1st International Semminar on New Issues of Artificial Intelligence
CAOS-EVANNAI-GIAA-PLG

Departamento de Informática
Universidad Carlos III de Madrid

Sesión Inagural: 30 de enero de 2007

Escuela Politécnica Superior, Campus de Leganés

Seminarios: del 11 al 15 de febrero de 2008

Escuela Politécnica Superior, Campus de Colmenarejo
Sesiones Finales: 17 y 18 de abril de 2008

Escuela Politécnica Superior, Campus de Leganés

Mesa redonda: The limits of Machine Learning

Sesión Inaugural

Fecha de celebración: 30 de Enero de 15:00 a 17:00

Lugar de celebración: Escuela Politécnica Superior, campus de Leganés, aula 7.1j06 (Información de acceso al campus)

Nombre del ponente: Francisco Martín, Doctor por la Univ. Politécnica de Cataluña, cofundador de la empresa ISOCO, fundador y Chief Executive Officer de la empresa MyStrands. EEUU.

Título del seminario: Presente y futuro de los Sistemas de recomendación
Breve resumen: Recommender Systems are applications of AI that provide personalized advice to users about products or services they might be interested in. Recommender Systems are playing a major role in the Digital and Social Networking Revolution and becoming a part of everyday life. They are helping people efficiently manage content overload and dive into the long tail of content discovery. The social prevalence of this can be evidenced by the evolution of, and demand for, personalized radio, television, video and on-line shopping. The seminar will bring together the concepts and practices of Recommender Systems and is intended for researchers (including Ph.D. students) who want to know about Recommender Systems and personalization advances. An in-depth introduction to Recommender Systems will be provided.

Los Seminarios

Fecha de celebración: Semana del 11 al 15 de febrero de 2008.

Lugar de celebración: Escuela Politécnica Superior, campus de Colmenarejo, residencia de estudiantes Antonio Machado, salón de grados. (Información de acceso al campus)

Los Ponentes de los Seminarios

Kalyanmoy Deb, is a Professor of Mechanical Engineering (Indian Institute Of Technology Kanpur) and the Director of the Kanpur Genetic Algorithms Laboratory (KanGAL) which he established in 1997. Prof. Deb received his Bachelor's degree from IIT Kharagpur (Mechanical Engg 1985). Before joining Alabama, Prof. Deb served with Engineers India Limited (New Delhi) between 1985 and 1987. He was also a Visiting Research Assistant Professor in the Department of General Engineering at the University of Illinois, Urbana Champaign between 1991 and 1992 and worked at Illinois Genetic Algorithms Laboratory (IlliGAL). Author of more than 150 research papers and two books, his latest book on Evolutionary Multiobjective Optimization Algorithms is the first ever compilation of multiobjective optimization algorithms. Professor Deb has organized several conferences and founder-chaired the First Conference on Evolutionary Multicriterion Optimization (EMO 2001) held at Zurich. His research has a practical bend, because of which many researchers and applicationists refer to his research. His NSGA-II paper from IEEE Trans. on Evolutionary Computation (2000) is judged as the Fast-Breaking Paper in Engineering by ESI Web of Science recently.

Institución: Indian Institute Of Technology Kanpur

Título del seminario: Practical Optimization Using Evolutionary Methods
Breve resumen: Many real-world problem solving tasks, involve posing and solving optimization problems, which are usually non-linear, non-differentiable, multi-dimensional, multi-modal, stochastic, and computationally time-consuming. We discuss a number of such practical problems which are, in essence, optimization problems and review the classical optimization methods to show that they are not adequate in solving such demanding tasks. On the other hand, in the past couple of decades, new yet practical optimization methods, based on natural evolutionary techniques, are increasingly found to be useful in meeting the challenges. These methods are population based, stochastic, and flexible, thereby providing an ideal platform to modify them to suit to solve most optimization problems. The breadth of their application domain and ease and efficiency of their working make evolutionary optimization methods promising for taking up the challenges offered by the vagaries of various practical optimization problems.

Material del seminario: descargar aquí

Michael Littman, directs the Rutgers Laboratory for Real-Life Reinforcement Learning (RL3) and his research in machine learning examines algorithms for decision making under uncertainty. After earning his Ph.D. from Brown University in 1996, Littman worked as an assistant professor at Duke University, a member of technical staff in AT&T's Artificial Intelligence Principles Research Department, and is now an associate professor of computer science at Rutgers. Both Duke and Rutgers honored him with teaching awards and his research has been recognized with three best-paper awards on the topics of meta-learning for computer crossword solving, complexity analysis of planning underuncertainty, and algorithms for efficient reinforcement learning. He has served as an associate editor for three major journals in his field.

