ePrints

Can computational efficiency alone drive the evolution of modularity in neural networks?

Lookup NU author(s): Dr Colin Tosh

Downloads

• Published version [.pdf]

Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).

Abstract

Some biologists have abandoned the idea that computational efficiency in processing multipart tasks or input sets alone drives the evolution of modularity in biological networks. A recent study confirmed that small modular (neural) networks are relatively computationally-inefficient but large modular networks are slightly more efficient than non-modular ones. The present study determines whether these efficiency advantages with network size can drive the evolution of modularity in networks whose connective architecture can evolve. The answer is no, but the reason why is interesting. All simulations (run in a wide variety of parameter states) involving gradualistic connective evolution end in non-modular local attractors. Thus while a high performance modular attractor exists, such regions cannot be reached by gradualistic evolution. Non-gradualistic evolutionary simulations in which multi-modularity is obtained through duplication of existing architecture appear viable. Fundamentally, this study indicates that computational efficiency alone does not drive the evolution of modularity, even in large biological networks, but it may still be a viable mechanism when networks evolve by non-gradualistic means.

Publication metadata

Author(s): Tosh CR

Publication type: Article

Publication status: Published

Journal: Scientific Reports

Year: 2016

Volume: 6

Online publication date: 30/08/2016

Acceptance date: 26/07/2016

Date deposited: 27/07/2016

ISSN (electronic): 2045-2322

Publisher: Nature Publishing Group

URL: http://dx.doi.org/10.1038/srep31982

DOI: 10.1038/srep31982

Altmetrics

Funding

Share