Abstract
Biological neurons use electrical pulses to transmit and process information in a significantly efficient way. To understand the mysteries of the underlying processing principles of the biological nervous systems, spiking neurons have been proposed to process information in a brain-like way. However, how could neurons learn spikes in an efficient way still remains challenging. In this study, we propose a simple and efficient multi-spike learning rule which could train neurons to associate input spike patterns with different output spike numbers. Our learning algorithm adopts a Tempotron-like LTP and a PSD-like LTD to adapt neuron’s efficacies. The results show that the proposed rule is faster than other benchmarks for the given task. A fast running time and simple implementation can largely benefit applied developments in neuromorphic systems. Additionally, we show that neurons with our proposed rule can elicit different output spike numbers in response to input spike patterns. Thus, single neurons are capable of performing the challenging task of multi-category classifications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Gütig, R.: To spike, or when to spike? Curr. Opin. Neurobiol. 25, 134–139 (2014)
Borst, A., Theunissen, F.E.: Information theory and neural coding. Nat. Neurosci. 2(11), 947–957 (1999)
Brette, R.: Philosophy of the spike: rate-based vs. spike-based theories of the brain. Front. Syst. Neurosci. 9, 151 (2015)
Panzeri, S., Brunel, N., Logothetis, N.K., Kayser, C.: Sensory neural codes using multiplexed temporal scales. Trends Neurosci. 33(3), 111–120 (2010)
Yu, Q., Tang, H., Hu, J., Tan, K.C.: Neuromorphic Cognitive Systems: A Learning and Memory Centered Approach, vol. 126, 1st edn. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-55310-8
Reinagel, P., Reid, R.C.: Temporal coding of visual information in the thalamus. J. Neurosci. 20(14), 5392–5400 (2000)
Serre, T., Oliva, A., Poggio, T.: A feedforward architecture accounts for rapid categorization. Proc. Natl. Acad. Sci. 104(15), 6424–6429 (2007)
Merolla, P.A., et al.: A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345(6197), 668–673 (2014)
Yao, P., et al.: Face classification using electronic synapses. Nat. Commun. 8, 15199 (2017)
Gütig, R., Sompolinsky, H.: The tempotron: a neuron that learns spike timing-based decisions. Nat. Neurosci. 9(3), 420–428 (2006)
Yu, Q., Tang, H., Tan, K.C., Li, H.: Rapid feedforward computation by temporal encoding and learning with spiking neurons. IEEE Trans. Neural Netw. Learn. Syst. 24(10), 1539–1552 (2013)
Yu, Q., Tang, H., Tan, K.C., Yu, H.: A brain-inspired spiking neural network model with temporal encoding and learning. Neurocomputing 138, 3–13 (2014)
Ponulak, F., Kasinski, A.J.: Supervised learning in spiking neural networks with ReSuMe: sequence learning, classification, and spike shifting. Neural Comput. 22(2), 467–510 (2010)
Florian, R.V.: The chronotron: a neuron that learns to fire temporally precise spike patterns. PLoS One 7(8), e40233 (2012)
Bohte, S.M., Kok, J.N., La Poutré, J.A.: Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing 48(1–4), 17–37 (2002)
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)
Yu, Q., Yan, R., Tang, H., Tan, K.C., Li, H.: A spiking neural network system for robust sequence recognition. IEEE Trans. Neural Netw. Learn. Syst. 27(3), 621–635 (2016)
GĂĽtig, R.: Spiking neurons can discover predictive features by aggregate-label learning. Science 351(6277), aab4113 (2016)
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. 1–12 (2018). https://doi.org/10.1109/TCYB.2018.2821692
Yu, Q., Wang, L., Dang, J.: Neuronal classifier for both rate and timing-based spike patterns. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, E.S. (eds.) Neural Information Processing. ICONIP 2017, vol. 10639, pp. 759–766. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-70136-3_80
Ghosh-Dastidar, S., Adeli, H.: A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection. Neural Netw. 22(10), 1419–1431 (2009)
Acknowledgments
This work was supported by the National Natural Science Foundation of China (No. 61806139, 61771333), and by the Natural Science Foundation of Tianjin (No. 18JCYBJC41700).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Yu, Q., Wang, L., Dang, J. (2018). Efficient Multi-spike Learning with Tempotron-Like LTP and PSD-Like LTD. In: Cheng, L., Leung, A., Ozawa, S. (eds) Neural Information Processing. ICONIP 2018. Lecture Notes in Computer Science(), vol 11301. Springer, Cham. https://doi.org/10.1007/978-3-030-04167-0_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-04167-0_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04166-3
Online ISBN: 978-3-030-04167-0
eBook Packages: Computer ScienceComputer Science (R0)