Abstract
Complex networks like the scale-free model proposed by Barabasi-Albert are observed in many biological systems and the application of this topology to artificial neural network leads to interesting considerations. In this paper, we present a preliminary study on how to evolve neural networks with complex topologies. This approach is utilized in the problem of modeling a chemical process with the presence of unknown inputs (disturbance). The evolutionary algorithm we use considers an initial population of individuals with differents scale-free networks in the genotype and at the end of the algorithm we observe and analyze the topology of networks with the best performances. Experimentation on modeling a complex chemical process shows that performances of networks with complex topology are similar to the feed-forward ones but the analysis of the topology of the most performing networks leads to the conclusion that the distribution of input node information affects the network performance (modeling capability).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Yao, X.: Evolving Artificial Neural Networks. Proceedings of the IEEE 87(9), 1423–1447 (1999)
Alander, J.T.: An indexed bibliography of genetic algorithms and neural networks, Technical Report 94-1-NN, University of Vaasa, Department of Information Technology and Production Economics (1998)
Cant-Paz, E., Kamath, C.: An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems. IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics, 915–927 (2005)
Watts, D.J., Strogatz, S.: Collective dynamics of ’small-world’ networks. Nature 393(6684), 440–442 (1998)
Burns, G.A.P.C., Oung, M.P.Y: Analysis of the connectional organization of neural systems associated with the hippocampus in rats. Philosophical Transactions of the Royal Society B: Biological Sciences 355(1393), 55–70 (2000)
Eguiluz, V.M., Chialvo, D.R., Cecchi, G.A., Baliki, M., Apkarian, A.V.: Scale-Free Brain Functional Networks. Phys. Rev. Lett. 94, 18–102 (2005)
Dorogotvsev, S.N., Mendes, J.F.F.: Evolution of Networks. Advances in Physics 51(4), 1079–1187 (2002)
Barabasi, A.-L., Albert, R.: Emergence of scaling in random networks. Science 286, 509–512 (1999)
Erdos, P., Renyi, A.: On random graphs, Publ. Math. Debrecen (1959)
Watts, D.J.: Small Worlds: The Dynamics of Networks Between Order and Randomness. Princeton University Press (1999)
Coven, R., Havlin, S., ben-Avraham, D.: Structural Properties of Scale-Free Networks. In: Bornholdt, S., Schuster, H.G. (eds.) Handbook of graphs and networks, ch. 4, Wiley-VCH, Chichester (2002)
Jeong, H., Neda, Z., Barabasi, A.-L.: Measuring preferential attachment for evolving networks. Euro. Phys. Lett. 61, 567 (2003)
Langton, C.: Artificial Life. Addison-Wesley, Redwood City/CA, USA (1989)
Annunziato, M., Bertini, I., Lucchetti, M., Pannicelli, A., Pizzuti, S.: Adaptivity of Artificial Life Environment for On-Line Optimization of Evolving Dynamical Systems. In: Proc. EUNITE 2001, Tenerife, Spain (2001)
Annunziato, M., Bertini, I., Pannicelli, A., Pizzuti, S., Tsimring, L.: Complexity and Control of Combustion Processes in Industry. In: Proc. of CCSI 2000 Complexity and Complex System in Industry, Warwick, UK (2000)
Annunziato, M., Lucchetti, M., Orsini, G., Pizzuti, S.: Artificial life and on-line flows optimisation in energy networks. In: IEEE Swarm Intelligence Sympusium, Pasadena (CA), IEEE Computer Society Press, Los Alamitos (2005)
Annunziato, M., Bertini, I., Pannicelli, A., Pizzuti, S.: A Nature-inspired-Modeling-Optimization-Control system applied to a waste incinerator plant. In: 2nd European Symposium NiSIS’06, Puerto de la Cruz, Tenerife (Spain) (2006)
Annunziato, M., Bertini, I., Pannicelli, A., Pizzuti, S.: Evolutionary Control and On-Line Optimization of an MSWC Energy Process. Journal of Systemics, Cybernetics and Informatics 4(4) (2006)
Annunziato, M., Bertini, I., Iannone, R., Pizzuti, S.: Evolving feed-forward neural networks through evolutionary mutation parameters. In: Corchado, E., Yin, H., Botti, V., Fyfe, C. (eds.) IDEAL 2006. LNCS, vol. 4224, pp. 554–561. Springer, Heidelberg (2006)
Annunziato, M., Bruni, C., Lucchetti, M., Pizzuti, S.: Artificial life approach for continuous optimisation of non stationary dynamical systems. Integrated Computer-Aided Engineering 10(2), 111–125 (2003)
Russo, L.P., Bequette, B.W.: Impact of process design on the multiplicity behaviour of a jacketed exothermic CSTR. AIChE Journal 41, 135–147 (1995)
Saraf, V.S., Bequette, B.W.: Auto-tuning of cascade controlled open-loop unstable reactors. In: American Control Conference, Proceedings of the 2001, vol. 3, pp. 2021–2026 (2026)
Russo, L.P., Bequette, B.W.: State-Space versus Input/Output Representations for Cascade Control of Unstable Systems. Ind. Eng. Chem. Res. 36(6), 2271–2278 (1997)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Annunziato, M., Bertini, I., De Felice, M., Pizzuti, S. (2007). Evolving Complex Neural Networks. In: Basili, R., Pazienza, M.T. (eds) AI*IA 2007: Artificial Intelligence and Human-Oriented Computing. AI*IA 2007. Lecture Notes in Computer Science(), vol 4733. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74782-6_18
Download citation
DOI: https://doi.org/10.1007/978-3-540-74782-6_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74781-9
Online ISBN: 978-3-540-74782-6
eBook Packages: Computer ScienceComputer Science (R0)