[UAI] SLPAT 2013, third call for papers
SLPAT 2013, 3rd call for papers The 4th annual workshop on Speech and Language Processing for Assistive Technologies (SLPAT). 21 and 22 August 2013, Grenoble France (satellite event of Interspeech 2013). ==> Submission deadlines: 27 May (research papers) and 3 June (demo proposals) <== Full details: http://slpat.org/slpat2013 Contact: slpat2013.works...@gmail.com Colleagues, We invite you to join us in Grenoble for the 4th annual workshop on Speech and Language Processing for Assistive Technologies. This 2-day workshop will combine research in speech and language technology that assists people with physical, cognitive, sensory, emotional, or developmental disabilities. This year we are introducing a special topic -- Smart Homes and ambient intelligent technology applied to augmentative communication. The program committee is now online at http://www.slpat.org/slpat2013/people.html. It is our pleasure to announce that Professor Mark Hawley will be delivering an Invited Lecture on the first day of the workshop. Mark Hawley is Professor of Health Services Research at the University of Sheffield, UK, where he leads the Rehabilitation and Assistive Technology Research Group. He is also Honorary Consultant Clinical Scientist at Barnsley Hospital, where he is Head of Medical Physics and Clinical Engineering. Over the last 20 years, he has worked as a clinician and researcher -- providing, researching, developing and evaluating assistive technology, telehealth and telecare products and services for disabled people, older people and people with long-term conditions. This year's workshop will include a tour of a smart home at the Laboratory of Informatics of Grenoble. More details will become available on the SLPAT 2013 website. General topics of SLPAT 2013 include but are not limited to: - Automated processing of sign language - Speech synthesis and speech recognition for physical or cognitive impairments - Speech transformation for improved intelligibility - Speech and Language Technologies for Assisted Living - Translation systems; to and from speech, text, symbols and sign language - Novel modeling and machine learning approaches for AAC/AT applications - Text processing for improved comprehension, e.g., sentence simplification or text-to-speech - Silent speech: speech technology based on sensors without audio - Symbol languages, sign languages, nonverbal communication - Dialogue systems and natural language generation for assistive technologies - Multimodal user interfaces and dialogue systems adapted to assistive technologies - NLP for cognitive assistance applications - Presentation of graphical information for people with visual impairments - Speech and NLP applied to typing interface applications - Brain-computer interfaces for language processing applications - Speech, natural language and multimodal interfaces to assistive technologies - Assessment of speech and language processing within the context of assistive technology - Web accessibility; text simplification, summarization, and adapted presentation modes such as speech, signs or symbols - Deployment of speech and NLP tools in the clinic or in the field - Linguistic resources; corpora and annotation schemes - Evaluation of systems and components, including methodology - Anything included in this year's special topic - Other topics in Augmentative and Alternative Communication The special topic this year is smart homes and intelligent companions. Subtopics include: - Automatic Speech recognition in distant or multi-source environments - Understanding, modelling or recognition of aged speech - Speech analysis in the case of elderly with impairments, early recognition of speech capability loss - Multimodal speech recognition (context-aware ASR) - Multimodal emotion recognition - Applications of speech technology (ASR, dialogue, synthesis) for ambient assisted living This year, SLPAT will be co-located with the 1st Workshop on Affective Social Speech Signals (WASSS,http://wasss-2013.imag.fr/, which takes place on 22 and 23 August 2013). Participation in and submission to both workshops will be facilitated by reduced registration fees for double-registration (rather than registering for both individually), co-ordination of topics on the overlapping day (22 August) to enable participation in both, and common lunch and events combining the two communities. We look forward to your submissions! Regards, Organizing Committee, SLPAT 2013 ___ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai
[UAI] NEW TEXTBOOK: "Computational Intelligence - A Methodological Introduction"
NEW BOOK: "Computational Intelligence - A Methodological Introduction" Authored by Rudolf Kruse, Christian Borgelt, Frank Klawonn, Christian Moewes, Matthias Steinbrecher, and Pascal Held We are pleased to announce the publication of the book "Computational Intelligence - A Methodological Introduction" (Springer Series Texts in Computer Science). This clearly-structured, classroom-tested textbook presents a methodical introduction to the field of Computational Intelligence (CI) which encompasses a range of nature-inspired methods that exhibit intelligent behavior in complex environments. Providing an authoritative insight into all that is necessary for the successful application of CI methods, this textbook describes fundamental concepts and their practical implementations, and explains the theoretical background underpinning proposed solutions to common problems. It presents self-contained discussions on artificial neural networks, evolutionary algorithms, fuzzy systems, and Bayesian networks. Only a basic knowledge of mathematics is required. Further details can be found at http://www.springer.com/book/978-1-4471-5012-1 ___ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai
