Abstract
Spiking neural networks are promising candidates for representing aspects of cognitive context in human memory. We extended the liquid state machine model with time-delayed connections from liquid neurons to the readout unit to better capture context phenomena. We performed experiments in the area of spoken language recognition for studying two aspects of context dependency: influence of memory and temporal context. For the experiments, we derived a test data set from the well-known Brody-Hopfield test set to which we added varying degrees of Gaussian noise. We studied the influence of temporal context with a further specially designed test set. We found that the temporal context encoded in the pattern to be recognized was recognized better with our delayed synapses than without. Our experiments shed light on how context serves to integrate information and to increase robustness in human signal processing.
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
Auer, P., Burgsteiner, H.M., Maass, W.: The p-delta learning rule for parallel perceptrons. Science (2002)
Boyd, S., Chua, L.O.: Fading memory and the problem of approximating nonlinear operators with voltera series. IEEE Trans. on Circuits and Systems 32, 1150–1161 (1985)
Feldbusch, F., Kaiser, F.: Simulation of spiking neural nets with INspiRE. In: IEEE Conference on Systems, Man and Cybernetics, SMC (2005)
Gerstner, W., Kistler, W.: Spiking Neuron Models. Cambridge University Press, Cambridge (2002)
Hopfield, J.J., Brody, C.D.: What is a moment? cortical sensory integration over a brief interval. Proc. Natl. Acad. Sci. USA 97(25), 13919–13924 (2000)
Hopfield, J.J., Brody, C.D.: What is a moment? transient synchrony as a collective mechanism for spatiotemporal integration. Proc. Nat. Acad. Sci. USA 98(3), 1282–1287 (2001)
Jaeger, H.: Adaptive nonlinear system identification with echo state networks. Advances in Neural Information Processing Systems 15, 593–600 (2003)
Jaeger, H., Haas, H.: Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication. Science 304, 78–80 (2004)
Maass, W., Joshi, P., Sontag, E.: Computational aspects of feedback in neural circuits. PLOS Computational Biology (2006)
Maass, W.: Liquid state machines: Motivation, theory and applications. World Scientific Review 189 (2010)
Maass, W., Markram, H.: On the computational power of recurrent circuits of spiking neurons. In: Electronic Colloquium on Computational Complexity, vol. 22 (2001)
Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation 14(11), 2531–2560 (2002)
Schmidtke, H.R.: Granularity as a parameter of context. In: Dey, A.K., Kokinov, B., Leake, D.B., Turner, R. (eds.) CONTEXT 2005. LNCS (LNAI), vol. 3554, pp. 450–463. Springer, Heidelberg (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jakimovski, P., Schmidtke, H.R. (2011). Delayed Synapses: An LSM Model for Studying Aspects of Temporal Context in Memory. In: Beigl, M., Christiansen, H., Roth-Berghofer, T.R., Kofod-Petersen, A., Coventry, K.R., Schmidtke, H.R. (eds) Modeling and Using Context. CONTEXT 2011. Lecture Notes in Computer Science(), vol 6967. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24279-3_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-24279-3_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24278-6
Online ISBN: 978-3-642-24279-3
eBook Packages: Computer ScienceComputer Science (R0)