Abstract
In this chapter, we discuss recently developed methods for characterizing the dynamics of recurrent neural networks. Such methods rely on theory and concepts coming from the field of complex systems. We focus on a class of recurrent networks called echo state networks. First, we present a method to analyze and characterize the evolution of its internal state. This allows to provide a qualitative interpretation of the network dynamics. In addition, it allows to assess the stability of the system, a necessary requirement in many practical applications. Successively, we focus on the identification of the onset of criticality in such networks. We discuss an unsupervised method based on Fisher information, which can be used to tune the network hyperparameters. With respect to standard supervised techniques, we show that the proposed approach offers several advantages and is effective on a number of tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aljadeff, J., Stern, M., Sharpee, T.: Transition to chaos in random networks with cell-type-specific connectivity. Phys. Rev. Lett. 114, 088101 (2015). doi:10.1103/PhysRevLett.114.088101
Barzel, B., Barabási, A.-L.: Universality in network dynamics. Nat. Phys. 9(10), 673–681 (2013). doi:10.1038/nphys2741
Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166 (1994). ISSN 1045-9227. doi:10.1109/72.279181
Berisha, V., Hero, A.Q. III.: Empirical non-parametric estimation of the Fisher information. IEEE Signal Process. Lett. 22(7), 988–992 (2015). ISSN 1070-9908. doi:10.1109/LSP.2014.2378514
Bertschinger, N., Natschläger, T.: Real-time computation at the edge of chaos in recurrent neural networks. Neural Comput. 16(7), 1413–1436 (2004). doi:10.1162/089976604323057443
Bianchi, F.M., Livi, L., Alippi, C.: Investigating echo state networks dynamics by means of recurrence analysis. IEEE Trans. Neural Netw. Learn. Syst. 1–13 (2016). doi:10.1109/TNNLS.2016.2630802
Boedecker, J., Obst, O., Lizier, J.T., Mayer, N.M., Asada, M.: Information processing in echo state networks at the edge of chaos. Theory Biosci. 131(3), 205–213 (2012). doi:10.1007/s12064-011-0146-8
Charles, A., Yin, D., Rozell, C.: Distributed sequence memory of multidimensional inputs in recurrent networks. arXiv:1605.08346 (2016)
De Arcangelis, L., Lombardi, F., Herrmann, H.J.: Criticality in the brain. J. Stat. Mech. Theory Exp. 2014(3), P03026 (2014). doi:10.1088/1742-5468/2014/03/P03026
Enel, P., Procyk, E., Quilodran, R., Dominey, P.F.: Reservoir computing properties of neural dynamics in prefrontal cortex. PLoS Comput. Biol. 12(6), e1004967 (2016). doi:10.1371/journal.pcbi.1004967
Eroglu, D., Peron, T.K.D.M., Marwan, N., Rodrigues, F.A., da Costa, L.F., Sebek, M., Kiss, I.Z., Kurths, J.: Entropy of weighted recurrence plots. Phys. Rev. E 90(4), 042919 (2014). doi:10.1103/PhysRevE.90.042919
Elman, J.L.: Finding structure in time. Cogn. Sci. 14(2), 179–211 (1990). ISSN 0364-0213. doi:10.1016/0364-0213(90)90002-E
Friedman, J.H., Rafsky, L.C.: Multivariate generalizations of the Wald-Wolfowitz and Smirnov two-sample tests. Ann. Stat. 7(4), 697–717 (1979)
Grigolini, P.: Emergence of biological complexity: criticality, renewal and memory. Chaos, Solitons Fractals (2015). doi:10.1016/j.chaos.2015.07.025
Hammer, B., Micheli, A., Sperduti, A., Strickert, M.: Recursive self-organizing network models. Neural Netw. 17(8–9), 1061–1085 (2004). ISSN 0893-6080. doi:10.1016/j.neunet.2004.06.009
Hidalgo, J., Grilli, J., Suweis, S., Muñoz, M.A., Banavar, J.R., Maritan, A.: Information-based fitness and the emergence of criticality in living systems. Proc. Natl. Acad. Sci. 111(28), 10095–10100 (2014). doi:10.1073/pnas.1319166111
Hidalgo, J., Grilli, J., Suweis, S., Maritan, A., Muñoz, M.A.: Cooperation, competition and the emergence of criticality in communities of adaptive systems. J. Stat. Mech. Theory Exp. 2016(3), 033203 (2016). doi:10.1088/1742-5468/2016/03/033203
Jaeger, H.: The “echo state” approach to analysing and training recurrent neural networks-with an erratum note. Bonn, Germany: German National Research Center for Information Technology GMD Technical Report, vol. 148, p. 34 (2001)
Lacasa, L., Nicosia, V., Latora, V.: Network structure of multivariate time series. Sci. Rep. 5, (2015). doi:10.1038/srep15508
Langton, C.G.: Computation at the edge of chaos: Phase transitions and emergent computation. Phys. D Nonlinear Phenom. 42(1), 12–37 (1990). doi:10.1016/0167-2789(90)90064-V
Legenstein, R., Maass, W.: Edge of chaos and prediction of computational performance for neural circuit models. Neural Netw. 20(3), 323–334 (2007). doi:10.1016/j.neunet.2007.04.017
Livi, L., Bianchi, F.M., Alippi, C.: Determination of the edge of criticality in echo state networks through Fisher information maximization. IEEE Trans. Neural Netw. Learn. Syst. 1–12 (2017). doi:10.1109/TNNLS.2016.2644268
Maass, W., Joshi, P., Sontag, E.D.: Computational aspects of feedback in neural circuits. PLoS Comput. Biol. 3(1), e165 (2007). doi:10.1371/journal.pcbi.0020165.eor
Magnus, J.R., Neudecker, H.: Matrix Differential Calculus with Applications in Statistics and Econometrics. Wiley, New York (1995)
Manjunath, G., Jaeger, H.: Echo state property linked to an input: Exploring a fundamental characteristic of recurrent neural networks. Neural Comput. 25(3), 671–696 (2013). doi:10.1162/NECO_a_00411
Marichal, R.L., Piñeiro, J.D.: Analysis of multiple quasi-periodic orbits in recurrent neural networks. Neurocomputing 162, 85–95 (2015). doi:10.1016/j.neucom.2015.04.001
Marwan, N.: How to avoid potential pitfalls in recurrence plot based data analysis. Int. J. Bifurcat. Chaos 21(04), 1003–1017 (2011). doi:10.1142/S0218127411029008
Marwan, N., Kurths, J.: Line structures in recurrence plots. Phys. Lett. A 336(4), 349–357 (2005). doi:10.1016/j.physleta.2004.12.056
Marwan, N., Carmen, M., Thiel, R.M., Kurths, J.: Recurrence plots for the analysis of complex systems. Phys. Rep. 438(5), 237–329 (2007). doi:10.1016/j.physrep.2006.11.001
Marwan, N., Schinkel, S., Kurths, J.: Recurrence plots 25 years later-Gaining confidence in dynamical transitions. EPL (Europhys. Lett.) 101(2), 20007 (2013). doi:10.1209/0295-5075/101/20007
Massar, M., Massar, S.: Mean-field theory of echo state networks. Phys. Rev. E 87(4), 042809 (2013). doi:10.1103/PhysRevE.87.042809
Massobrio, P., de Arcangelis, L., Pasquale, V., Jensen, H.J., Plenz, D.: Criticality as a signature of healthy neural systems. Front. Syst. Neurosci. 9, 22 (2015). doi:10.3389/fnsys.2015.00022
Mastromatteo, I., Marsili, M.: On the criticality of inferred models. J. Stat. Mech. Theory Exp. 2011(10), P10012 (2011). doi:10.1088/1742-5468/2011/10/P10012
Mora, T., Bialek, W.: Are biological systems poised at criticality? J. Stat. Phys. 144(2), 268–302 (2011). doi:10.1007/s10955-011-0229-4
Mora, T., Deny, S., Marre, O.: Dynamical criticality in the collective activity of a population of retinal neurons. Phys. Rev. Lett. 114(7), 078105 (2015). doi:10.1103/PhysRevLett.114.078105
Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. arXiv:1211.5063 (2012)
Peng, Y., Lei, M., Li, J.-B., Peng, X.-Y.: A novel hybridization of echo state networks and multiplicative seasonal ARIMA model for mobile communication traffic series forecasting. Neural Comput. Appl. 24(3–4), 883–890 (2014)
Prokopenko, M., Lizier, J.T., Obst, O., Wang, X.R.: Relating Fisher information to order parameters. Phys. Rev. E 84(4), 041116 (2011). doi:10.1103/PhysRevE.84.041116
Rajan, K., Abbott, L.F., Sompolinsky, H.: Stimulus-dependent suppression of chaos in recurrent neural networks. Phys. Rev. E 82(1), 011903 (2010). doi:10.1103/PhysRevE.82.011903
Reinhart, R.F., Steil, J.J.: Regularization and stability in reservoir networks with output feedback. Neurocomputing 90, 96–105 (2012). doi:10.1016/j.neucom.2012.01.032
Roli, A., Villani, M., Filisetti, A., Serra, R.: Dynamical criticality: overview and open questions. arXiv:1512.05259 (2015)
Rumelhart, D.E., Smolensky, P., McClelland, J.L., Hinton, G.: Sequential thought processes in pdp models. V 2, 3–57 (1986)
Scheffer, M., Bascompte, J., Brock, W.A., Brovkin, V., Carpenter, S.R., Dakos, V., Held, H., Van Nes, E.H., Rietkerk, M., Sugihara, G.: Early-warning signals for critical transitions. Nature 461(7260), 53–59 (2009). doi:10.1038/nature08227
Scheffer, M., Carpenter, S.R., Lenton, T.M., Bascompte, J., Brock, W., Dakos, V., van De Koppel, J., van De Leemput, I.A., Levin, S.A., van Nes, E.H., Pascual, M., Vandermeer, J.: Anticipating critical transitions. Science 338(6105), 344–348 (2012). doi:10.1126/science.1225244
Schiller, U.D., Steil, J.J.: Analyzing the weight dynamics of recurrent learning algorithms. Neurocomputing 63, 5–23 (2005). doi:10.1016/j.neucom.2004.04.006
Shen, Y., Wang, J.: An improved algebraic criterion for global exponential stability of recurrent neural networks with time-varying delays. IEEE Trans. Neural Netw. 19(3), 528–531 (2008). ISSN 1045-9227. doi:10.1109/TNN.2007.911751
Steil, J.J.: Memory in backpropagation-decorrelation o(n) efficient online recurrent learning. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) Artificial Neural Networks: Formal Models and Their Applications-ICANN 2005, pp. 649–654. Springer, Berlin, Heidelberg (2005)
Sussillo, D.: Neural circuits as computational dynamical systems. Curr. Opin. Neurobiol. 25, 156–163 (2014). doi:10.1016/j.conb.2014.01.008
Sussillo, D., Barak, O.: Opening the black box: low-dimensional dynamics in high-dimensional recurrent neural networks. Neural Comput. 25(3), 626–649 (2013). doi:10.1162/NECO_a_00409
Tiňo, P., Rodan, A.: Short term memory in input-driven linear dynamical systems. Neurocomputing 112, 58–63 (2013). doi:10.1016/j.neucom.2012.12.041
Tkačik, G., Bialek, W.: Information processing in living systems. Ann. Rev. Condens. Matter Phys. 7(1), 89–117 (2016). doi:10.1146/annurev-conmatphys-031214-014803
Tkačik, G., Mora, T., Marre, O., Amodei, D., Palmer, S.E., Berry, M.J., Bialek, W.: Thermodynamics and signatures of criticality in a network of neurons. Proc. Natl. Acad. Sci. 112(37), 11508–11513 (2015). doi:10.1073/pnas.1514188112
Torres, J.J., Marro, J.: Brain performance versus phase transitions. Sci. Rep. 5 (2015). doi:10.1038/srep12216
Toyoizumi, T., Abbott, L.F.: Beyond the edge of chaos: amplification and temporal integration by recurrent networks in the chaotic regime. Phys. Rev. E 84(5), 051908 (2011). doi:10.1103/PhysRevE.84.051908
Toyoizumi, T., Aihara, K., Amari, S.-I.: Fisher information for spike-based population decoding. Phys. Rev. Lett. 97(9), 098102 (2006). doi:10.1103/PhysRevLett.97.098102
Verstraeten, D., Schrauwen, B.: On the quantification of dynamics in reservoir computing. In: Artificial Neural Networks–ICANN 2009, pp. 985–994. Springer, Berlin (2009). doi:10.1007/978-3-642-04274-4_101
Verstraeten, D., Schrauwen, B., D’Haene, M., Stroobandt, D.: An experimental unification of reservoir computing methods. Neural Netw. 20(3), 391–403 (2007). ISSN 0893-6080. doi:10.1016/j.neunet.2007.04.003. Echo State Networks and Liquid State Machines
Wainrib, G., Touboul, J.: Topological and dynamical complexity of random neural networks. Phys. Rev. Lett. 110, 118101 (2013). doi:10.1103/PhysRevLett.110.118101
Wang, X., Lizier, J., Prokopenko, M.: Fisher information at the edge of chaos in random boolean networks. Artif. Life 17(4), 315–329 (2011). ISSN 1064-5462. doi:10.1162/artl_a_00041
Werbos, P.J.: Backpropagation: past and future. Proc. IEEE Int. Conf. Neural Netw. 1, 343–353 (1988). doi:10.1109/ICNN.1988.23866
Yildiz, I.B., Jaeger, H., Kiebel, S.J.: Re-visiting the echo state property. Neural Netw. 35, 1–9 (2012). doi:10.1016/j.neunet.2012.07.005
Zegers, P.: Fisher information properties. Entropy 17(7), 4918–4939 (2015). doi:10.3390/e17074918
Zhang, B., Miller, D.J., Wang, Y.: Nonlinear system modeling with random matrices: echo state networks revisited. IEEE Trans. Neural Netw. Learn. Syst. 23(1), 175–182 (2012). ISSN 2162-237X. doi:10.1109/TNNLS.2011.2178562
Zhang, Y., Wang, J.: Global exponential stability of recurrent neural networks for synthesizing linear feedback control systems via pole assignment. IEEE Trans. Neural Netw. 13(3), 633–644 (2002). ISSN 1045-9227. doi:10.1109/TNN.2002.1000129
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this chapter
Cite this chapter
Bianchi, F.M., Livi, L., Alippi, C. (2018). On the Interpretation and Characterization of Echo State Networks Dynamics: A Complex Systems Perspective. In: Gawęda, A., Kacprzyk, J., Rutkowski, L., Yen, G. (eds) Advances in Data Analysis with Computational Intelligence Methods. Studies in Computational Intelligence, vol 738. Springer, Cham. https://doi.org/10.1007/978-3-319-67946-4_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-67946-4_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67945-7
Online ISBN: 978-3-319-67946-4
eBook Packages: EngineeringEngineering (R0)