[UAI] ADT 2013 - Final Call for Papers - Extended deadlines: May, 10 (abstract) May, 19 (papers)
[apologies for multiple postings] FINAL CALL FOR PAPERS = ADT 2013 Third International Conference on ALGORITHMIC DECISION THEORY Brussels, Belgium, Nov. 13-15, 2013 www.adt2013.org == The International Research Group on Algorithmic Decision Theory in collaboration with the European working group on preferences is proud to announce the Third International Conference on Algorithmic Decision Theory (ADT 2013). ADT seeks to bring together researchers and practitioners coming from diverse areas such as Artificial Intelligence, Database Systems, Operations Research, Decision Theory, Discrete Mathematics, Game Theory, Multiagent systems, Computational Social Choice, and Theoretical Computer Science in order to improve the theory and practice of modern decision support and automation systems. The contemporary theory and practice of decision theory and decision analysis must account for the presence of massive databases containing data extracted from the web or via data mining, combinatorial structures, partial and/or uncertain information, and distributed, possibly interoperating decision makers, and the existence of masses of potential users on the web. Such problems arise in various real-world decision making problems such as electronic commerce, and recommender systems, network optimization (communication, transport, energy), risk assessment and management, e-government. ADT provides a multi-disciplinary forum for sharing knowledge in this area with a special focus on algorithmic issues in Decision Theory. The two first International Conference on Algorithmic Decision Theory (ADT 2009, 2011) brought together researchers and practitioners from diverse areas of computer science, economics, and operations research from around the globe, with proceedings published in LNAI 5783 and LNAI 6992. ADT 2013 seeks to continue this tradition and invites technical research papers on the following areas: - Algorithmic Challenges to Modern Decision Support and Automation - Uncertainty and Robustness in Decision Making - Multi-Criteria Decision Analysis and optimization - Collective Decision Making - Preferences in Reasoning and Decision Making - Decision Theoretic Artificial Intelligence - Learning and Knowledge Extraction for Decision Support More specifically contributions to the conference are sought in the following topics: Preference Modeling and Aggregation; Multiobjective optimization; Planning and Sequential Decision Making under uncertainty; Robustness in Decision Making; Computational Social Choice; Compact Representation of Preferences; Preference Elicitation, Queries in Data Bases; Universal Languages for Preferences; Efficient Algorithms for Decision Making and Support; Multi-Agent Systems; Algorithmic Game Theory ; Communication Complexity; Argumentation and Explanation in Decision Support; Preferences and Policies Learning; Knowledge Extraction; Algorithm Tuning; Recommender Systems; Decision Support Systems. The ADT 2013 Program Committee invites submissions of technical research papers that will be reviewed based on the standard criteria of clarity, relevance, significance, originality, and soundness. These papers are expected to convey substantial technical contributions to the field, or to describe case studies and deployed applications, all placed in the context of existing work. Important dates: - Title and abstract submission: May 10, 2013; (new date***) Paper submission: May 19, 2013 (***new date***) Notification: around June 7, 2013 (will be extended accordingly to the new submission deadline) Final version June 28, 2013; ADT'13: November 13-15, 2013; Submission Details: --- Two types of submission are proposed: - Submission for proceedings: Submissions are invited on significant, original, and previously unpublished research on all aspects of Algorithmic Decision Theory. Papers must be at most 12 pages long in the LNCS format. The proceedings of ADT 2013 will be published by Springer Verlag in the Lecture Notes in Artificial Intelligence series. Papers will be accepted for either oral or poster presentation, or both. However, no distinction will be made between accepted papers in the conference proceedings. - Submission without proceedings: Submission are invited on significant recent results on Algorithmic Decision Theory. Papers must be at most 12 pages long. They will not appear in the proceedings and can be submitted elsewhere. Selected papers in this category will be accepted for either oral or poster presentation, or both. In any case, at least one author of each accepted paper is required to attend the conference to present the work. Authors will be required to agree to this requirement at the time of submission. Papers must be submitted via the Easychair system (see the conference web page for details). Location: -
[UAI] PhD position / scholarship in Machine Learning / Linked Data / Semantic Web
