Session:

MOD - Modularity, regularity and hierarchy in open-ended evolutionary computation

Title:

Evolving Large-Scale Modular Neural Networks

Authors:

Jae-Yoon Jung
James A. Reggia

Abstract:

Modularity is a major feature of biological central nervous systems. For example, the human/primate cerebral cortex is composed of dozens of structurally and functionally identifiable regions that are interconnected in a hierarchical network [1]. Motivated by this, our research group is studying the evolution and self-organization of modular neural networks. We are interested both in explaining the origin of modularity in biological systems, and in understanding the fundamental principles that govern the emergence of modular neural networks in general. There has been a substantial amount of past research in this area during the last decade, examining how modularity in neural networks evolves (e.g., [2{4]). Our own group initially focused on using genetic algorithms and multiobjective evolutionary optimization methods to evolve module parameters that influence acquisition of functionality in predefined modules during learning [5,6]. This past work was directed at explaining left-right asymmetries and hemispheric specialization in the brain.