Abstract
Sensory signals are encoded and processed by neurons in the brain in a form of action potentials, also called spikes that carry clue information across both spatial and temporal dimensions. Learning of such a clue information could be challenging, especially considering the case of long-delayed reward. This temporal credit assignment problem has been solved by a new concept of aggregate-label learning that motivates the development of a family of multi-spike learning algorithms whose remarkable learning performance has been demonstrated. However, most of the current spike-based learning methods are developed without consideration of input temporal fluctuations that constitute a common source of variability in sensory signals such as speech. Therefore, robust spike-based learning under fluctuations of both compression and dilation remains intriguing for exploration. In this paper, we first show the time-warp invariant characteristic of a conductance-based neuron model, based on which we then develop a new multi-spike learning algorithm for time-warp-invariant processing. Experimental results for speech recognition highlight the outstanding robustness of our algorithm against temporal distortions as compared with other relevant spike-based methods. Therefore, our study successfully confirms the effectiveness of multi-spike learning for time-warp robustness, extending a new scope for spike-based processing and learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Brette, R.: Philosophy of the spike: rate-based vs spike-based theories of the brain. Front. Syst. Neurosci. 9, 151 (2015)
Burkitt, A.N.: A review of the integrate-and-fire neuron model: I. homogeneous synaptic input. Biol. Cybern. 95(1), 1–19 (2006). https://doi.org/10.1007/s00422-006-0068-6
Gerstner, W., Kistler, W.M.: Spiking neuron models: single neurons, populations, plasticity. Cambridge University Press (2002)
Gütig, R.: Spiking neurons can discover predictive features by aggregate-label learning. Science 351(6277), aab4113 (2016)
Gütig, R., Sompolinsky, H.: The tempotron: a neuron that learns spike timing-based decisions. Nat. Neurosci. 9(3), 420–428 (2006)
Gütig, R., Sompolinsky, H.: Time-warp-invariant neuronal processing. PLoS Biol. 7(7), e1000141 (2009)
Hodgkin, A.L., Huxley, A.F.: A quantitative description of membrane current and its application to conduction and excitation in nerve. J. Physiol. 117(4), 500–544 (1952)
Instruments, T.: TI 46-word speaker-dependent isolated word corpus (cd-rom). NIST, Gaithersburg (1991)
Kandel, E.R., Schwartz, J.H., Jessell, T.M., Siegelbaum, S., Hudspeth, A.J., Mack, S.: Principles of neural science, vol. 4. McGraw-hill New York (2000)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Leonard, R.G., Doddington, G.: TIDIGITS speech corpus. Texas Instruments, Inc. (1993)
Li, S., Yu, Q.: New efficient multi-spike learning for fast processing and robust learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 4650–4657 (2020)
Maass, W.: Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10(9), 1659–1671 (1997)
Miao, Y., Tang, H., Pan, G.: A supervised multi-spike learning algorithm for spiking neural networks. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–7. IEEE (2018)
Ponulak, F.: ReSuMe-new supervised learning method for spiking neural networks. Poznan University of Technology, Institute of Control and Information Engineering (2005)
Roy, K., Jaiswal, A., Panda, P.: Towards spike-based machine intelligence with neuromorphic computing. Nature 575(7784), 607–617 (2019)
Tavanaei, A., Maida, A.S.: A spiking network that learns to extract spike signatures from speech signals. Neurocomputing 240, 191–199 (2017)
Wade, J.J., McDaid, L.J., Santos, J.A., Sayers, H.M.: Swat: a spiking neural network training algorithm for classification problems. IEEE Trans. Neural Networks 21(11), 1817–1830 (2010)
Wu, J., Chua, Y., Li, H.: A biologically plausible speech recognition framework based on spiking neural networks. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2018)
Yu, Q., Li, H., Tan, K.C.: Spike timing or rate? Neurons learn to make decisions for both through threshold-driven plasticity. IEEE Trans. Cybern. 49(6), 2178–2189 (2018)
Yu, Q., Tang, H., Tan, K.C., Li, H.: Precise-spike-driven synaptic plasticity: learning hetero-association of spatiotemporal spike patterns. PLoS ONE 8(11), e78318 (2013)
Zhang, M., et al.: Supervised learning in spiking neural networks with synaptic delay-weight plasticity. Neurocomputing 409, 103–118 (2020)
Zhang, M., et al.: MPD-AL: an efficient membrane potential driven aggregate-label learning algorithm for spiking neurons. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 1327–1334 (2019)
Zhang, Y., Li, P., Jin, Y., Choe, Y.: A digital liquid state machine with biologically inspired learning and its application to speech recognition. IEEE Trans. Neural Netw. Learn. Syst. 26(11), 2635–2649 (2015)
Acknowledgement
This work was supported by the National Natural Science Foundation of China under Grant 62176179.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhou, X., Liu, Y., Sun, W., Yu, Q. (2024). Time-Warp-Invariant Processing with Multi-spike Learning. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Communications in Computer and Information Science, vol 1962. Springer, Singapore. https://doi.org/10.1007/978-981-99-8132-8_2
Download citation
DOI: https://doi.org/10.1007/978-981-99-8132-8_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8131-1
Online ISBN: 978-981-99-8132-8
eBook Packages: Computer ScienceComputer Science (R0)