, electrical stimulation (tDCS, rTMS, CES, EEG, neurofeedback)
How to analyze the health and cognitive data for discovering the new meanings: Discovery informatics technologies; data mining and knowledge modeling for wellness, collective intelligence/ knowledge, life log analysis (for example, vital data analyses, Twitter-based analysis), data visualization, human computation), biomedical informatics, personal medicine; cognitive and biomedical modeling; brain science, brain interface, physiological modeling, biomedical informatics, systems biology, network analysis, mathematical modeling, disease dynamics, personal genome, gene networks, genetics and lifestyle with microbiome, health and disease risk.
How to design our health and cognitive enhancement space: Social data analyses and social relation design, mood analyses, human computer interaction, health care communication system, natural language dialog system, personal behavior discovery, Kansei, zone and ceativity, compassion, calming technology, Kansei engineering, gamification, assistive technologies, ambient assisted living (AAL) technology.
Applications, platforms and field studies: Medical recommendation system, care support system for aged person, web service for personal wellness, games for health and happiness, life log applications, disease improvement experiment (such as metabolic syndrome, diabetes), sleep improvement experiment, healthcare or disabled support systems, community computing platform.
The symposium is organized by the invited talks, presentations, and posters and interactive demos.
Interested participants should submit either full papers (8 pages maximum) or extended abstracts (2 pages maximum). Extend abstracts should state your presentation types (long paper (6–8 pages), short papers (1–2 pages), demonstration, or poster presentation). The electronic version of your paper should be send to email@example.com by October 10, 2014.
Takashi Kido (Rikengenesis, Japan)
Keiki Takadama (The University of Electro-Communications, Japan)
Quantifying Our Health and Cognitive Performance Committee: Melanie Swan (DIYgenomics, USA), Katarzyna Wac (Stanford University, USA and University of Geneva, Switzerland), Ikuko Eguchi Yairi (Sophia University, Japan)
Discovery Informatics and Health/Cognitive Modeling Committee: Chirag Patel (Stanford University, USA), Rui Chen (Stanford University, USA), Ryota Kanai (University of Sussex, UK.), Yoni Donner (Stanford, USA), Yutaka Matsuo (University of Tokyo, Japan)
Designing Health and Cognitive Enhancement Committee: Eiji Aramaki (University of Tokyo, Japan), Pamela Day (Stanford, USA), Tomohiro Hoshi (Stanford, USA)
Application, Platform, Field Study Committee: Miho Otake (Chiba University, Japan), Yotam Hineberg (Stanford, USA), Yukiko Shiki (Kansai University, Japan)
Advisory Committee: Atul J. Butte (Stanford University, USA), Seiji Nishino (Stanford University, USA.), Katsunori Shimohara (Doshisha University, Japan)
For More Information
Game theory's popularity continues to increase in a whole variety of disciplines, such as economics, biology, political science, computer science, electrical engineering, business, law, public policy, and many others. The focus of this symposium is to bring together the community working on applied computational game theory motivated by any of these domains.
A variety of very large-scale real-world problems can be cast in game-theoretic contexts. For example, software assistants based on game theory have been developed for generating randomized patrol plans to protect computer networks, ports, airports, flights and transit systems. Also game theory has been utilized for disaster management, medical record inspections and mechanism design for markets. Further, interdisciplinary work of game theory and machine learning has been applied to domains such as spam detection, fishery protection and poaching prevention where the repeated interactions between players are involved. Another area with growing interest is computer poker, where the presence of imperfect information in the game raises important new challenges.
While there has been significant progress, there still exist many major challenges facing the design of effective approaches to deal with the difficulties in these real-world domains. These may include building predictive behavioral models for the players, dealing with uncertainties in games, scaling up for large games, learning in repeated games. Addressing these challenges requires collaboration from different communities including artificial intelligence, game theory, operations research, social science, and psychology. This symposium is structured to encourage a lively exchange of ideas between members from these communities. We encourage all researchers working towards applying computational game theory for real-world problems to submit to the symposium.
