Scalable optimization via probabilistic modeling: From algorithms to applications

SOPM

The book “Scalable Optimization via Probabilistic Modeling: From Algorithms to Applications” edited by Martin Pelikan, Kumara Sastry, and Erick Cantu-Paz has just been published by Springer.

Estimation of distribution algorithms combine evolutionary computation and machine learning to provide a class of robust and scalable optimization techniques applicable to broad classes of difficult problems. Scalable optimization via Probabilistic Modeling compiles articles by some of the leading experts in academia and industry that range from design and analysis to efficiency enhancement and real-world applications of estimation of distribution algorithms. The book is written for the general audience and should be of interest for optimization researchers and practitioners alike.A sample chapter can be downloaded here and more Information can be found at http://medal.cs.umsl.edu/scalable-optimization-book/

E2K: Evolution to knowledge

Evolution to Knowledge (E2K) is a set of Data to Knowledge (D2K) modules and itineraries that perform genetic algorithms (GA) and genetics-based machine learning (GBML) related tasks. The goal of E2K is to fold: simplify the process of building GA/GBML related tasks, and provide a simple exploratory workbench for the evolutionary computation community to help users to interact with evolutionary processes. It can help to create complex tasks or help the newcomer to get familiarized and trained with the evolutionary methods and techniques provided. Moreover, due to its integration into D2K, the creation of combined data mining and evolutionary task can be effortlessly done via the visual programming paradigm provided by the workflow environment and also wrap other evolutionary computation software.

E2K targets the creation of a common shared framework for the evolutionary computation community. E2K allows users to reuse evolutionary components and, using a visual programming paradigm, connect them to create applications that fulfill the targeted needs. E2K is a project built around the D2K framework developed by the Automated Learning Group at the National Center for Supercomputing Applications. D2K’s dataflow architecture provides users with a simple workbench where they can rapidly create applications visually by just dragging and connecting components (modules) together. E2K modules provide simple computation activities—such as evaluation, selection, and recombination mechanism—that when combined together create complex evolutionary computation algorithms. Due to the module standardization in D2K, it can act as integrator of evolutionary techniques and library—for instance wrapping ECJ or Open BEAGLE components—and also take advantage of the data mining techniques provided with the D2K.

IWLCS 2007 organizers

Finally, we finished the pool process to get the organizers for IWLCS 2007. The next three volunteers that will be forming the organizing committee are:

Please join us welcoming them and encouraging them while taking the challenge of keeping IWLCS moving forward and expanding its reach. The advisory committee is now formed by

IWLCS 2007: Call for organizers

Dear colleagues,

The term for Tim Kovacs, Xavier Llorà, and Keiki Takadama as organizers of the International Workshop on Learning Classifier Systems is over. For the last two years we have organized the workshop and we have put together a book that covers 2003, 2004, and 2005 workshops (soon to enter the printing stage).

We have greatly enjoyed working with you all. Your friendship and help has motivated and guide us maintain alive the great effort that Pier Luca Lanzi, Stewart Wilson, and Wolfgang Stolzman started in 1999.

We would humbly put out this call for organizer for IWLCS 2007. For those of you that have been with us in the workshops, please, do not be afraid and volunteer. We would encourage you to get in touch with us before August 1st. Just sent and email to any of us (Tim Kovacs, Xavier Llorà, and Keiki Takadama). We would announce the next organizing committee by September 1st.

Thank you all for all the support during this two-year period!
Tim, Xavier, Keiki.

Slides of the presentations of IWLCS 2006

Here you can find the slides of the presentations done at the Ninth International Workshop on Learning Classifier Systems (IWLCS 2006).

  • Empirical evaluation of ensemble techniques for a Pittsburgh Learning Classifier System, Jaume Bacardit, Natalio Krasnogor. [Download PDF]
  • The Χ-ary Extended Compact Classifier System: Linkage Learning in Pittsburgh LCS, Xavier Llorà, Kumara Sastry, David E. Goldberg, Luis delaOssa. [Download PDF]
  • An Initial Analysis of Parameter Sensitivity for XCS with Computed Prediction, Pier Luca Lanzi, Matteo Zanini.
  • Improving Classifier Error Estimate in XCSF, Daniele Loiacono, Jan Drugowitsch, Alwyn Barry, Pier Luca Lanzi. [Download PDF]
  • Dual-structured Classifier System Mediating XCS and Gradient Descent based Update, Atsushi Wada, Keiki Takadama, Katsunori Shimohara. [Download PDF]
  • A Further Look at UCS Classifier System, Albert Orriols-Puig, Ester Bernadó-Mansilla. [Download PPT]
  • Using XCS for Action Selection in RoboCup Rescue Simulation League, Ivette C. Martínez, David Ojeda, Ezequiel Zamora. [Download PDF]
  • Community of Practice under Learning Classifier Systems, Yutaka I. Leon Suematsu, Keiki Takadama, Katsunori Shimohara, Osamu Katai. [Download PDF]
  • Technology Extraction for Future Generations from Process Time Series Data Reflecting Expert Operator Skills, Setsuya Kurahashi, Takao Terano. [Download PDF]
  • An Artificial Life Classifier System for Real-Valued Inputs, Julian Bishop. [Download PDF]
  • Developing Conversational Interfaces with XCS, Dave Toney, Johanna Moore, Oliver Lemon. [Download PDF]

The Ninth International Workshop on Learning Classifier Systems (IWLCS 2006) is here!

