SS07: Bridging Machine Learning and Evolutionary Computation(ISICA 2021 Special Session)
Machine learning is to discover patterns and knowledge from existing data, and predict future events. By nature, many machine learning problems can be modelled as optimization problems, often with more than one conflicting objectives such as accuracy and complexity. It is also common that these problems have many locally optimal solutions. Traditional local optimization methods may not work well. For these reasons, evolutionary algorithms (EAs) have been widely used as an optimization tool in the field of machine learning in recent years. On the other hand, ideas and techniques from machine learning can be used in and hybridized with EAs. A good example is estimation of distribution algorithms. It should also be a very promising research direction to study optimization problems from the machine learning point of view.
Scope
This special session is intended to provide a forum for state-of-the-art research on the interdisciplinary work between EAs and machine learning. We solicit original contributions in, but not limited to, the following topics:
- Evolutionary algorithms using machine learning techniques and their applications.
- Machine learning algorithms using the ideas from Evolutionary algorithms.
- Evolutionary clustering, feature extraction and feature selection.
- Model selection by using evolutionary algorithms.
- Empirical and/or theoretical comparisons between evolutionary single objective and multiobjective machine learning techniques.
- New developments of EA techniques specialized for machine learning problems.
- Ensemble Machine Learning Methods based on evolutionary algorithms.
- Evolutionary multiobjective optimization techniques in machine learning.
- Applications of EAs and machine learning on bioinformatics, computational biology and other areas.
Organizers
Qingfu Zhang
City University of Hong Kong, China, qzhang@essex.ac.ukAimin Zhou
East China Normal University, China, amzhou@cs.ecnu.edu.cn