Modeling the Dynamics of Spiking Networks with Memristor-Based STDP to Solve Classification Tasks
Abstract
:1. Introduction
2. Materials and Methods
2.1. Neuron Model
2.2. Plasticity Models
2.2.1. Additive Spike-Timing-Dependent Plasticity
2.2.2. Nanocomposite Memristor Plasticity
2.2.3. Model of Poly-p-Xylylene Memristors
2.3. Network Model Implementation
2.4. Input Preprocessing and Encoding
2.5. Learning Algorithm
Algorithm 1 Learning algorithm |
Input: matrix of preprocessed input objects X, vector of object classes Y, neuron parameters, plasticity parameters, initial distribution of weights Parameter: N_epochs, , h Output: network weights
|
2.6. Datasets
3. Results
3.1. Memorizing Repeating Patterns
3.2. Classification with SNN
4. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Paugam-Moisy, H.; Bohte, S.M. Computing with spiking neuron networks. In Handbook of Natural Computing; Rozenberg, G., Back, T., Kok, J., Eds.; Springer: Berlin/Heidelberg, Germany, 2012; pp. 335–376. [Google Scholar] [CrossRef] [Green Version]
- Tavanaei, A.; Ghodrati, M.; Kheradpisheh, S.R.; Masquelier, T.; Maida, A. Deep learning in spiking neural networks. Neural Netw. 2019, 111, 47–63. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Taherkhani, A.; Belatreche, A.; Li, Y.; Cosma, G.; Maguire, L.P.; McGinnity, T. A review of learning in biologically plausible spiking neural networks. Neural Netw. 2020, 122, 253–272. [Google Scholar] [CrossRef] [PubMed]
- Davies, M.; Srinivasa, N.; Lin, T.H.; Chinya, G.; Cao, Y.; Choday, S.H.; Dimou, G.; Joshi, P.; Imam, N.; Jain, S.; et al. Loihi: A neuromorphic manycore processor with on-chip learning. IEEE Micro 2018, 38, 82–99. [Google Scholar] [CrossRef]
- Indiveri, G.; Corradi, F.; Qiao, N. Neuromorphic architectures for spiking deep neural networks. In Proceedings of the 2015 IEEE International Electron Devices Meeting, Washington, DC, USA, 7–9 December 2015; pp. 4.2.1–4.2.4. [Google Scholar]
- Merolla, P.A.; Arthur, J.V.; Alvarez-Icaza, R.; Cassidy, A.S.; Sawada, J.; Akopyan, F.; Jackson, B.L.; Imam, N.; Guo, C.; Nakamura, Y.; et al. A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 2014, 345, 668–673. [Google Scholar] [CrossRef]
- Rajendran, B.; Sebastian, A.; Schmuker, M.; Srinivasa, N.; Eleftheriou, E. Low-Power Neuromorphic Hardware for Signal Processing Applications: A review of architectural and system-level design approaches. IEEE Signal Process. Mag. 2019, 36, 97–110. [Google Scholar] [CrossRef] [Green Version]
- Camuñas-Mesa, L.A.; Linares-Barranco, B.; Serrano-Gotarredona, T. Neuromorphic spiking neural networks and their memristor-CMOS hardware implementations. Materials 2019, 12, 2745. [Google Scholar] [CrossRef] [Green Version]
- Saïghi, S.; Mayr, C.G.; Serrano-Gotarredona, T.; Schmidt, H.; Lecerf, G.; Tomas, J.; Grollier, J.; Boyn, S.; Vincent, A.F.; Querlioz, D.; et al. Plasticity in memristive devices for spiking neural networks. Front. Neurosci. 2015, 9, 51. [Google Scholar] [CrossRef]
- Ismail, M.; Chand, U.; Mahata, C.; Nebhen, J.; Kim, S. Demonstration of synaptic and resistive switching characteristics in W/TiO2/HfO2/TaN memristor crossbar array for bioinspired neuromorphic computing. J. Mater. Sci. Technol. 2022, 96, 94–102. [Google Scholar] [CrossRef]
- Ryu, J.H.; Mahata, C.; Kim, S. Long-term and short-term plasticity of Ta2O5/HfO2 memristor for hardware neuromorphic application. J. Alloys Compd. 2021, 850, 156675. [Google Scholar] [CrossRef]
- Sboev, A.G.; Emelyanov, A.V.; Nikiruy, K.E.; Serenko, A.V.; Sitnikov, A.V.; Presnyakov, M.Y.; Rybka, R.B.; Rylkov, V.V.; Kashkarov, P.K.; Kovalchuk, M.V.; et al. Self-adaptive STDP-based learning of a spiking neuron with nanocomposite memristive weights. Nanotechnology 2019, 31, 045201. [Google Scholar] [CrossRef]