The schedule for the Ninth International Workshop on Learning Classifier Systems (IWLCS’2006) is ready. We are getting together on July 9 during the GECCO 2006 Workshops. Here is the timetable. Each presentation may last for 25 minutes for the oral presentation plus five minutes for question. We are looking forward to meet you all there!

Timetable

  • 9:10 -9:20: Opening remarks. Chair: Tim Kovacs.
  • 9:20-10:20:Pittsburgh Approach Session. Chair: Tim Kovacs.

    • 9:20- 9:50: Empirical evaluation of ensemble techniques for a Pittsburgh Learning Classifier System, Jaume Bacardit, Natalio Krasnogor.
    • 9:50-10:20: The Chi-ary Extended Compact Classifier System: Linkage Learning in Pittsburgh LCS, Xavier Llorà, Kumara Sastry, David E. Goldberg, Luis delaOssa.
  • 10:20-10:40: Break 20 minutes.
  • 10:40-12:40: Method and Analysis. Chair: Xavier Llorà.

    • 10:40-11:10: An Initial Analysis of Parameter Sensitivity for XCS with Computed Prediction, Pier Luca Lanzi, Matteo Zanini.
    • 11:10-11:40: Improving Classifier Error Estimate in XCSF, Daniele Loiacono, Jan Drugowitsch, Alwyn Barry, Pier Luca Lanzi.
    • 11:40-12:10: Dual-structured Classifier System Mediating XCS and Gradient Descent based Update, Atsushi Wada, Keiki Takadama, Katsunori Shimohara.
    • 12:10-12:40: A Further Look at UCS Classifier System, Albert Orriols-Puig, Ester Bernado-Mansilla.
  • 12:40-14:20: Lunch break [NOTE: 10 minutes later + 10 minutes addition in comparison with the workshop schedule posted at the GECCO WEB page]
  • 14:20-15:50: Distributed and Multiagent System. Chair: Keiki Takadama.

    • 14:20-14:50: Using XCS for Action Selection in RoboCup Rescue Simulation League, Ivette C. Martinez, David Ojeda, Ezequiel Zamora.
    • 14:50-15:20: Community of Practice under Learning Classifier Systems, Yutaka I. Leon Suematsu, Keiki Takadama, Katsunori Shimohara, Osamu Katai.
    • 15:20-15:50: Technology Extraction for Future Generations from Process Time Series Data Reflecting Expert Operator Skills, Setsuya Kurahashi, Takao Terano.
  • 15:50-16:10: Break 20 minutes
  • 16:10-17:10: Advanced Architecture. Chair: Tim Kovacs.

    • 16:10-16:40: An Artificial Life Classifier System for Real-Valued Inputs, Julian Bishop.
    • 16:40-17:10: Developing Conversational Interfaces with XCS, Dave Toney, Johanna Moore, Oliver Lemon.
  • 17:10-17:50: Open Discussion.
  • 17:50-18:00: Closing remarks.

NCSA/IlliGAL Gathering on Evolutionary Learning (NIGEL’2006)

On May 16th and 17th, a group formed by more than twenty researchers got together in Urbana-Champaign (Illlinois) to participate in the gathering on evolutionary learning organized by the National Center for Supercomputer Applications and the Illinois Genetic Algorithms Laboratory (NIGEL 2006). The goals were to discus current state-of-the-art research in learning classifier systems and other genetics-based machine learning, and to identify future research trends and applications where evolutionary learning might provide a competitive advantage. The first day attendees gave presentations about challenges and current research topics (see the materials below). The second day, a series of three topic-oriented brainstorming sessions were conducted covering: (1) future of LCS and other GBML, (2) areas of application, and (3) techniques.

The list of participants included Loretta Auvil, Jaume Bacardit, Alwyn Barry, Lashon Booker, Ester Bernado, Will Browne, Martin Butz, Jorge Casillas, Helen Dam, Dipankar Dasgupta, Deon Garrett, David Goldberg, Noriko Imafuji, Pier Luca Lanzi, Xavier Llora, Kumara Sastry, Kamran Shafi, Kenneth Turvey, Michael Welge, Ashley Williams, Stewart Wilson, and Paul Winward.

Presentations slides and videos of the presentations

Some pictures of the event can be found here or at the NIGEL web site.

