Why don't the modules dominate - Investigating the Structure of a Well-Known Modularity-Inducing Problem Domain

07/11/2018
by   Zhenyue Qin, et al.
0

Wagner's modularity inducing problem domain is a key contribution to the study of the evolution of modularity, including both evolutionary theory and evolutionary computation. We study its behavior under classical genetic algorithms. Unlike what we seem to observe in nature, the emergence of modularity is highly conditional and dependent, for example, on the eagerness of search. In nature, modular solutions generally dominate populations, whereas in this domain, modularity, when it emerges, is a relatively rare variant. Emergence of modularity depends heavily on random fluctuations in the fitness function, with a randomly varied but unchanging fitness function, modularity evolved far more rarely. Interestingly, high-fitness non-modular solutions could frequently be converted into even-higher-fitness modular solutions by manually removing all inter-module edges. Despite careful exploration, we do not yet have a full explanation of why the genetic algorithm was unable to find these better solutions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/15/2021

Resolving Anomalies in the Behaviour of a Modularity Inducing Problem Domain with Distributional Fitness Evaluation

Discrete gene regulatory networks (GRNs) play a vital role in the study ...
research
04/17/2017

The Emergence of Canalization and Evolvability in an Open-Ended, Interactive Evolutionary System

Natural evolution has produced a tremendous diversity of functional orga...
research
05/13/2022

Modularity in NEAT Reinforcement Learning Networks

Modularity is essential to many well-performing structured systems, as i...
research
03/28/2023

When to be critical? Performance and evolvability in different regimes of neural Ising agents

It has long been hypothesized that operating close to the critical state...
research
02/02/1999

A Discipline of Evolutionary Programming

Genetic fitness optimization using small populations or small population...
research
04/07/2021

Bootstrapping of memetic from genetic evolution via inter-agent selection pressures

We create an artificial system of agents (attention-based neural network...
research
05/16/2023

Capturing Emerging Complexity in Lenia

This research project investigates Lenia, an artificial life platform th...

Please sign up or login with your details

Forgot password? Click here to reset