Institución: Rutgers University

Título del seminario: Probabilistic Planning and Reinforcement Learning

Breve resumen:Through a combination of classic papers and more recent work, the course will explore automated decision making from a computer-science perspective. It will examine efficient algorithms, where they exist, for single agent and multiagent planning as well as approaches to learning near-optimal decisions from experience. Topics will include Markov decision processes, stochastic and repeated games, partially observable Markov decision processes, and reinforcement learning.

Material del seminario: descargar aquí

Luis Correia

Institución: Universidad de Lisboa

Título del seminario: Biologicaly Inspired Algorithms, Artificial Life and Self-Organisation

Breve resumen: This course will present an overview of computational models inspired by natural systems and by their processes. These models try to capture interesting properties of natural systems, such as self-organisation and robustness. Not only bio-inspired models are used for software development but also to produce embodied artifacts, which interact with the real world as artificial animals. Themes covered include evolutionary algorithms, artificial immune systems, neural networks, swarm models, behaviour based mobile robots. The course is organised in breadth instead of an in-depth study, in order to relate together all these models. It will be shown that, in all cases self-organisation is an underlying concept always present. The last part of the course will study natural self-organised systems, at different levels. Physical and chemical systems on one end and social systems on the other will be discussed. Finally, a few engineered solutions of self-organised systems will be presented.

Material del seminario: descargar aquí

Talbi El-Ghazali

Institución: Université des Sciences et Technologies de Lille

Title - Efficient metaheuristics: Application to networking and computational biology

Abstract: In this talk we will present our roadmap in developing efficient metaheuristics for combinatorial optimization problems. This roadmap is based on the landscape analysis of the problem, the design of hybrid metaheuristics, and their parallel implementation on grid computing platforms. Then, we will assess the performance of the presented approaches on some treated applications such as molecular structure prediction and docking, and network design problems.

Material del seminario: descargar aquí

Henrik Boström is professor of computer science with speciality in information fusion. His main research interests are at the intersection of information fusion and machine learning, as well as applications within chemo- and bio­infor­matics. He is co-director of the information fusion research program at University of Skövde (www.infofusion.se). He is on the editorial boards of Journal of Machine Learning Research, Journal of Intelligent Data Analysis, the Open Journal of Applied Informatics, and regularly on a number of program committees in these areas.
Institución: School of Humanities and Informatics, University of Skövde, Sweden

Title - Information Fusion for Predictive Data Mining

Abstract: Information fusion is a field that studies efficient methods for automatically or semi-automatically transforming information from different sources and different points in time into a representation that provides effective support for human or automated decision making. In this seminar, I will focus on information fusion for predictive data mining, i.e., how to combine information from multiple sources to obtain accurate predictive models. Strategies for fusing information prior to generating the models, as well as strategies for fusing generated models are presented. Results from experiments comparing these strategies will also be presented.

Material del seminario: descargar aquí

Horarios de Charlas y Ponencias

Nota: La ponencia de Henrik Boström será los días 17 y 18 de Abril. Las horas y lugar están todavía por determinar.

Asistencia de personal ajeno a la Universidad Carlos III de Madrid.

El seminario está abierto a toda la comunidad investigadora. Se pretende que sea un foro abierto a la discusión y la participación de todos aquellos interesados en la inteligencia artificial, incluyendo estudiantes, profesores, investigadores, y empresas interesadas en estas tecnologías.
La asistencia a los seminarios es gratuita. Además, se darán certificados de asistencia tras su finalización.

Becas de asistencia

Se ofertan, además, 10 becas de ayuda para la asistencia a estos seminarios para estudiantes de doctorado ajenos a la Universidad Carlos III de Madrid. Las becas incluyen la estancia en la residencia de estudiantes Antonio Machado de Colmenarejo donde se impartirá el seminario. Para solicitar estas becas, se debe enviar un correo a Fernando Fernández Rebollo (fernando.fernandez@uc3m.es), incluyendo la siguiente información:

• Carta describiendo el interés en la asistencia a este seminario

• Currículo del solicitante, incluyendo el programa de doctorado en el que está matriculado

Departamento de Informática
Universidad Carlos III de Madrid
Avenida de la Universidad 30
28911 Leganés, Madrid, España