AAAI 2013 Fall Symposium Descriptions

AAAI 2013 Fall Symposium Descriptions

The Association for the Advancement of Artificial Intelligence is pleased to present the 2013 Fall Symposium Series, to be held Friday through Sunday, November 15–17, at the Westin Arlington Gateway in Arlington, Virginia. The titles of the seven symposia are as follows:

Behavioral Web Analytics

Web intelligence has sought to understand and predict web behavior in order to improve a specific exogenous outcome such as the checkout of a shopping cart or improvement in meaningful search results. More interest is given now to understanding those behaviors themselves. For instance, it is of interest to understand individual and collective web behaviors to further model and support knowledge extraction in applications such as cybersecurity, recommendation systems, and human computation systems. This proposed symposium on behavioral web analytics aims to bring together artificial intelligence researchers from the machine learning and planning community, the cognitive science community, social computing community, and the human-centered computing community to develop a more meaningful understanding of individual and group behavior in online environments.

Topics

Topics of interest include, but are not limited to the following:

Characterization of web behavior (for example, click rate, revisit rate, session length)
Categorization of web behavior (for example, shopping, information seeking)
Modeling web behavior including behavioral changes (computational models, tools and techniques)
Authentication/Identification (learning methodologies for attribution)
Inferring intent from web behavior
Assessment of web behavior (metrics for trustworthiness, influence)

Organizing Committee

Myriam Abramson (Naval Research Laboratory), Nitin Agarwal (University of Arkansas at Little Rock)

For More Information

For more information, please see the supplemental symposium website.

Discovery Informatics: AI Takes a Science-Centered View on Big Data

Discovery informatics focuses on intelligent systems aimed at accelerating discovery, particularly in science but also from any data-rich domain. It is a generalization of scientific informatics work (for example, medical-, bio, eco, or geoinformatics) that seeks to apply principles of intelligent computing and information systems in order to understand, automate, improve, and innovate any aspects of discovery processes. A range of AI research is directly relevant including process representation and workflows; intelligent interfaces; causal reasoning; machine learning; knowledge representation and engineering; semantic web; advanced visualization toolkits and social computing.

The application of AI approaches to assist in scientific discovery is an open ended knowledge-driven challenge with a very high potential impact. This is especially true in this era of big data, which provides the theme of this symposium.

Topics

This symposium will provide a forum for researchers interested in understanding the role of AI techniques in improving or innovating scientific processes. We encourage submissions that: (1) build on success stories that provide a contextual understanding of why certain approaches worked in scientific domains; (2) push the envelope of discoveries in big data; (3) characterizes the act of discovery as a computing challenge for intelligent systems.

Specific topics of discussion include, but are not limited to the following:

What are the broad AI challenges in discovery in big data?
How can we support the way scientists approach big data?
How do we get to big data from smaller data through automated or assisted integration and aggregation?
What integrated AI capabilities are needed to tackle big data in science?
How can we improve our understanding of science and discovery processes and the role of AI in the context of those processes?
How can we capture science processes and open them to scientists in other disciplines and the broader public?
Can AI be effective in facilitating insights and looking for knowledge gaps using big data?

Format

The symposium will be organized around thematic sessions. Each session will include paper presentations and in some cases invited speakers, followed by discussions.

Submissions

Submissions should be up to 6 pages. Please submit to the EasyChair Submission site.

Main Contact
Gully APC Burns, University of Southern California, burns@isi.edu, (310) 448-8712.

Cochairs
Gully APC Burns (University of Southern California, burns@isi.edu); Yolanda Gil (University of Southern California, gil@isi.edu); Yan Liu (University of Southern California, yanliu.cs@usc.edu); Natalia Villanueva-Rosales (University of Texas at El Paso, nvillanuevarosales@utep.edu)

For More Information

For more information, please see the supplemental symposium website.

How Should Intelligence be Abstracted in AI Research: MDPs, Symbolic Representations, Artificial Neural Networks, or — ?

