Aims and Scope
This Special Session focuses on using Evolutionary Computation for Automated Algorithm Design (EC4AAD), contrary to its twin AAD4EC: Automated Algorithm Design for Evolutionary Computation.
Computational intelligence systems play an imperative role in solving complex real-world problems in the industry. These systems have contributed to many facets of the industry, including data mining, transportation, health systems, computer vision, computer security, robotics, software engineering, and scheduling, amongst others. Computational intelligence systems employ one or more computational intelligence techniques such as neural networks, fuzzy logic, genetic algorithms, multi-agent approaches, and rule-based systems. Implementing these techniques requires a non-insignificant number of design decisions, e.g., what architecture to use, what parameter values to use, and the derivation of problem-specific operators. It may also be necessary to employ a hybrid system combining techniques to solve a problem, which introduces additional decisions such as which techniques to use and how to combine them. This makes the development of computational strategies time-consuming, requiring extensive expertise and many person-hours. Consequently, there have been many initiatives to automate these processes.
There has been a fair amount of research into parameter tuning and control. The field of Auto-Machine Learning aims to automate the design of machine learning algorithms to produce off-the-shelf machine learning techniques. Attempts to automate neural network architecture design have led to the field of Neuroevolution. Research in this area has also been directed at inducing fuzzy functions, rule-based systems, and multi-agent architectures. Hyper-heuristics, initially aimed at providing generalized solutions to combinatorial optimization problems, are proving to be effective in the automated development of techniques such as metaheuristics. These initiatives have chiefly used evolutionary algorithms such as genetic programming and genetic algorithms. Recent areas requiring investigation in the context of evolutionary algorithms for automated design include transfer learning and explainable artificial intelligence. Therefore, this special session aims to examine recent developments in the field and future directions, including the challenges and how these can be overcome.
List of Topics
The topics covered include, but are not limited to, the use of evolutionary algorithms for the following:
- Parameter control and tuning
- Architecture design, e.g., design of neural network and multi-agent architectures
- Automated hybridization of intelligent techniques
- Derivation of operators
- Derivation of construction heuristics
- Derivation of evaluation functions
- Automatic system development using hyper-heuristics
- Automatic programming
- Search-based software engineering
- Transfer learning
- Explainable artificial intelligence
- Metaheuristic Combination Optimization Problems
- Applications of automatic design systems
All submissions should follow the CEC2023 submission guidelines provided at IEEE CEC 2023 Submission Website. Special session papers are treated the same as regular conference papers. Please specify that your paper is for the Special Session on EC4AAD: Evolutionary Computation for Automated Algorithm Design. All papers accepted and presented at CEC 2023 will be included in the conference proceedings published by IEEE Explore.
Full or student registration of CEC 2023 is needed to participate in this special session.
The following dates have been taken from https://2023.ieee-cec.org/important-dates/:
January 27th, 2023
March 17th, 2023
April 7th, 2023
|Paper Final Notifications|
April 14th, 2023
April 29th, 2023
Jorge Mario Cruz Duarte
Tecnológico de Monterrey
University of Pretoria
Tecnológico de Monterrey