Xavier Llorà: “Welcome and presentation”[Slides]
Stewart W. Wilson: “Can We Do Captchas?” [Slides]
David E. Goldberg: “Searle, Intentionality, and the Future of Classifier Systems” [Slides]
Dipankar Dasgupta: “Artificial Immune Systems in Anomaly Detection” [Slides]
Lashon Booker: “A Retrospective Look at Classifier System Research” [Slides]
Martin Butz: “XCS: Current Capabilities and Future Challenges” [Slides]
Alwyn Barry: “Towards a Formal Framework for Accuracy-based LCS” [Slides]
Xavier Llorà: “Linkage Learning for Pittsburgh Learning Classifier Systems: Making Problems Tractable” [Slides]
Jorge Casillas: “Scalability in GBML, Accuracy-Based Michigan Fuzzy LCS, and New Trends” [Slides]
Ester Bernadó: “Learning Classifier Systems for Unbalanced Datasets” [Slides]
Pier-Luca Lanzi: “Computed Prediction: so far, so good. Now what?” [Slides]
Jaume Bacardit: “Pittsburgh Learning Classifier Systems for Protein Structure Prediction: Scalability and Explanatory Power” [Slides]

NCSA/IlliGAL Gathering on Evolutionary Learning (NIGEL’2006)

On May 16th and 17th, a group formed by more than twenty researchers got together in Urbana-Champaign (Illlinois) to participate in the gathering on evolutionary learning organized by the National Center for Supercomputer Applications and the Illinois Genetic Algorithms Laboratory (NIGEL 2006). The goals were to discus current state-of-the-art research in learning classifier systems and other genetics-based machine learning, and to identify future research trends and applications where evolutionary learning might provide a competitive advantage. The first day attendees gave presentations about challenges and current research topics (see the materials below). The second day, a series of three topic-oriented brainstorming sessions were conducted covering: (1) future of LCS and other GBML, (2) areas of application, and (3) techniques.

The list of participants included Loretta Auvil, Jaume Bacardit, Alwyn Barry, Lashon Booker, Ester Bernado, Will Browne, Martin Butz, Jorge Casillas, Helen Dam, Dipankar Dasgupta, Deon Garrett, David Goldberg, Noriko Imafuji, Pier Luca Lanzi, Xavier Llora, Kumara Sastry, Kamran Shafi, Kenneth Turvey, Michael Welge, Ashley Williams, Stewart Wilson, and Paul Winward.

Presentations slides and videos of the presentations

Some pictures of the event can be found here or at the NIGEL web site.

Xavier Llorà: “Welcome and presentation”[Slides][Video]
Stewart W. Wilson: “Can We Do Captchas?” [Slides][Video]
David E. Goldberg: “Searle, Intentionality, and the Future of Classifier Systems” [Slides][Video]
Dipankar Dasgupta: “Artificial Immune Systems in Anomaly Detection” [Slides][Video]
Lashon Booker: “A Retrospective Look at Classifier System Research” [Slides][Video]
Martin Butz: “XCS: Current Capabilities and Future Challenges” [Slides][Video]
Alwyn Barry: “Towards a Formal Framework for Accuracy-based LCS” [Slides][Video]
Xavier Llorà: “Linkage Learning for Pittsburgh Learning Classifier Systems: Making Problems Tractable” [Slides][Video]
Jorge Casillas: “Scalability in GBML, Accuracy-Based Michigan Fuzzy LCS, and New Trends” [Slides][Video]
Ester Bernadó: “Learning Classifier Systems for Unbalanced Datasets” [Slides][Video]
Pier-Luca Lanzi: “Computed Prediction: so far, so good. Now what?” [Slides][Video]
Jaume Bacardit: “Pittsburgh Learning Classifier Systems for Protein Structure Prediction: Scalability and Explanatory Power” [Slides][Video]

List of papers to be presented at IWLCS 2006

This is the list of papers accepted for presentation at IWLCS 2006 that will take place during GECCO 2006.

  • Empirical evaluation of ensemble techniques for a Pittsburgh Learning Classifier System
    Bacardit, J. and Krasnogor, N.
  • An Artificial Life Classifier System for Real-Valued Inputs
    Bishop, J.
  • Technology Extraction for Future Generations from Process Time Series Data Reflecting Expert Operator Skills
    Kurahashi, S. and Terano, T.
  • An Initial Analysis of Parameter Sensitivity for XCS with Computed Prediction
    Lanzi, P.L., and Zanini, M.
  • The χ-ary Extended Compact Classifier System: Linkage Learning in Pittsburgh LCS
    Llorà, X., Sastry, K., Goldberg, D.E., and delaOssa, L.
  • Using XCS for Action Selection in RoboCup Rescue Simulation League
    Martínez, I. C., Ojeda, D., and Zamora, E.
  • Extending XCS with Representation in First-Order Logic
    Mellor, D.
  • A Further Look at UCS Classifier System
    Orriols-Puig, A., Bernad&oaccute;-Mansilla, E.
  • Agent-Based Learning Classifier Systems for Grid Data Mining
    Santos, M.F, Quintela, H., and Neves, J.
  • Community of Practice under Learning Classifier Systems
    Suematsu, Y.I.L., Takadama, K., Shimohara, K., and Katai, O.
  • Developing Conversational Interfaces with XCS
    Toney, D., Moore, J., and Lemon, O.
  • Dual-structured Classifier System Mediating XCS and Gradient Descent based Update
    Wada, A., Takadama, K., and Shimohara, K.