Topics of interest include but are not limited to:
- Real-world applications of game theory
- Game theory foundations
- Algorithms for scaling to very large games
- Behavioral game theory
- Modeling uncertainty in game theoretic applications
- Learning in games
- Imperfect information in games and computer poker
- Agent/human interaction for preference elicitation and optimization
- Risk Analysis
- Applied Mechanism Design for Markets, Auctions
The symposium will consist of welcome session, invited talks, paper presentations, and a panel discussion.
Submissions should be made through EasyChair following the AAAI format, and should be up to 8 pages in length, including figures and references.
Chair and Main Contact Fei Fang University of Southern California 3737 Watt Way, Powell Hall of Engineering 210, Los Angeles, CA 90089 Phone: (213) 740-7231 Email: firstname.lastname@example.org Organizing Committee Christopher Kiekintveld (University of Texas at El Paso, email@example.com), Yevgeniy Vorobeychik (Vanderbilt University, firstname.lastname@example.org), Peter Stone (University of Texas at Austin, email@example.com), Bo An (Nanyang Technological University, firstname.lastname@example.org), Manish Jain (Armorway, email@example.com), Fei Fang (University of Southern California, firstname.lastname@example.org), Albert Xin Jiang (Trinity University, email@example.com)
For More Information
Approaches using artificial intelligence (AI) may soon manage complex systems with teams, including hybrid teams composed arbitrarily of humans, machines, and robots. Already, AI has been useful in modeling the defense of individuals, teams, and institutions, as well as the management of social systems such as virtual ship bridges. However, foundational problems remain in the continuing development of AI for team autonomy, especially with objective measures able to optimize team function, performance and composition.
AI approaches often attempt to address autonomy by modeling aspects of human decision-making or behavior. Behavioral theory is either based on modeling the individual, such as through cognitive architectures or, more rarely, through group dynamics and interdependence theory. Approaches focusing on the individual assume that individuals are more stable than the social interactions in which they engage. Interdependence theory assumes the opposite, that a state of mutual dependence among participants in an interaction affects the individual and group beliefs and behaviors of participants. The latter is conceptually more complex, but both approaches must satisfy the demand for predictable outcomes as autonomous teams grow in importance and number.
Despite its theoretical complexity, including the inherent uncertainty and nonlinearity exposed by interdependence, we argue that complex autonomous systems must consider multiagent interactions to develop predictable, effective and efficient hybrid teams. Important examples include cases of supervised autonomy, where a human oversees several interdependent autonomous systems; where an autonomous agent is working with a team of humans, such as in a network cyber defense; or where the agent is intended to replace effective, but traditionally worker-intensive team tasks, such as warehousing and shipping. Autonomous agents that seek to fill these roles, but do not consider the interplay between the participating entities, will likely disappoint.
Our symposium offers opportunities with AI to address these and other fundamental issues about autonomy, including its application to hybrids at the individual, group and system levels.
Papers should address "Foundations of autonomy and its (cyber) threats: From individuals to interdependence," and specify the relevance of their topic to AI or how AI can be used to help address their issue.
Initial submissions by October 10, 2014 for review can be either 2 pages or 8 pages; initial submissions should be submitted to the organizers listed below. After review and approval, papers should use the format specified by AAAI, and may be either 2 page abstracts or up to 8 pages for final submissions. The AAAI AuthorKit includes templates and further formatting instructions.
