Abstract
The present work addresses the issue of using complex networks as artificial intelligence mechanisms. More specifically, we consider the situation in which puzzles, represented as complex networks of varied types, are to be assembled by complex network processing engines of diverse structures. The puzzle pieces are initially distributed on a set of nodes chosen according to different criteria, including degree and eigenvector centrality. The pieces are then repeatedly copied to the neighboring nodes. The provision of buffering of different sizes are also investigated. Several interesting results are identified, including the fact that BA-based assembling engines tend to provide the fastest solutions. It is also found that the distribution of pieces according to the eigenvector centrality almost invariably leads to the best performance. Another result is that using the buffer sizes proportional to the degree of the respective nodes tend to improve the performance.
Graphical abstract
Similar content being viewed by others
References
E. Davis, G. Marcus, Artif. Intell. 233, 60 (2016)
M.A. Al-Nakhal, S.S. Abu Naser, Eur. Acad. Res. 4, 8770 (2017)
H.S. Fang, Y. Xu, W. Wang, X. Liu, S.C. Zhu, Learning pose grammar to encode human body configuration for 3D pose estimation, in Thirty-Second AAAI Conference on Artificial Intelligence, 2018
J. Schmidhuber, Neural Netw. 61, 85 (2015)
T.N. Sainath, B. Kingsbury, G. Saon, H. Soltau, A.R. Mohamed, G. Dahl, B. Ramabhadran, Neural Netw. 64, 39 (2015)
A.L. Barabási et al., Network Science (Cambridge University Press, Cambridge, 2016)
H.F. de Arruda, C.H. Comin, M. Miazaki, M.P. Viana, L. da Fontoura Costa, J. Neurosci. Methods 245, 1 (2015)
H.F. de Arruda, F.N. Silva, L. da Fontoura Costa, D.R. Amancio, Inf. Sci. 421, 154 (2017)
C.D. Brummitt, S. Chatterjee, P.S. Dey, D. Sivakoff et al., Ann. Appl. Probab. 25, 2013 (2015)
D. Stauffer, A. Aharony, L. da Fontoura Costa, J. Adler, Eur. Phys. J. B 32, 395 (2003)
C.J. Stam, Nat. Rev. Neurosci. 15, 683 (2014)
A.L. Barabási, R. Albert, Science 286, 509 (1999)
D.J. Watts, S.H. Strogatz, Nature 393, 440 (1998)
M.E. Newman, Phys. Rev. Lett. 89, 208701 (2002)
C.L. da Fontoura, O. Sporns, L. Antiqueira, N.M. das Graças Volpe, O.N. Oliveira Jr., Appl. Phys. Lett. 91, 054107 (2007)
C.H. Comin, M.P. Viana, L. da Fontoura Costa, New J. Phys. 15, 013048 (2013)
P.J. Souza, C.H. Comin, L. da Fontoura Costa, Europhys. Lett. 122, 26001 (2018)
M. Mitchell, Artif. Intell. 170, 1194 (2006)
T.C. Silva, L. Zhao, Inf. Sci. 294, 109 (2015)
J.R.B. Junior, N.M. do Carmo, L. Zhao, Neural Netw. 85, 69 (2017)
F. Breve, L. Zhao, Soft Comput. 17, 659 (2013)
R.F. i Cancho, R.V. Solé, Optimization in complex networks, in Statistical Mechanics of Complex Networks (Springer, Berlin, 2003), pp. 114–126
W. Du, M. Zhang, W. Ying, M. Perc, K. Tang, X. Cao, D. Wu, Appl. Math. Comput. 338, 33 (2018)
R. Tinós, L. Zhao, F. Chicano, D. Whitley, IEEE Trans. Evol. Comput. 22, 748 (2018)
M.G. Carneiro, R. Cheng, L. Zhao, Y. Jin, Neural Netw. 110, 243 (2019)
O. Sporns, From complex networks to intelligent systems, in Creating Brain-Like Intelligence (Springer, Berlin, 2009), pp. 15–30
E.B. Goldstein, J. Brockmole, Sensation and Perception (Cengage Learning, Belmont, 2016)
P. Erdos, A. Rényi, Publ. Math. Inst. Hung. Acad. Sci. 5, 17 (1960)
E. Ravasz, A.L. Barabási, Phys. Rev. E 67, 026112 (2003)
B.M. Waxman, IEEE J. Sel. Areas Commun. 6, 1617 (1988)
L. da Fontoura Costa, F.A. Rodrigues, G. Travieso, P.R. Villas Boas, Adv. Phys. 56, 167 (2007)
P. Bonacich, Am. J. Sociol. 92, 1170 (1987)
M. Newman, Networks: An Introduction (Oxford University Press, Oxford, 2010)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
de Arruda, H.F., Comin, C.H. & da F. Costa, L. Problem-solving using complex networks. Eur. Phys. J. B 92, 132 (2019). https://doi.org/10.1140/epjb/e2019-100100-8
Received:
Revised:
Published:
DOI: https://doi.org/10.1140/epjb/e2019-100100-8