Abstract
We investigate possibilities of inducing temporal structures without fading memory in recurrent networks of spiking neurons strictly operating in the pulse-coding regime. We extend the existing gradient-based algorithm for training feed-forward spiking neuron networks (SpikeProp [1]) to recurrent network topologies, so that temporal dependencies in the input stream are taken into account. It is shown that temporal structures with unbounded input memory specified by simple Moore machines (MM) can be induced by recurrent spiking neuron networks (RSNN). The networks are able to discover pulse-coded representations of abstract information processing states coding potentially unbounded histories of processed inputs.
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
Bohte, S., Kok, J., Poutré, H.L.: Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing 48, 17–37 (2002)
Siegelmann, H., Sontag, E.: On the computational power of neural nets. Journal of Computer and System Sciences 50, 132–150 (1995)
Bengio, Y., Frasconi, P., Simard, P.: The problem of learning long-term dependencies in recurrent networks. In: Proceedings of the 1993 IEEE International Conference on Neural Networks, vol. 3, pp. 1183–1188 (1993)
Giles, C., Miller, C., Chen, D., Chen, H., Sun, G., Lee, Y.: Learning and extracting finite state automata with second–order recurrent neural networks. Neural Computation 4, 393–405 (1992)
Casey, M.: The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction. Neural Computation 8, 1135–1178 (1996)
Gerstner, W.: Spiking neurons. In: Maass, W., Bishop, C. (eds.) Pulsed Coupled Neural Networks, pp. 3–54. MIT Press, Cambridge (1999)
Moore, S.: Back propagation in spiking neural networks. Master’s thesis, The University of Bath (2002)
Maass, W.: Lower bounds for the computational power of networks of spiking neurons. Neural Computation 8, 1–40 (1996)
Natschläger, T., Maass, W.: Spiking neurons and the induction of finite state machines. Theoretical Computer Science: Special Issue on Natural Computing 287, 251–265 (2002)
Floreano, D., Zufferey, J., Nicoud, J.: From wheels to wings with evolutionary spiking neurons. Artificial Life 11, 121–138 (2005)
Martignon, L., Deco, G., Laskey, K.B., Diamond, M., Freiwald, W., Vaadia, E.: Neural coding: Higher-order temporal patterns in the neurostatistics of cell assemblies. Neural Computation 12, 2621–2653 (2000)
Nadas, A.: Replay and time compression of recurring spike sequences in the hippocampus. The Journal of Neuroscience 19, 9497–9507 (1999)
Gerstner, W.: Time structure of activity in neural network models. Phys. Rev. E 51, 738–758 (1995)
Werbos, P.: Generalization of backpropagation with applications to a recurrent gas market model. Neural Networks 1, 339–356 (1989)
Hopcroft, J., Ullman, J.: Introduction to automata theory, languages, and computation. Addison–Wesley, Reading (1979)
Forcada, M., Carrasco, R.: Learning the initial state of a second-order recurrent neural network during regular-language inference. Neural Computation 7, 923–930 (1995)
Tiňo, P., Šajda, J.: Learning and extracting initial mealy machines with a modular neural network model. Neural Computation 7, 822–844 (1995)
Lawrence, S., Giles, C., Fong, S.: Natural language grammatical inference with recurrent neural networks. IEEE Transactions on Knowledge and Data Engineering 12, 126–140 (2000)
Yao, X.: Evolving artificial neural networks. Proceedings of the IEEE 87, 1423–1447 (1999)
Puskorius, G., Feldkamp, L.: Recurrent network training with the decoupled extended Kalman filter. In: Proceedings of the 1992 SPIE Conference on the Science of Artificial Neural Networks, Orlando, Florida (1992)
Rowe, J., Hidovic, D.: An evolution strategy using a continuous version of the gray-code neighbourhood distribution. In: Deb, K., et al. (eds.) GECCO 2004. LNCS, vol. 3102, pp. 725–736. Springer, Heidelberg (2004)
Maass, W., Markram, H.: Synapses as dynamic memory buffers. Neural Networks 15, 155–161 (2002)
Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation 14, 2531–2560 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tiňo, P., Mills, A. (2005). Learning Beyond Finite Memory in Recurrent Networks of Spiking Neurons. In: Wang, L., Chen, K., Ong, Y.S. (eds) Advances in Natural Computation. ICNC 2005. Lecture Notes in Computer Science, vol 3611. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11539117_95
Download citation
DOI: https://doi.org/10.1007/11539117_95
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28325-6
Online ISBN: 978-3-540-31858-3
eBook Packages: Computer ScienceComputer Science (R0)