Ranjeev Mittu (firstname.lastname@example.org); Gavin Taylor (email@example.com); Don Sofge (Naval Research Laboratory, firstname.lastname@example.org), W.F. Lawless (Paine College, email@example.com)
For More Information
Early work on knowledge representation and inference, which was done in the AI community back in the 1980s, was primarily symbolic. Subsequently, symbolic approaches fell out of favor, and were largely supplanted by statistical methods. This symposium will try to close the gap between the two paradigms, and aim to formulate a new paradigm that is inspired by our current understanding of how humans solve these tasks. Both symbolic / structured approaches and distributed / statistical approaches have a long history, and both have strengths and weaknesses. For example, symbolic systems are able to represent and reason with crisp rules, and distributed systems are able to represent (and to a much lesser extent, reason with) fuzzy concepts. It is widely believed that "general" AI systems will need both forms of functionality. This dichotomy was widely debated during the first "connectionist revolution" in the 1980s. We feel the time is ripe to revisit this discussion, based on the development and wide availability of massive symbolic knowledge bases (for example, Freebase) on the one hand, and recent advances in deep learning on the other. While historically this research has been conducted in the computer science community, we would like to bridge between this work and the study of human cognition.
The symposium will include a mix of invited and submitted (peer-reviewed) contributions, which will be presented as formal talks as well as posters. The symposium will be highly interactive, with plenty of time for unstructured discussion. The last day of the workshop will be devoted to summarizing the various approaches presented at the symposium, and fusing them to formulate a hybrid research agenda for the field. We will also formulate a list of tasks that are expected to benefit from the improvements in knowledge representation and reasoning in the short to medium term, so that new approaches can be measured and evaluated on a common set of tasks.
Submissions should be in the form of an extended abstract, up to 4 pages in PDF format. Submissions should be made via the Easychair site below; no email submissions will be accepted. Submissions should not be anonymized, and the author names and affiliations should be displayed on the first page.
Contact email: firstname.lastname@example.org
Symposium Chairs / Organizing Committee Andrew McCallum (UMass), Evgeniy Gabrilovich, Ramanathan Guha, and Kevin Murphy (Google)
For More Information
We invite submissions for presentation at Commonsense-2015. Endowing computers with common sense is one of the major long-term goals of Artificial Intelligence research. One approach to this problem is to formalize commonsense reasoning using representations based on formal logic or other formal theories. The challenges to creating such formalizations include the accumulation of large amounts of knowledge about our everyday world, the representation of this knowledge in suitable formal languages, the integration of different representations in a coherent way, and the development of reasoning methods that use these representations.
Commonsense reasoning is relevant for many applications, including systems in which robots and humans interact, and natural language systems that use both commonsense knowledge and corpus-based learning. In his IJCAI 2013 Research Excellence Award lecture, Hector Levesque argued that commonsense reasoning is central for intelligent behavior and proposed the commonsense-knowledge-based Winograd Schema Challenge as an alternative to the Turing Test. We especially solicit papers describing research on the Nuance-sponsored Winograd Schema Challenge Competition.
- Formal representations, reasoning, and algorithms, for specific commonsense domains such as: time, change, action, causality, and geometry; commonsense physical, biological, legal, medical, etc. reasoning; mental states and propositional attitudes, such as knowledge, belief, intention, desire; and social relations
- Methods for creating commonsense knowledge bases, including: statistical and corpus-based machine learning techniques; crowd sourcing; and hand crafting microtheories
- Applications of commonsense reasoning to specific tasks such as robotics, natural language processing, machine learning, vision, search, and planning.
- Relations among object-level theories, such as abstraction and contextualization
- Methods of deductive and plausible reasoning that are applicable to commonsense domains and problems, including: answer set programming; probability, heuristic, or approximate reasoning; nonmonotonic reasoning; and belief revision
- Meta-theorems about commonsense theories and techniques
- Relation of other fields, such as philosophy, linguistics, cognitive psychology, game theory, and economics to formal theories of commonsense knowledge.
We aim for rigorous and concrete submissions, in a wide variety of forms, including new results, demos, surveys, empirical comparisons of different approaches, and papers on methodological issues. While mathematical logic is expected to be the primary lingua franca of the symposium, we also welcome papers using a rigorous but not logic-based representation of commonsense domains.
Submissions should be made through EasyChair.
