The Effect of Connection Cost on Modularity in Evolved Neural Networks

Modularity, often observed in biological systems, does not easily arise in computational evolution. We explore the effect of adding a small fitness cost for each connection between neurons on the modularity of neural networks produced by the NEAT neuroevolution algorithm. We find that this connection cost does not increase the modularity of the best network produced by each run of the algorithm, but that it does lead to increased consistency in the level of modularity produced by the algorithm.

[1]  Herbert A. Simon,et al.  The Sciences of the Artificial , 1970 .

[2]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[3]  Adrian Thompson,et al.  Hardware evolution - automatic design of electronic circuits in reconfigurable hardware by artificial evolution , 1999, CPHC/BCS distinguished dissertations.

[4]  J. Hopfield,et al.  From molecular to modular cell biology , 1999, Nature.

[5]  Julian Francis Miller,et al.  Towards the automatic design of more efficient digital circuits , 2000, Proceedings. The Second NASA/DoD Workshop on Evolvable Hardware.

[6]  Hod Lipson,et al.  ON THE ORIGIN OF MODULAR VARIATION , 2002, Evolution; international journal of organic evolution.

[7]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[8]  Annie S. Wu,et al.  Effects of Module Encapsulation in Repetitively Modular Genotypes on the Search Space , 2004, GECCO.

[9]  Risto Miikkulainen,et al.  Competitive Coevolution through Evolutionary Complexification , 2011, J. Artif. Intell. Res..

[10]  Risto Miikkulainen,et al.  Evolving Reusable Neural Modules , 2004, GECCO.

[11]  M E J Newman,et al.  Finding and evaluating community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[12]  U. Alon,et al.  Spontaneous evolution of modularity and network motifs. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[13]  Günter P. Wagner,et al.  Complex Adaptations and the Evolution of Evolvability , 2005 .

[14]  Uri Alon,et al.  Varying environments can speed up evolution , 2007, Proceedings of the National Academy of Sciences.

[15]  U. Alon,et al.  Environmental variability and modularity of bacterial metabolic networks , 2007, BMC Evolutionary Biology.

[16]  Annie S. Wu,et al.  On the performance effects of unbiased module encapsulation , 2009, GECCO '09.

[17]  Charles Ofria,et al.  Investigating whether hyperNEAT produces modular neural networks , 2010, GECCO '10.

[18]  Kenneth O. Stanley,et al.  Constraining connectivity to encourage modularity in HyperNEAT , 2011, GECCO '11.

[19]  O. Sporns,et al.  The economy of brain network organization , 2012, Nature Reviews Neuroscience.

[20]  Hod Lipson,et al.  The evolutionary origins of modularity , 2012, Proceedings of the Royal Society B: Biological Sciences.

[21]  Fernando Silva,et al.  ALIFE 14 : Proceedings of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems , 2014 .