Scaling up the self-optimization model by means of on-the-fly computation of weights

The Self-Optimization (SO) model is a useful computational model for investigating self-organization in “soft” Artificial life (ALife) as it has been shown to be general enough to model various complex adaptive systems. So far, existing work has been done on relatively small network sizes, precluding the investigation of novel phenomena that might emerge from the complexity arising from large numbers of nodes interacting in interconnected networks. This work introduces a novel implementation of the SO model that scales as $\mathcal{O}(N^{2})$ with respect to the number of nodes N, and demonstrates the applicability of the SO model to networks with system sizes several orders of magnitude higher than previously was investigated. Removing the prohibitive computational cost of the naive $\mathcal{O}(N^{3})$ algorithm, our on-the-fly computation paves the way for investigating substantially larger system sizes, allowing for more variety and complexity in future studies.

[1]  I. Shpurov,et al.  Combining Self-critical dynamics and Hebbian learning to explain utility of bursty dynamics in neural networks , 2021, IEEE Symposium Series on Computational Intelligence.

[2]  I. M. de la Fuente,et al.  Self-Organization and Information Processing: From Basic Enzymatic Activities to Complex Adaptive Cellular Behavior , 2021, Frontiers in Genetics.

[3]  Tom Froese,et al.  The distribution of inhibitory neurons in the C. elegans connectome facilitates self-optimization of coordinated neural activity , 2020, 2020 IEEE Symposium Series on Computational Intelligence (SSCI).

[4]  Tom Froese,et al.  Unsupervised Learning Facilitates Neural Coordination Across the Functional Clusters of the C. elegans Connectome , 2020, Frontiers in Robotics and AI.

[5]  Tom Froese,et al.  Self-optimization in a Hopfield neural network based on the C. elegans connectome , 2019, Artificial Life Conference Proceedings.

[6]  Justin Werfel,et al.  Self-Organization and Artificial Life , 2019, Artificial Life.

[7]  Tom Froese,et al.  Modeling collective rule at ancient Teotihuacan as a complex adaptive system: Communal ritual makes social hierarchy more effective , 2018, Cognitive Systems Research.

[8]  Tom Froese,et al.  Self-Optimization in Continuous-Time Recurrent Neural Networks , 2018, Front. Robot. AI.

[9]  Jiahao Chen,et al.  Robust benchmarking in noisy environments , 2016, ArXiv.

[10]  Eörs Szathmáry,et al.  What can ecosystems learn? Expanding evolutionary ecology with learning theory , 2015, Biology Direct.

[11]  Tom Froese,et al.  Can Government Be Self-Organized? A Mathematical Model of the Collective Social Organization of Ancient Teotihuacan, Central Mexico , 2014, PloS one.

[12]  Tom Froese,et al.  Neural coordination can be enhanced by occasional interruption of normal firing patterns: A self-optimizing spiking neural network model , 2014, Neural Networks.

[13]  Chun Wong,et al.  Modeling complex systems with adaptive networks , 2013, Comput. Math. Appl..

[14]  Richard A. Watson,et al.  Global Adaptation in Networks of Selfish Components: Emergent Associative Memory at the System Scale , 2011, Artificial Life.

[15]  Jason Noble,et al.  “If You Can't Be With the One You Love, Love the One You're With”: How Individual Habituation of Agent Interactions Improves Global Utility , 2011, Artificial Life.

[16]  Richard A. Watson,et al.  Transformations in the scale of behavior and the global optimization of constraints in adaptive networks , 2011, Adapt. Behav..

[17]  Richard A. Watson,et al.  Optimization in "self-modeling" complex adaptive systems , 2011, Complex..

[18]  Eörs Szathmáry,et al.  The Neuronal Replicator Hypothesis , 2010, Neural Computation.

[19]  Richard A. Watson,et al.  Symbiosis Enables the Evolution of Rare Complexes in Structured Environments , 2009, ECAL.

[20]  Richard A. Watson,et al.  The Effect of Hebbian Learning on Optimisation in Hopfield Networks , 2009 .

[21]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[22]  Tom Froese,et al.  Self-modeling in Hopfield Neural Networks with Continuous Activation Function , 2017, BICA.

[23]  Kerstin M. Mueller,et al.  Dynamic Patterns: The Self-Organization of Brain and Behavior , 1995 .

[24]  Richard A. Watson,et al.  Emergent associative memory as a local organising principle for global adaptation in adaptive networks , 2011 .

[25]  Richard A. Watson,et al.  Associative Memory in Gene Regulation Networks , 2010, ALIFE.

[26]  F. Attneave,et al.  The Organization of Behavior: A Neuropsychological Theory , 1949 .