Leora Morgenstern (Leidos), Theodore Patkos (Foundation for Research and Technology Hellas), Robert Sloan (University of Illinois at Chicago)
For More Information
Information is extremely critical for efficient decision-making, whether it is for business processes, policy design, or complex military operations confronting a broad spectrum of conflict and human security. However, more information does not always imply more effectiveness. With the advances in ICTs, especially the participatory media (or, social media), information analysts find themselves inundated with data, or rather the "big data". To put things in perspective, a conservative estimate suggests that 2.5 billion gigabytes of data was created every day in 2012, of which 68% was the user generated content or data from social media sites, with no signs of slowing down, in fact doubling up every month. The prevalence of the social media and smart handheld devices has irreversibly transformed our communication, interaction, and information sharing styles, giving rise to novel socio-technical behaviors (for example, "hacktivism", crowdsourcing, self-organization, flash mobs, citizen journalism, "live-tweeting" or "tweetcasting", etc.). Efficient data analysis techniques are needed to understand and model emerging socio-technical behaviors.
Existing studies provide limited understanding of these behaviors. A fundamental and systematic investigation of social media platforms is a precursor to conduct studies at a more foundational level filling this critical research gap. Through this symposium, we intend to create a collaborative and interdisciplinary platform bringing researchers and practitioners from various disciplinary backgrounds, including (but not limited to), computational and information science, social science, cognitive science, mathematics, statistics, economics, among others to share, exchange, learn, and develop preliminary models, new concepts, ideas, principles, and methodologies, aiming to advance the understanding and the current state of research in the socio-technical behavior mining. The outcome of the symposium would serve as a collection of resources that can be used by researchers contributing to a continuous and synergistic advancement of the various disciplines.
The following topics are of key interest:
Fundamental or Theoretical Contributions
- Social science informed data mining algorithms
- Group dynamics
- Social processes
- Collective actions and manifestations (for example, campaigns, flash mobs, movements)
Data Processing and Analytics
- Rumor (misinformation or disinformation) detection
- Data provenance and trust
- Spam (for example, Twitter bot) detection
- Social-cyber systems (crowdsourcing, crowdfunding, etc.)
- Smart health
- Government 2.0
- Crisis management
- Conflict monitoring
All submissions should be made in AAAI format, and should be up to 8 pages in length, including figures and references.
Submissions should be made through EasyChair.
Nitin Agarwal (University of Arkansas at Little Rock, email@example.com), Huan Liu (Arizona State University, Huan.Liu@asu.edu), Laurie Fenstermacher (Air Force Research Lab, firstname.lastname@example.org)
For More Information
Technology is playing an increasingly important role in all aspects of humanitarian operations including search and rescue, early warning, and coordination of logistics. However, applications that support humanitarian operations often consume data stored in standalone databases, or in spreadsheets requiring manual steps for data merging and management. Moreover, the data structure is driven by schemas developed in isolation as opposed to ontological structures supported by the community such as the humanitarian exchange language (HXL) and management of a crisis (MOAC). Consequently, the increasingly unorganized and scattered information becomes noise in the overall system, slowing down decision-making processes.
Our objective is to assess the role of structured data (SD) standards such as linked data, which can be quickly reused, integrated and extended, in the humanitarian space. Using SD would permit effective integration of and analysis over data generated by multiple parties, including informal communities that is, the crowd, relief organizations, and more formally by government agencies. However, there are several important challenges that prevent its widespread adoption such as the lack of data sources, lack of mature libraries, and lack of standards across different humanitarian sectors. This symposium proposes to investigate the role of SD in the humanitarian relief domain. Is the technology mature enough to warrant further investigation or do the disadvantages outweigh the utility of SD for this domain? We invite both position papers discussing these issues as well as technical papers that demonstrate the effective use of SD in the humanitarian domain or where another comparable technology has been used to address the reuse and integration issues.
