Evolutionary algorithms, based on the Darwinian theory of evolution and Mendelian theory of genetic processes and swarm algorithms (based on the emergent behavior of natural swarms), are popular and widely used for solving various optimization tasks. These algorithms, in general, are subject to hybridization with various techniques that improve their performance and/or help to analyze and better understand their inner dynamics, which can be complex and even often chaotic or exhibiting various interesting patterns. Currently, many researchers are investigating performance, efficiency, convergence speed, population diversity, and dynamics, and developing original population models and visualization methods for a broad class of swarm and evolutionary algorithms.
This special session is focused on the classical evolutionary computing techniques (Genetic algorithms (GA), Differential evolution (DE), …), swarm intelligence algorithms, like Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Firefly, Self-Organizing Migrating Algorithm (SOMA), and more original algorithms that were not created only based on the metaphors, but that were built on a solid foundation of balancing between exploration and exploitation, techniques to prevent stagnation in local extremes, competitive-cooperative phases, self-adaptation of movement over the search space, and more. Thus, defining the overlap between SIS and SDE symposiums.
This special session aims to bring together experts from fundamental research and various application fields to enable a fusion of a broad spectrum of novel methods, facilitate deeper insights into population dynamics, and propose original visualization approaches for evolutionary and swarm methods. Such research has become a vitally important part of science and engineering at the theoretical and practical levels. Also, a discussion of real-world problem-solving experiences will be carried out to define new open problems and challenges in this interesting and fast-growing field of research that is currently undergoing re-exploration of methods due to neuro-evolution. We encourage the submission of performance improving techniques based on population dynamic analysis and tested on widely accepted benchmark tests. The scope will be focused on, but not limited to, the below-listed topics.
List of topics:
- Population dynamics analysis for swarm/evolutionary algorithms.
- Boundary and constraints handling strategies.
- Visualization of population dynamics.
- Visualization of fitness landscape and relation with algorithm performance.
- Population diversity measure, control and analysis.
- Complex systems for swarm/evolutionary algorithms.
- Original models of population dynamics.
- Mutual relations amongst swarm/evolutionary dynamics, complex networks and its analysis.
- Evolutionary dynamics as a feedback loop system, analysis and control.
- Randomness, chaos and fractals in evolutionary dynamics and its impact on algorithmperformance.
- Recent advances in better understanding, fine tuning, adaptation forswarm/evolutionary algorithms.
- Control and explainability through visualisation in swarm/evolutionary computation.
- Search space characterisation and population dynamics visualisation.
Organizers: Roman Senkerik, Michal Pluhacek, Pavel Kromer