- Prudnikov, N.V.; Lapkin, D.A.; Emelyanov, A.V.; Minnekhanov, A.A.; Malakhova, Y.N.; Chvalun, S.N.; Demin, V.A.; Erokhin, V.V. Associative STDP-like learning of neuromorphic circuits based on polyaniline memristive microdevices. J. Phys. D Appl. Phys. 2020, 53, 414001. [Google Scholar] [CrossRef]
- Lapkin, D.A.; Emelyanov, A.V.; Demin, V.A.; Berzina, T.S.; Erokhin, V.V. Spike-timing-dependent plasticity of polyaniline-based memristive element. Microelectron. Eng. 2018, 185–186, 43–47. [Google Scholar] [CrossRef]
- Demin, V.; Nekhaev, D.; Surazhevsky, I.; Nikiruy, K.; Emelyanov, A.; Nikolaev, S.; Rylkov, V.; Kovalchuk, M. Necessary conditions for STDP-based pattern recognition learning in a memristive spiking neural network. Neural Netw. 2021, 134, 64–75. [Google Scholar] [CrossRef]
- Minnekhanov, A.A.; Shvetsov, B.S.; Martyshov, M.M.; Nikiruy, K.E.; Kukueva, E.V.; Presnyakov, M.Y.; Forsh, P.A.; Rylkov, V.V.; Erokhin, V.V.; Demin, V.A.; et al. On the resistive switching mechanism of parylene-based memristive devices. Org. Electron. 2019, 74, 89–95. [Google Scholar] [CrossRef]
- Serrano-Gotarredona, T.; Masquelier, T.; Prodromakis, T.; Indiveri, G.; Linares-Barranco, B. STDP and STDP variations with memristors for spiking neuromorphic learning systems. Front. Neurosci. 2013, 7, 2. [Google Scholar] [CrossRef] [Green Version]
- Du, N.; Kiani, M.; Mayr, C.; You, T.; Bürger, D.; Skorupa, I.; Schmidt, O.; Schmidt, H. Single pairing spike-timing dependent plasticity in BiFeO3 memristors with a time window of 25 ms to 125 μs. Front. Neurosci. 2015, 9, 227. [Google Scholar] [CrossRef] [Green Version]
- Qu, L.; Zhao, Z.; Wang, L.; Wang, Y. Efficient and hardware-friendly methods to implement competitive learning for spiking neural networks. Neural Comput. Appl. 2020, 32, 13479–13490. [Google Scholar] [CrossRef]
- Wang, Z.; Joshi, S.; Savel’ev, S.; Song, W.; Midya, R.; Li, Y.; Rao, M.; Yan, P.; Asapu, S.; Zhuo, Y.; et al. Fully memristive neural networks for pattern classification with unsupervised learning. Nat. Electron. 2018, 1, 137–145. [Google Scholar] [CrossRef]
- Pedretti, G.; Milo, V.; Ambrogio, S.; Carboni, R.; Bianchi, S.; Calderoni, A.; Ramaswamy, N.; Spinelli, A.; Ielmini, D. Memristive neural network for on-line learning and tracking with brain-inspired spike timing dependent plasticity. Sci. Rep. 2017, 7, 1–10. [Google Scholar] [CrossRef] [Green Version]
- Burkitt, A.N. A review of the integrate-and-fire neuron model: II. Inhomogeneous synaptic input and network properties. Biol. Cybern. 2006, 95, 97–112. [Google Scholar] [CrossRef]
- Bi, G.Q.; Poo, M.M. Synaptic modification by correlated activity: Hebb’s postulate revisited. Annu. Rev. Neurosci. 2001, 24, 139–166. [Google Scholar] [CrossRef] [Green Version]
- Diehl, P.U.; Cook, M. Unsupervised learning of digit recognition using Spike-Timing-Dependent Plasticity. Front. Comput. Neurosci. 2015, 9, 99. [Google Scholar] [CrossRef] [Green Version]
- Morrison, A.; Diesmann, M.; Gerstner, W. Phenomenological models of synaptic plasticity based on spike timing. Biol. Cybern. 2008, 98, 459–478. [Google Scholar] [CrossRef] [Green Version]
- Querlioz, D.; Dollfus, P.; Bichler, O.; Gamrat, C. Learning with memristive devices: How should we model their behavior? In Proceedings of the 2011 IEEE/ACM International Symposium on Nanoscale Architectures, San Diego, CA, USA, 8–9 June 2011; pp. 150–156. [Google Scholar] [CrossRef] [Green Version]
- Gerstner, W. A framework for spiking neuron models: The spike response model. Handb. Biol. Phys. 2001, 4, 469–516. [Google Scholar]
- Gerstner, W.; Kistler, W.M. Spiking Neuron Models: Single Neurons, Populations, Plasticity; Cambridge University Press: Cambridge, UK, 2002. [Google Scholar]
- Kunkel, S.; Morrison, A.; Weidel, P.; Eppler, J.M.; Sinha, A.; Schenck, W.; Schmidt, M.; Vennemo, S.B.; Jordan, J.; Peyser, A.; et al. NEST 2.12.0. 2017. Available online: https://doi.org/10.5281/zenodo.259534 (accessed on 13 October 2021).
