Abstract
Most of the differential Hebbian rules derived from Spike-Timing Dependent Plasticity (STDP) focus on the rates of change of post-synaptic activity that carries the information about the future and enables the neural network to predict. And the current model mainly consider three factors for the adjustment of synaptic weight, namely, the rate of pre- and post-synaptic activity and the rate of change of post-synaptic activity. We argue that the rate of change of pre-synaptic activity also plays an important role on the adjustment of synaptic weight. Hence, this paper proposes a quaternionic rate-based synaptic learning rule that depends on four elements, namely, the instantaneous firing rates of both pre- and post-synaptic neurons and their time derivatives.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bengio, Y., Lee, D.H., Bornschein, J., Lin, Z.: Towards biologically plausible deep learning. arXiv preprint arXiv:1502.04156 (2015)
Bengio, Y., Mesnard, T., Fischer, A., Zhang, S., Wu, Y.: STDP as presynaptic activity times rate of change of postsynaptic activity. arXiv preprint arXiv:1509.05936 (2015)
Bi, G.Q., Poo, M.M.: Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type. J. Neurosci. 18(24), 10464–10472 (1998)
Chrol-Cannon, J., Grüning, A., Jin, Y.: The emergence of polychronous groups under varying input patterns, plasticity rules and network connectivities. In: The 2012 International Joint Conference on Neural Networks (IJCNN), pp. 1–6 (2012)
Froemke, R.C., Letzkus, J.J., Kampa, B.M., Hang, G.B., Stuart, G.J.: Dendritic synapse location and neocortical spike-timing-dependent plasticity. Front. Synaptic Neurosci. 2, 29 (2010)
Gabbiani, F., Cox, S.J.: Mathematics for neuroscientists. Academic Press, Cambridge (2010)
Gerstner, W., Kempter, R., van Hemmen, J.L., Wagner, H.: A neuronal learning rule for sub-millisecond temporal coding. Nature 383(6595), 76–78 (1996)
Gerstner, W., Kistler, W.M.: Mathematical formulations of hebbian learning. Biol. Cybern. 87(5–6), 404–415 (2002)
Guyonneau, R., VanRullen, R., Thorpe, S.J.: Neurons tune to the earliest spikes through STDP. Neural Comput. 17(4), 859–879 (2005)
Henneman, E., Mendell, L.M.: Functional organization of motoneuron pool and its inputs. In: Comprehensive Physiology, pp. 423–507 (2011). http://onlinelibrary.wiley.com/doi/10.1002/cphy.cp010211/abstract;jsessionid=DC8038A8B928C849064AFF986290D55A.f04t01
Iakymchuk, T., Rosado-Muñoz, A., Guerrero-Martínez, J.F., Bataller-Mompeán, M., Francés-Víllora, J.V.: Simplified spiking neural network architecture and STDP learning algorithm applied to image classification. EURASIP J. Image Video Process. 2015(1), 1–11 (2015)
Izhikevich, E.M., Desai, N.S.: Relating STDP to BCM. Neural Comput. 15(7), 1511–1523 (2003)
Kempter, R., Gerstner, W., Van Hemmen, J.L.: Spike-based compared to rate-based hebbian learning. Adv. Neural Inf. Process. Syst. 11, 125–131 (1999)
Lass, Y., Abeles, M.: Transmission of information by the axon: I. Noise and memory in the myelinated nerve fiber of the frog. Biol. Cybern. 19(2), 61–67 (1975)
Markram, H., Sakmann, B.: Action potentials propagating back into dendrites trigger changes in efficacy of single-axon synapses between layer V pyramidal neurons. Soc. Neurosci. Abstr. 21, 2007 (1995)
Nessler, B., Pfeiffer, M., Maass, W.: STDP enables spiking neurons to detect hidden causes of their inputs. In: Advances in Neural Information Processing Systems, pp. 1357–1365 (2009)
Rao, R.P., Sejnowski, T.J.: Spike-timing-dependent hebbian plasticity as temporal difference learning. Neural Comput. 13(10), 2221–2237 (2001)
Roberts, P.D.: Computational consequences of temporally asymmetric learning rules: I. Differential hebbian learning. J. Comput. Neurosci. 7(3), 235–246 (1999)
Scellier, B., Bengio, Y.: Equilibrium propagation: bridging the gap between energy-based models and backpropagation. arXiv preprint arXiv:1602.05179 (2016)
Senn, W., Pfister, J.P.: Spike-timing-dependent plasticity, learning rules. In: Jaeger, D., Jung, R. (eds.) Encyclopedia of Computational Neuroscience, pp. 1–10. Springer, Heidelberg (2014)
Sjöström, P.J., Rancz, E.A., Roth, A., Häusser, M.: Dendritic excitability and synaptic plasticity. Physiol. Rev. 88(2), 769–840 (2008)
Stevens, C.F., Wang, Y., et al.: Changes in reliability of synaptic function as a mechanism for plasticity. Nature 371(6499), 704–707 (1994)
Waddington, A., Appleby, P.A., De Kamps, M., Cohen, N.: Triphasic spike-timing-dependent plasticity organizes networks to produce robust sequences of neural activity. Front. Comput. Neurosci. 6, 88 (2012)
Xie, X., Seung, H.S.: Spike-based learning rules and stabilization of persistent neural activity. Adv. Neural Inf. Process. Syst. 12, 199–208 (2000)
Acknowledgement
This study was funded by the Strategic Priority Research Program of the Chinese Academy of Sciences (XDB02060007), and Beijing Municipal Commission of Science and Technology (Z151100000915070, Z161100000216124). This research is conducted at Institute of Automation, Chinese Academy of Science.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Qiao, G., Du, H., Zeng, Y. (2017). A Quaternionic Rate-Based Synaptic Learning Rule Derived from Spike-Timing Dependent Plasticity. In: Cong, F., Leung, A., Wei, Q. (eds) Advances in Neural Networks - ISNN 2017. ISNN 2017. Lecture Notes in Computer Science(), vol 10261. Springer, Cham. https://doi.org/10.1007/978-3-319-59072-1_54
Download citation
DOI: https://doi.org/10.1007/978-3-319-59072-1_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-59071-4
Online ISBN: 978-3-319-59072-1
eBook Packages: Computer ScienceComputer Science (R0)