24th International Workshop on Learning Classifier Systems
(IWLCS 2021)

Aims and Scope of IWLCS

Learning Classifier Systems (LCSs) are a class of powerful Evolutionary Machine Learning (EML) algorithms that combine the global search of evolutionary algorithms with the local optimization of reinforcement or supervised learning. They form predictions by combining an evolving set of localized models each of which is responsible for a part of the problem space. While the localized models themselves are trained using machine learning techniques ranging from simple adaptive filters to more complex ones such as artificial neural networks, their responsibilities are optimized by powerful heuristic such as GAs.

Over the last four decades, LCSs have shown great potential in various problem domains such as behaviour modelling, online control, function approximation, classification, prediction and data mining. Their unique strengths lie in their adaptability and flexibility, them making only a minimal set of assumptions and, most importantly, their transparency. Topics that have been central to LCS for many years are more and more becoming a matter of high interest for other machine learning communities as well these days; the prime example is an increase in human interpretability of generated models which especially the booming Deep Learning community is keen on obtaining (Explainable AI). This workshop serves as a critical spotlight to disseminate the long experience of LCS research in these areas, to present new and ongoing research in the field, to attract new interest and to expose the machine learning community to an alternative, often advantageous, modelling paradigm. Particular topics of interest are (not exclusively):

  • advances in LCS methods (local models, problem space partitioning, classifier mixing, …)

  • evolutionary reinforcement learning (multi-step LCS, neuroevolution, …)

  • state of the art analysis (quantitative/qualitative surveys, carefully crafted comparative experimental benchmarks, …)

  • formal developments in LCSs (provably optimal parametrization, time bounds, generalization, …)

  • interpretability of evolved knowledge bases (knowledge extraction, visualization, …)

  • advances in LCS paradigms (Michigan/Pittsburgh style, hybrids, iterative rule learning, …)

  • hyperparameter optimization (hyperparameter selection, online self-adaptation, …)

  • applications (medical domains, bio-informatics, intelligence in games, cyber-physical systems, …)

  • optimizations and parallel implementations (GPU acceleration, matching algorithms, …)

  • other evolutionary rule-based ML systems (artificial immune/evolving fuzzy rule-based systems, …)

Deadlines

Submission deadline: 12 April 2021

Decisions due: 26 April 2021

Camera-ready version: 3 May 2021

Early and mandatory author registration deadline: 3 May 2021


Submission Information

Papers are expected to report on innovative ideas and novel research results around the topic of LCS and general Evolutionary Rule-based Machine Learning (ERBML). Reported results and findings have to be integrated with the current state of the art and should provide details and metrics allowing for an assessment of practical as well as statistical significance. Contributions bringing in novel ideas and concepts from related fields such as general ML and EC are explicitly solicited but authors are at the same time strongly encouraged to clearly state the relevance and relation to the field of LCS and ERBML.

Submissions must

Organization Committee

David Pätzel

University of Augsburg (DE)

david.paetzel@informatik.uni-augsburg.de

David Pätzel is a PhD student at the Department of Computer Science at the University of Augsburg, Germany. He received his B.Sc. in Computer Science from the University of Augsburg in 2015 and his M.Sc. in the same field in 2017. His main research is directed towards Learning Classifier Systems with a focus on developing a more formal, probabilistic understanding of LCSs such as XCS(F) that can, for example, be used to improve existing algorithms. Besides that, his research interests include evolutionary machine learning algorithms, reinforcement learning and pure functional programming. He is an elected organizing committee member of the International Workshop on Learning Classifier Systems since 2020.

Alexander Wagner

University of Hohenheim (DE)

a.wagner@uni-hohenheim.de

Alexander Wagner is a PhD student at the Department of Artificial Intelligence in Agricultural Engineering at the University of Hohenheim, Germany. He received his B.Sc. and M.Sc. degrees in computer science from the University of Augsburg in 2018 and 2020, respectively. His bachelor’s thesis already dealt with the field of Learning Classifier Systems. This sparked his interest and he continued working on Learning Classifier Systems, especially XCS, during his master studies. Consequently, he also dedicated his master’s thesis to this topic in greater depth. His current research focuses on the application of Learning Classifier Systems, in particular XCS and its derivatives, to self-learning adaptive systems designed to operate in real-world environments, especially in agricultural domains. In this context, the emphasis of his research is to increase reliability of XCS or LCS in general. His research interests also include reinforcement learning, evolutionary machine learning algorithms, neural networks and neuro evolution.

Michael Heider

University of Augsburg (DE)

michael.heider@informatik.uni-augsburg.de

Michael Heider is a PhD student at the Department of Computer Science at the University of Augsburg, Germany. He received his B.Sc. in Computer Science from the University of Augsburg in 2016 and his M.Sc. in Computer Science and Information-oriented Business Management in 2018. His main research is directed towards Learning Classifier Systems, especially following the Pittsburgh style, with a focus on regression tasks encountered in industrial settings. Those have a high regard for both accurate as well as comprehensive solutions. To achieve comprehensibility he focuses on compact and simple rule sets. Besides that, his research interest include optimization techniques and unsupervised learning (e.g. for data augmentation or feature extraction).

Advisory Board

  • Jaume Bacardit, Newcastle University, UK

  • Will N. Browne, Victoria University of Wellington, New Zealand

  • Martin V. Butz, University of Tübingen, Germany

  • John Holmes, University of Pennsylvania, US

  • Muhammad Iqbal, Higher Colleges of Technology/Xtracta, United Arab Emirates

  • Pier Luca Lanzi, Politecnico Di Milano, Italy

  • Masaya Nakata, Yokohama National University, Japan

  • Kamran Shafi, University of New South Wales, Australia

  • Anthony Stein, University of Hohenheim, Germany

  • Wolfgang Stolzmann, CMORE Automotive, Germany

  • Ryan J. Urbanowicz, University of Pennsylvania, US

  • Stewart W. Wilson, Prediction Dynamics, US

Program Committee

  • Jaume Bacardit, Newcastle University, UK

  • Lashon B. Booker, The MITRE Corporation, US

  • Will N. Browne, Queensland University of Technology, Australia

  • Larry Bull, The University of the West of England, UK

  • Michael Heider, University of Augsburg, Germany

  • Luis Miramontes Hercog, University of Notre Dame, US

  • Karthik Kuber, Loblaw Companies Limited/York University, Canada, Canada

  • Masaya Nakata, Yokohama National University, Japan

  • Yusuke Nojima, Osaka Prefecture University, Japan

  • David Pätzel, University of Augsburg, Germany

  • Sonia Schulenburg, Level E Research, UK

  • Shinichi Shirakawa, Yokohama National University, Japan

  • Anthony Stein, University of Hohenheim, Germany

  • Sven Tomforde, Kiel University, Germany

  • Ryan J. Urbanowicz, University of Pennsylvania, US

  • Danilo Vasconcellos Vargas, Kyushu University, Japan

  • Alexander Wagner, University of Hohenheim, Germany