We invite contributions to our AAAI 2013 Fall Symposium, where we aim to bring together a diverse and multi-disciplinary group of AI researchers interested in discussing and comparing different abstractions of intelligence and processes that might create it. We hope to provide a common ground to actively encourage cross-pollination of ideas between levels and types of abstraction, and generate new ideas for revising or creating abstractions of intelligence and intelligence-generating processes.

We invite contributions related to how intelligence can or should be abstracted in artificial intelligence research. Papers that provide a high-level overview of existing work or summarize the results of an extended research program along these lines are most welcome, as are position papers or contributions describing speculative work or work in progress. Works bridging traditionally separate AI paradigms are encouraged.

Topics

Areas of interest include but are not limited to the following:

Different levels and types of knowledge representation and reasoning
Abstractions of the following:
Neural networks (for example, deep learning networks, spiking ANNs, and plastic ANNs)
Learning (for example, machine learning and reinforcement learning)
Biological development (for example, generative and developmental systems, and developmental robotics)
Evolutionary search (for example, digital evolution and evolutionary algorithms)
Biologically-inspired computation
Evolutionary robotics
Swarm intelligence
Artificial life
Philosophical arguments on characteristics of appropriate abstractions for AI

Submissions

Interested participants may submit either full-length papers (up to 6 pages in AAAI format) or short papers/extended abstracts (2 pages) in PDF format to sebastian.risi@cornell.edu.

Organizing Committee

Sebastian Risi (Cornell University), Joel Lehman (University of Texas at Austin), Jeff Clune (University of Wyoming)

For More Information

For more information, please see the supplemental symposium website.

Integrated Cognition

Integrated cognition is concerned with consolidating the functionality and phenomena implicated in natural minds or brains and/or artificial cognitive systems (virtual humans, intelligent agents or intelligent robots). The aim of this symposium is to bring together researchers from across the spectrum of approaches and perspectives to exchange research results and discuss how best to create an ongoing forum for such exchanges. The focus is on how the mind arises from the interaction of its constituent parts, and includes everything implicated in human-level performance in complex environments. This includes not only traditional cognitive aspects - such as planning and problem solving, knowledge representation and reasoning, language and interaction, and learning — but also perception and control, personality and emotion, and motivation. It also includes not only integration across cognitive mechanisms, as is typical in work on cognitive architectures, but also across more abstract constraints on cognition. It furthermore includes work on across-level integration, including combining cognitive capabilities with aspects of lower levels, whether computational or neural; as well as integrating in aspects of higher levels, whether cognitive applications or the social band from Newell's time scales.

Topics

Contributions to this symposium may cover the integration of mechanisms, capabilities, constraints, models, applications and levels; and may involve the creation, enhancement, evaluation and/or analysis of such combinations. Contributions may be in the form of technical papers with results on integrated cognition, panel discussions of key issues in integrated cognition, or proposals for new approaches to integrated cognition. The forum is open to all paradigms, with evaluation of submissions based on the general criterion of how much they further our understanding of integrated cognition.

Submissions

Proposals for discussion panels should involve 4 to 6 participants and include a description of the overall panel topic as well as abstracts for each panelist contributions. Papers and discussion panel proposals should be between 5 and 8 pages long, including references, in AAAI format. Submissions in PDF format should be sent to either of both of the conference cochairs by email only:

Christian Lebiere
Department of Psychology
Carnegie Mellon University
Pittsburgh, PA 15213, USA
Email: cl@cmu.edu
Phone: (412) 268-6028
Fax: (41) 268-2798

Paul S. Rosenbloom
USC Institute for Creative Technologies
12015 Waterfront Dr.,
Playa Vista, CA 90094, USA
Email: rosenbloom@usc.edu
Phone: (310) 448-5341
Fax: (310) 574-5725

For More Information

For more information, please see the supplementary symposium web site.

Semantics for Big Data

One of the key challenges in making use of big data lies in finding ways of dealing with heterogeneity, diversity, and complexity of the data, while its volume and velocity forbid solutions available for smaller datasets as based, for example, on manual curation or manual integration of data.

