IEEE Symposium on Automated Algorithm Design, Configuration and Selection (IEEE AADCS)

Automated algorithm design, configuration and selection (AADCS) is a rapidly growing area which has a synergistic relationship with computational intelligence. AADCS has had an impact on computational intelligence while at the same time computational intelligence techniques has been essential for advancing the field of AADCS. 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 so as to produce off-the-shelf machine learning techniques. Attempts to automate neural network architecture design has 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, which were initially aimed at providing generalized solutions to combinatorial optimization problems, are proving to be effective in the automated development of techniques such as metaheuristics. Evolutionary algorithms such as genetic programming and genetic algorithms have chiefly been used in these initiatives. Recent areas that need investigation for automated design include transfer learning an explainable artificial intelligence. The aim of this special session is to examine recent developments in the field and future directions including the challenges and how these can be overcome.

Topics

Potential topics include, but are not limited to:

  • Parameter control and tuning
  • Algorithm selection
  • Model selection
  • Algorithm portfolios
  • Architecture design, e.g., design of neural network and multi-agent architectures
  • Hybridization of intelligent techniques
  • Operator creation
  • Heuristic generation
  • Feature selection
  • Derivation of evaluation functions
  • Automatic system development using hyper-heuristics
  • Automatic programming
  • Auto-ML
  • Automated hybridization of algorithms
  • Search-based software engineering
  • Neuroevolution
  • Theoretical aspects
  • Transfer learning
  • Explainable artificial intelligence

Symposium Chairs

  • Nelishia Pillay
    npillay@cs.up.ac.za
    University of Pretoria
  • Rong Qu
    Rong.Qu@nottingham.ac.uk
    University of Nottingham