- Gütig, R.; Sompolinsky, H. The tempotron: A neuron that learns spike timing-based decisions. Nat. Neurosci. 2006, 9, 420–428. [Google Scholar] [CrossRef]
- Yu, Q.; Tang, H.; Tan, K.C.; Yu, H. A brain-inspired spiking neural network model with temporal encoding and learning. Neurocomputing 2014, 138, 3–13. [Google Scholar] [CrossRef]
- Wang, X.; Hou, Z.G.; Lv, F.; Tan, M.; Wang, Y. Mobile robots’ modular navigation controller using spiking neural networks. Neurocomputing 2014, 134, 230–238. [Google Scholar] [CrossRef]
- Barto, A.G.; Sutton, R.S.; Anderson, C.W. Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Trans. Syst. Man Cybern. 1983, SMC-13, 834–846. [Google Scholar] [CrossRef]
- Masquelier, T.; Guyonneau, R.; Thorpe, S.J. Spike Timing Dependent Plasticity finds the start of repeating patterns in continuous spike trains. PLoS ONE 2008, 3, e1377. [Google Scholar] [CrossRef]
Task | Plasticity | , mV | , ms | F1, % | |||
---|---|---|---|---|---|---|---|
mean | min | max | |||||
Fisher’s Iris | STDP | 5 | 0.005 | 0 | 97 | 93 | 100 |
Fisher’s Iris | NC | 5 | 0.005 | 0 | 97 | 93 | 100 |
Fisher’s Iris | PPX | 3 | 0.005 | 0 | 97 | 93 | 100 |
Breast cancer | STDP | 8 | 0.005 | 3.2 | 94 | 89 | 97 |
Breast cancer | NC | 8 | 0.005 | 3.2 | 93 | 88 | 96 |
Breast cancer | PPX | 6 | 0.005 | 3.2 | 93 | 89 | 96 |
CartPole | STDP | 5 | 0.01 | 1.2 | 66 (199/200) | 65 | 68 |
CartPole | NC | 6 | 0.01 | 1.2 | 63 (199/200) | 62 | 65 |
CartPole | PPX | 5 | 0.01 | 1 | 60 (197/200) | 60 | 68 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Sboev, A.; Vlasov, D.; Rybka, R.; Davydov, Y.; Serenko, A.; Demin, V. Modeling the Dynamics of Spiking Networks with Memristor-Based STDP to Solve Classification Tasks. Mathematics 2021, 9, 3237. https://doi.org/10.3390/math9243237
Sboev A, Vlasov D, Rybka R, Davydov Y, Serenko A, Demin V. Modeling the Dynamics of Spiking Networks with Memristor-Based STDP to Solve Classification Tasks. Mathematics. 2021; 9(24):3237. https://doi.org/10.3390/math9243237
Chicago/Turabian StyleSboev, Alexander, Danila Vlasov, Roman Rybka, Yury Davydov, Alexey Serenko, and Vyacheslav Demin. 2021. "Modeling the Dynamics of Spiking Networks with Memristor-Based STDP to Solve Classification Tasks" Mathematics 9, no. 24: 3237. https://doi.org/10.3390/math9243237
APA StyleSboev, A., Vlasov, D., Rybka, R., Davydov, Y., Serenko, A., & Demin, V. (2021). Modeling the Dynamics of Spiking Networks with Memristor-Based STDP to Solve Classification Tasks. Mathematics, 9(24), 3237. https://doi.org/10.3390/math9243237