Applications are invited for a PhD position (with possible scholarship) based at the College of Engineering & Informatics at National University of Ireland, Galway. The successful candidate will perform research in the area of Artificial Intelligence under the supervision of Dr. Matthias Nickles and will have the opportunity to collaborate with the Digital Enterprise Research Institute (DERI), Galway. Candidates should have a very good degree in Computer Science or in a closely related subject. They should have excellent analytical skills and should be able to work independently as well as in cooperation with others. The successful applicant needs to have very good English skills. Prior research experience in some area of Artificial Intelligence such as machine learning, logic, Data Science/Big Data, probabilistic modeling, or Semantic Web and Linked Data technologies, is a significant plus. Applicants are expected to possess very good programming skills in at least one of the following languages: Scala, Java, C/C++, Haskell, Clojure, Prolog, or Answer Set Programming/AnsProlog. Suitable candidates will be considered for a scholarship. The scholarship is expected to start in September 2013 and is tenable for up to a maximum of four years, dependent on satisfactory progress and availability of funding. The value of the scholarship is up to 12,000 euro per year (tax-free) plus course fees. The PhD research work will be positioned in the areas of Statistical Relational Learning (SRL) and/or uncertainty reasoning for the Web, the Semantic Web, and Linked Data. SRL is an emerging subfield of Machine Learning and Data Mining for learning in relationally-, graph- or network-like structured domains, such as the (Semantic) Web, Linked Data and Social Networks. SRL builds upon classical Machine Learning and probability theory as well as on first-order logic and formal knowledge representation, bridging the gap between two of the most important spheres of Artificial Intelligence. SRL frameworks such as Markov Logic Networks have already proven to be highly successful in real-world applications. A direction of SRL which is particularly interesting in regard to the prospective PhD research is Relational Reinforcement Learning (RRL), which combines Reinforcement Learning with structurally rich relational or graph-like representation formats. Possible topics for PhD work are the investigation and development of novel methods, techniques and tools for the SRL of interaction processes on the Web/the Semantic Web, SRL for predictions using large-scale dynamic data on the Web/Semantic Web, and SRL backed-up by Constraint Solving or Answer Set Programming. Further topics can be found at http://www.it.nuigalway.ie/researchtopics.html#_Toc201304261 Variants of these might also be possible. Interested candidates should contact Dr. Matthias Nickles < matthias.nick...@nuigalway.ie > as soon as possible for a discussion of suitable project topics and for further details. Application is a two-stage process. Initial applications consisting of a CV, transcript(s), a motivation letter and a list of papers published (if any) should be sent to Dr. Matthias Nickles no later than 15th May 2013. ___ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai
[UAI] Call for Participation - Multi-Agent Systems and Collaborative Technologies Workshop
== Call for Participation = The 4th International Workshop on Multi-Agent Systems and Collaborative Technologies (I-MASC’13), San Diego, California, USA, May 23, 2013. http://cts2013.cisedu.info/2-conference/workshops/workshop-06-imasc *** Session Keynote Speech: “Security and Game Theory: Key Algorithmic Principles, Deployed Applications, Lessons Learned” Milind Tambe, Ph.D., Helen N. and Emmett H. Jones Professor in Engineering, Computer Science and Industrial Systems Engineering, University of Southern California *** IMASC'13 is a session to the International Conference on Collaborative Technologies and Systems (CTS’13), The Sheraton San Diego Hotel & Marina, San Diego, California, USA, May 20-24, 2013. http://cts2013.cisedu.info/ I-MASC'13 SCOPE AND OBJECTIVES Multi-Agent Systems (MAS) has grown into an interdisciplinary field that includes various tracks and embraces many previously distinctive research areas. Particularly, multi-agent coordination, a sub-area of MAS, investigates how multiple intelligent computational agents work together to achieve high-level goals beyond the capabilities of single agents. Many different approaches have been investigated, such as the partially observable Markov decision process (POMDP), task structure analysis, coordination communication protocols, etc. Collaboration Technologies and Systems (CTS) have evolved significantly as well. These tend to investigate the design and development of effective environments or tools that help human users work together in a distributed collaborative, possibly virtual, fashion. Some notable examples of CTS include Collaboratories, collaborative design/editing, and on-line collaboration tools and environments. CTS is beginning to look at the challenges of supporting coordinated, purposive activities. MAS is still facing challenges of scaling to large numbers of entities and real-world tasks (see, for example, Hendler's question of, “where are all the intelligent agents?"). This workshop will explore potential synergy between CTS and MAS/coordination because they share a common ground: how multiple entities ─ intelligent agents or humans alike - work together to carry out potentially related tasks. We will ask questions of whether and how design and development