[Neuroscience] Special Session on "Multi-objective Machine Learning" submission deadline extended

Yaochu.Jin at honda-ri.de Yaochu.Jin at honda-ri.de
Tue Jan 31 03:26:35 EST 2006

(Apologize if you receive multiple copies of this message.)

Call for Papers

Special Session on "Multi-objective Machine Learning"
2006 International Joint Conference on Neural Networks (part of WCCI'06)
July 16-21, Vancouver, Canada

Organized by Yaochu Jin (yaochu.jin at honda-ri.de)
URL: http://www.soft-computing.de/CFP_SS_MOML.html
The submission deadline has been extended to February 15, 2006

Motivation and Scope:

Machine learning usually has to achieve multiple targets, which are often
conflicting with each other.
For example in feature selection, minimizing the number of features and the
maximizing feature
quality are two conflicting objectives. It is also well realized that model
selection has to deal with
the trade-off between model complexity and approximation or classification
Traditional learning algorithms attempt to deal with multiple objectives by
combining them into a
scalar cost function so that multi-objective machine learning problems are
reduced to single-objective

Recently, increasing interest has been shown in applying Pareto-based
multi-objective optimization
to machine learning, particularly inspired by the successful developments
in evolutionary multi-objective
optimization. It has been shown that the multi-objective approach to
machine learning is particularly successful
in 1) improving the performance of the traditional single-objective machine
methods 2) generating highly diverse multiple Pareto-optimal models for
constructing ensembles and,
3) in achieving a desired trade-off between accuracy and interpretability
of neural networks or fuzzy systems.

This proposed special session intends to further promote research interests
in multi-objective machine learning
by presenting the most recent research results and discussing the main
challenges in this area. Topics include
but are not limited to

* multi-objective clustering, feature extraction and feature selection
* multi-objective model selection to improve the performance of learning
models, such as neural networks,
  support vector machines, decision trees, and fuzzy systems
* multi-objective model selection to improve the interpretability of
learning models, e.g., to extract
  symbolic rules from neural networks, or to improve the interpretability
of fuzzy systems
* multi-objective generation of learning ensembles
* multi-objective learning to deal with tradeoffs between plasticity and
stability, long-term and short-term
  memories, specialization and generalization
* multi-objective machine learning applications


All special session papers must be submitted no later than January 31, 2005
through the conference
webpage at Please choose
"S.Special Sessions,
Sa: Multi-objective machine learning" as your main research topic

More information about the Neur-sci mailing list

Send comments to us at biosci-help [At] net.bio.net