Abstract
In spiking neural networks (SNN), information is considered to be encoded mainly in the temporal patterns of their firing activity. Temporal integration of information plays a crucial role in a variety of cognitive processes, such as sensory discrimination, decision-making, or interval timing. However, it is rarely considered in traditional computational SNN models. In this paper, we investigate the influence of temporal integration on the computational performance of liquid state machine (LSM) from two aspects: the synaptic decay constant and time delay from presynaptic neurons to the output neurons. LSM is a biologically spiking neural network model for real-time computing on time-varying inputs, where the high dimensionality of dynamical spikes is transformed into smoothly changing states through synaptic integration into the readout neuron. Our experimental results show that increasing the decay constant of synapses from SNN to the output neuron can remarkably improve the computational performance due to the enhancement of temporal integration. Moreover, transmission delays have an even larger impact on the richness of dynamical states, which in turn significantly increase the computational accuracy of SNN. These results may have important implications for the modeling of spiking neural networks with excellent computational performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Maass, W., Natschläger, T., et al.: Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput. 14(11), 2531–2560 (2002)
Verstraeten, D., Schrauwen, B., Stroobandt, D., et al.: Isolated word recognition with the liquid state machine: a case study. Inf. Process. Lett. 95(6), 521–528 (2005)
Schrauwen, B., D’Haene, M., Verstraeten, D., et al.: Compact hardware liquid state machines on FPGA for real-time speech recognition. Neural Netw. Off. J. Int. Neural Netw. Soc. 21(2–3), 511–523 (2008)
Werner, M., Genta, V.M., Williams, D.: Movement generation and control with generic neural microcircuits. In: Biologically Inspired Approaches to Advanced Information Technology, First International Workshop, BioADIT 2004, Lausanne, 29–30 Jan 2004. Revised Selected Papers, pp. 258–273. DBLP (2004)
Maass, W., Natschläger, T., Markram, H.: A Model for Real-Time Computation in Generic Neural Microcircuits. DBLP 213–220 (2002)
Izhikevich, E.M.: Simple model of spiking neurons. IEEE Trans. Neural Netw. 14(6), 1569 (2003)
Maass, W., Joshi, P., Sontag, E.D.: Computational aspects of feedback in neural circuits. PLoS Comput. Biol. 3(1), e165 (2007)
Maass, W.: Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10(9), 1659–1671 (1997)
Schmitt, M.: On Computing Boolean Functions by a Spiking Neuron. Kluwer Academic, Boston (1998)
Maass, W., Schmitt, M.: On the complexity of learning for a spiking neuron. In: Proceedings of the Tenth Annual Conference on Computational Learning Theory, pp. 54–61. ACM (1997)
Maass, W., Schmitt, M., Bochum, R.U.: On the Complexity of Learning for Spiking Neurons with Temporal Coding. Academic (2000)
Maass, W.: On the relevance of time in neural computation and learning. Theor. Comput. Sci. 261(1), 157–178 (2001)
Acknowledgements
This paper is supported by the National Natural Science Foundation of China (No. 61304165 and No. 61473051) and Natural Science Foundation of Chongqing (No. cstc2016jcyjA0015).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Xue, F., Zhang, Y., Zhou, H., Li, X. (2018). Effects of Temporal Integration on Computational Performance of Spiking Neural Network. In: Delgado-GarcÃa, J., Pan, X., Sánchez-Campusano, R., Wang, R. (eds) Advances in Cognitive Neurodynamics (VI). Advances in Cognitive Neurodynamics. Springer, Singapore. https://doi.org/10.1007/978-981-10-8854-4_16
Download citation
DOI: https://doi.org/10.1007/978-981-10-8854-4_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-8853-7
Online ISBN: 978-981-10-8854-4
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)