Semantic web technologies are meant to deal with these issues, and indeed since the advent of linked data a few years ago, they have become central to mainstream semantic web research and development. We can easily understand linked data as being a part of the greater big data landscape, as many of the challenges are the same. The linking component of linked data, however, puts an additional focus on the integration and conflation of data across multiple sources.

Topics

In this symposium, we will explore the many opportunities and challenges arising from transferring and adapting semantic web technologies to the big data quest. Topics of interest focus explicitly on the interplay of semantics and big data, and include the following:

The use of semantic metadata and ontologies for big data,
The use of formal and informal semantics,
The integration and interplay of deductive (semantic) and statistical methods,
Methods to establish semantic interoperability between data sources
Ways of dealing with semantic heterogeneity,
Scalability of semantic web methods and tools, and
Semantic approaches to the explication of requirements from eScience applications.

Format

The symposium will be highly interactive with spotlight presentations and small breakout groups interleaved with plenary sessions for reports on the breakout groups and for consolidation of results.

Submissions

To prime and channel discussions and group activities during the event, we call for the submission of position papers or extended abstracts of 2–4 pages, or of technical papers of 6–8 pages (in AAAI format). Submissions shall be made through EasyChair by May 24th, 2013.

Organizing Committee

Frank van Harmelen (Vrije Universiteit Amsterdam, The Netherlands, frank.van.harmelen@cs.vu.nl); James A. Hendler (Rensselaer Polytechnic Institute, USA, hendler@cs.rpi.edu); Pascal Hitzler (Kno.e.sis Center, Wright State University, USA, pascal.hitzler@wright.edu); Krzysztof Janowicz (University of California, Santa Barbara, USA, jano@geog.ucsb.edu

For More Information

For more information, please see the the supplementary symposium web site.

Social Networks and Social Contagion

With the emergence of computational social science as a field of collaboration between computer scientists and social scientists, the study of social networks and processes on these networks (social contagion) has been gaining interest. Many topics of traditional sociological interest (such as the diffusion of innovations, emergence of norms, identification of influencer) can now be studied using detailed computational models and extensive simulation. The advent and popularity of online social media also allows the creation of massive data sets which can inform models and underlying sociological theory. The ubiquity of "smart devices" (such as smart phones) also provides opportunities to gather extensive data on the behaviors and interactions of humans in real space.

The goal of this symposium is to bring together a community of researchers interested in addressing these issues and to encourage interdisciplinary approaches to these problems. We specifically encourage participation and contributions from many communities, including computer science, statistics, mathematics, the social, behavioral and economic sciences, and the medical and health sciences.

Topics

Papers are invited on topics including, but not limited to, the following:

Social Contagion

The spread of ideas or beliefs
Emotion contagion
Diffusion of information
The spread of changes in language
Diffusion of innovations
Emergence of norms
Interventions to prevent contagion
Influence maximization
Complex contagion
virtual agents, agent-human contagion
Disease contagion
Diffusion of risk behaviors in networks
Diffusion of health behaviors in networks

Game Theory in Social Networks and Social Contagion

Influence maximization
Influence blocking maximization game
Other game-theoretic approaches

Network Modeling

Exponential random graph models
Stochastic actor models
Network evolution models, etc.

Network-Based Inference

Label inference
Network structure inference
Contagion model inference

Human Data Elicitation

Expression of attitudes/personality from online sources (such as Twitter and Facebook)
Using social media for tracking social contagion, developing social networks, and others
Crowdsourcing as a means to learn about humans
Massively multiplayer online games (MMOG) as virtual laboratories to study social contagion
Reality mining for social networks

Submissions

Submissions can be a paper of up to eight pages in AAAI format.

Organizing Committee

Samarth Swarup (Virginia Tech), Madhav Marathe (Virginia Tech), Kiran Lakkaraju (Sandia National Laboratory), Milind Tambe (University of Southern California), Cynthia Lakon (University of California, Irvine)

For More Information

For more information, please contact Samarth Swarup at swarup@vbi.vt.edu.

AAAI 2013 Fall Symposia Descriptions