AIMS AND SCOPE
Springer Link here
Modularity is a concept that is intuitively clear, yet it can be conceptually difficult to pin down because it appears in a multitude of forms in nature and technology. Thus, support for modularity is a central element in human attempts to build complex systems in general. Software would not scale without functions and objects, likewise electronic circuits and mechanical systems can only be constructed through extensive reuse of modules at different levels of selection. Viewed from this perspective, modules take the form of a `process view' in which the operation performed by each component remains consistent while the overall system complexity increases.
However, this need not be the only approach to defining modules. From a biological perspective, a structural view might imply that modules are components of a system with stronger connections, or components defined by more frequent (internal) interaction. Both process and structural views implicitly attempt to define modules in terms of the degree of autonomy versus integration. Another potentially important aspect of a module is how it contributes to the dynamics of the wider system's behaviour, and how its contribution may change over time. Moreover, modules might invoke other modules, or sequences of modules may be invoked depending on context, facilitating the interpretation of behaviours at steadily higher levels of abstraction.
This special issue invites new perspectives on the role of modularity in addressing issues such as scalability, reuse, and co-design in evolvable machines. We are particularly interested in submissions that illustrate advances to:
- Open ended development of hierarchical relationships between modules and/or
- Modular self-organization and emergence to achieve specific functional properties and/or
- Biological underpinnings of modularity in digital evolution of computer programs/evolvable machines.
We invite authors to submit works that illustrate the impact of modularity and self-organization on the ability to discover genotype/phenotypes more efficiently or improve the efficiency of operation. To this end, ongoing themes include mechanisms by which communication, ensembles, and cellular automata enable modules to develop or interact. Another related topic is the role of modularity on improving interpretability, where specific decision-making processes might be associated with particular modules.
Environments that demonstrate the importance of modularity are also of interest and might include multi-task learning or situations in which catastrophic forgetting plays a role.
We also invite submissions that illustrate how co-design or co-evolution may result in better use of modules, or to what degree decomposing a task facilitates the organization of behavioural properties through module reuse.
TOPICS OF INTEREST
- efficiency of operation
- compartmentalizing credit assignment such that only specific modules are refined / catastrophic forgetting is mitigated
- emergence of individual versus group behaviours and their co-ordination
- hierarchical relationships versus ensembles or teams, and major transitions
- generalization, robustness, and evolvability
- automatic feature selection, feature construction and/or interpretability
- hardware acceleration, microarchitectures, and cyber-physical systems
- self organization, complexity, and emergence of modularity
- organization and development of units of selection
- the co-design or co-evolution of effective modularity
- distributed and/or shared memory versus individual internal state
- cycles of interaction between modules or internal / external state
IMPORTANT DATES
- Submission deadline: December 15, 2026
- Notification of first review: January 26, 2027
- Submission of revised manuscript: March 26, 2027
- Notification of final decision: April 26, 2027
GUEST EDITORS
- Stephen Kelly, McMaster University, Hamilton, Canada, spkelly@mcmaster.ca
- Malcolm Heywood, Dalhousie University, Halifax, Canada, mheywood@dal.ca