of collaboration systems, promoting coordinated human activity, could be enhanced by incorporating insights from MAS. Collaboration technologies embody practical considerations from the human users' points of view, allowing users to ignore how the underlying (agent) infrastructure is implemented. Meanwhile, MAS/coordination investigates intelligent agents’ underlying algorithms and mechanisms and, in some cases, how artificial agents can interact with people as peers. Conversely, intelligent agents will not see significant acceptance, nor will they be able to manage the complexity and knowledge-intensity of meaningful practical applications, without developing some understanding of how to make effective use of human contributions throughout the specification, execution, evaluation, and refinement stages of the software lifecycle. This workshop solicits papers that discuss synergies between MAS and CTS, possible advantages/disadvantages of hybrids between them for designing and developing modern distributed collaborative software systems, and research and/or real-world experience and/or applications and/or lessons learned that involve both CTS and MAS. That is, any paper that addresses both CTS and MAS, preferably in one or a set of applications that share similar underlying research challenges, is of interest to this workshop. An example could be: the design and development of a collaboration environment (say, a distributed planning tool) that enables multiple heterogeneous, human experts and agents to work in combination across computer networks on courses of actions in response to cyber attacks. Another example might be systems or interfaces supporting the division of labor between CTS and MAS elements during execution. ORGANIZERS Dr. Myriam Abramson, NRL Dr. Wei Chen, Intelligent Automation, Inc. Dr. Edmund Durfee,University of Michigan Dr. Robert Neches, IARPA INTERNATIONAL PROGRAM COMMITTEE Christopher Amato, Massachusetts Institute of Technology, USA Giacomo Cabri, Università di Modena e Reggio Emilia, Italy Bradley Clement, NASA JPL, California, USA Kevin Cousin, Air Force Institute of Technology, Ohio, USA Kerstin Dautenhahn, University of Hertfordshire, UK Geoffrey Fox, Indiana University, Indiana, USA Zhi Jin, Peking University, China Peng Liu, Pennsylvania State University, Pennsylvania, USA Frank Liu,Missouri University of Science and Technology, Missouri, USA Christopher Lynnes, NASA, USA Priya Ranjan, Human Development Foun
[UAI] Workshop on Real-World Challenges for Data Stream Mining @ ECMLPKDD2013
CALL FOR WORKSHOP TALKS Real-World Challenges for Data Stream Mining Workshop-Discussion at ECMLPKDD 2013 September 27th, 2013, Prague, Czech Republic https://sites.google.com/site/realstream2013/ * * * * * * * * * * * * * * * * * * * * * * * * FOCUS Data streams, online learning and adaptation to concept drift have become important research topics during the last decade. Data arrives in a stream in real time and needs to be mined in real time. In spite of the popularity of the research, truly autonomous, self-maintaining, adaptive data mining systems are rarely reported. This workshop will provide a forum for researchers and practitioners to discuss real-world challenges for data stream mining, identify gaps between data streams research and meaningful applications, and define new application-relevant research directions for data stream mining. CALL FOR PAPERS The focus of this workshop is on presentations and discussions rather than on full written articles. Only extended abstracts (up to 4 pages in Springer LNCS format) are required as a submission and will be published in the online proceedings. The submission of works-in-progress, industrial experiences, as well as the presentation of works already published elsewhere is strongly encouraged. Well articulated position papers are welcome. TOPICS OF INTEREST We invite contributions focusing on real world challenges for data stream mining. Topics include, but are not limited to: 1.Challenges and lessons learned from mining real-world data streams 2.Dealing with realistic data and workflows - End user participation to varying degrees - Interactive user feedback for adaptive learning - Reliability / correctness of feedback - Availability and delay of feedback 3.Integrating expert knowledge into data stream models - What to ask of an expert? - When to ask? How to set the priorities? 4.Moving from data stream algorithms towards data stream tools - Online data preparation and pre-processing - Improving usability and trust - Developing autonomous, self-diagnosing data stream tools 5.Scalability of data stream mining systems KEY DATES June 28, 2013: Extended abstract submission July 19, 2013: Notification of acceptance August 2, 2013: Camera-ready September 27, 2013: Workshop date ORGANIZATION Workshop organizers Georg Krempl, KMD, Otto-von-Guericke-University Magdeburg, Germany Indre Zliobaite, Aalto University, Finland Yin Wang, HP Labs, USA George Forman, HP Labs, USA Program Committee Albert Bifet, Yahoo! Research, Spain Joao Gama, LIAAD - INESC Porto, University Porto T. Ryan Hoens, SAS Institute, USA Petr Kadlec, Evonik Industries, Germany Vincent Lemaire, Orange Labs, France Fabian Moerchen, Amazon, USA Mykola Pechenizkiy, TU Eindhoven, The Netherlands Myra Spiliopoulou, KMD, Otto-von-Guericke-University Magdeburg, Germany Alexey Tsymbal, Siemens, Germany (to be finalized) ___ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai