Abstract
The paper investigates a new type of truly critical echo state networks where individual transfer functions for every neuron can be modified to anticipate the expected next input. Deviations from expected input are only forgotten slowly in power law fashion. The paper outlines the theory, numerically analyzes a one neuron model network and finally discusses technical and also biological implications of this type of approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lukoševičius, M., Jäger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3(3), 127–149 (2009)
Schrauwen, B., Verstraeten, D., Van Campenhout, J.: An overview of reservoir computing: theory, applications and implementations. In: Proceedings of the 15th European Symposium on Artificial Neural Networks. Citeseer (2007)
Jäger, H.: The “echo state” approach to analysing and training recurrent neural networks - with an erratum note. In: GMD Report 148, GMD German National Research Insitute for Computer Science (2010). http://www.gmd.de/People/Herbert.Jaeger/Publications.html
Jäger, H.: Adaptive nonlinear system identification with echo state networks. In: Proceedings of NIPS 2002, AA14 (2003)
Jäger, H., Maass, W., Principe, J.: Special issue on echo state networks and liquid state machines. Neural Netw. 20(3), 287–289 (2007)
Natschläger, T., Bertschinger, N., Legenstein, R.: At the edge of chaos: real-time computations and self-organized criticality in recurrent neural networks. In: Advances in Neural Information Processing Systems, vol. 17 (2005)
Hajnal, M.A., Lörincz, A.: Critical echo state networks. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds.) ICANN 2006. LNCS, vol. 4131, pp. 658–667. Springer, Heidelberg (2006). doi:10.1007/11840817_69
Boedecker, J., Obst, O., Lizier, J., Mayer, N., Asada, M.: Information processing in echo state networks at the edge of chaos. Theory Biosci. 131, 205–213 (2012)
Beggs, J., Plenz, D.: Neuronal avalanches in neocortical curcuits. J. Neurosci. 24(22), 5216–5229 (2004)
Mayer, N.M.: Adaptive critical reservoirs with power law forgetting of unexpected input events. Neural Comput. 27, 1102–1119 (2015)
Mayer, N.M.: Critical echo state networks that anticipate input using adaptive transfer functions (2016). http://arxiv.org/abs/1606.03674
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)
Wainrib, G., Galtier, M.N.: A local echo state property through the largest lyapunov exponent. Neural Netw. 76, 39–45 (2016)
Mayer, N.M., Browne, M.: Self-prediction in echo state networks. In: Proceedings of the First International Workshop on Biological Inspired Approaches to Advanced Information Technology (BioAdIt2004), Lausanne (2004)
Mayer, N.M., Asada, M.: Is self-prediction a useful paradigm for echo state networks that are driven by robotic sensory input? In: 20th Neural Information Processing Systems Conference (NIPS 2006): Workshop on Echo State Networks and Liquid State Machines, H. Jaeger, W. Maass, Jose C. Principe (Organisers), December 2006
Wang, L., Chen, X., Li, S., Cai, X.: General adaptive transfer functions design for volume rendering by using neural networks. In: King, I., Wang, J., Chan, L.-W., Wang, D.L. (eds.) ICONIP 2006. LNCS, vol. 4233, pp. 661–670. Springer, Heidelberg (2006). doi:10.1007/11893257_74
Acknowledgements
This manuscript has been posted at arxiv.org. The authors thanks MOST of Taiwan for financial support and O. Obst for all his help.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Mayer, N.M. (2017). Critical Echo State Networks that Anticipate Input Using Morphable Transfer Functions. In: Cong, F., Leung, A., Wei, Q. (eds) Advances in Neural Networks - ISNN 2017. ISNN 2017. Lecture Notes in Computer Science(), vol 10261. Springer, Cham. https://doi.org/10.1007/978-3-319-59072-1_49
Download citation
DOI: https://doi.org/10.1007/978-3-319-59072-1_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-59071-4
Online ISBN: 978-3-319-59072-1
eBook Packages: Computer ScienceComputer Science (R0)