We invite papers on various research topics in the context of extracting, organizing, and using SD in the applications for humanitarian relief, including but not limited to the following:
- Data schemas or ontologies for disaster management
- Data schemas or ontologies for need/offer to assist coordination
- Schemas or ontologies for humanitarian response and recovery operations
- Applications of SD in humanitarian technologies
- Use cases for use of SD for humanitarian operations at various levels — field, regional and headquarters
The symposium will include paper presentations, invited talks, and panel discussions that will bring together multidisciplinary experts.
We invite two types of submissions: position papers (up to 5 pages), and technical papers (up to 8 pages). 5. Submit to EasyChair.
Lalana Kagal (MIT, email@example.com), Hemant Purohit (Kno.e.sis, Wright State University, firstname.lastname@example.org), Oshani Seneviratne (MIT, email@example.com)
For More Information
The goal of this symposium is to bring together researchers across multiple disciplines — including multimodal systems, human-robot interaction, embodied conversational agents, and spoken dialogue systems — to address a topic of common interest: the modeling, realization, and evaluation of turn-taking and real-time action coordination between humans and artificial interactive systems. This symposium will serve to build common ground for researchers from these disparate backgrounds to share their perspectives, methodologies, and results from their own investigations into the problem of multimodal coordination.
Regulating human-computer coordination hinges critically on multimodal sensing, making decisions under uncertainty and time constraints, and on synchronizing behaviors across different output modalities. On the sensing side, there are numerous challenges with tracking the conversational dynamics from multimodal data. Making coordination decisions often requires reasoning under uncertainty and strict time constraints. Designing and rendering appropriate coordination behaviors (for example, floor-taking actions, floor-releasing actions, and back-channels) appropriate for the affordances of a system's embodiment raises additional challenges.
Topics include, but are not limited to the following:
- models for coordinating linguistic and nonlinguistic actions
- computational models for multiparty coordination and turn-taking
- multimodal inference for turn-taking (inferences about user utterances, transition relevant places, floor control actions, backchannels)
- incremental speech and audio-visual processing
- high-frequency, real-time decision making under uncertainty
- fusion of multiple information sources for making coordination decisions
- machine learning for multimodal inference and making coordination decisions
- communication dynamics in human-human action coordination and turn-taking
- listener feedback behavior, including back-channel generation
- turn-taking phenomena and affordances (for example, linguistic and nonlinguistic actions such as disfluencies, filled pauses, hedging, floor-holding, gestures and gaze, etc)
- generation of coordination and turn-taking behaviours (behavioural rendering)
- issues in coordination among parties with asymmetric roles, goals, or affordances
- effects of social factors and relationships on coordination behaviour
- cross-linguistic and cross-cultural factors
- corpora and resources for action coordination and turn-taking research
- metrics and methodologies for assessing coordination competencies
- empirical evaluation of action coordination and turn-taking models
- comparisons across human-robot interaction, embodied conversational agents, and spoken dialogue systems
The symposium will include the following:
- Oral presentation sessions for accepted full papers
- Poster sessions for accepted short papers and position papers
- Plenary presentations by invited speakers
- Open panel discussions on core challenges from the perspective of different fields
- Breakout discussion sessions on how to facilitate new collaborative research efforts
- Video session
We invite the submission of videos that illustrate both successful coordination in human-machine interactions and also failure cases, as we believe these are as important (if not more) in driving research and the field forward. The accepted videos will be presented during the video session, and will serve as drivers for an open, plenary discussion on research challenges and opportunities in this area.
Prospective authors are invited to submit full papers (6 pages), short papers (3 pages), and/or videos (up to 5 minutes) to EasyChair. Accepted papers will be published in a technical report on the AAAI Digital Library. Videos will not be archived.
Sean Andrist (University of Wisconsin-Madison, USA, firstname.lastname@example.org), Dan Bohus (Microsoft Research, USA, email@example.com), Eric Horvitz (Microsoft Research, USA, firstname.lastname@example.org), Bilge Mutlu (University of Wisconsin-Madison, USA, email@example.com), David Schlangen (Bielefeld University, Germany, firstname.lastname@example.org)