Analog Implementation of a Spiking Neuron with Memristive Synapses for Deep Learning Processing
Abstract
1. Introduction
2. Materials and Methods
2.1. Neuron Modeling
2.2. Memristor Modeling
Vourkas Memristor Model
Listing 1. SPICE code for the Vourkas macromodel. |
2.3. Synaptic Weight Adjustment in Neurons
2.3.1. Long-Term Potentiation and Long-Term Depression on Memristive Synapses
2.3.2. Spike-Timing-Dependent Plasticity
2.4. Analog Leaky Integrate-and-Fire Functional Blocks and Control Signals
Phase Control for Reconfiguration of the LIF Neuron
2.5. Electrical Characteristics of the Block Components of the LIF Neuron
2.5.1. Integration/Buffer and Comparator Module
2.5.2. Selection of Transmission Gates Modules
2.5.3. Spiking Generator Block Design
- The commercial memristors by Knowm exhibit the greatest change in memristance at a low frequency (1 Hz) and the smallest change at a high frequency (1 KHz) [42].
- A total relaxation time of 1.25 ms is within the absolute refractory period of mammal neurons, where neurons cannot generate new output spikes [43], contributing to sparse computing with low power.
3. Results
3.1. Electrical Simulation of the LIF Neuron
Algorithm 1: Least squares regression algorithm for logarithm fitting. |
|
3.2. Hardware Implementation of the LIF Neuron
Methodology for the Characterization of the Physical LIF Neuron
3.3. Simulation of the Synaptic Weight Adjustment of a Memristive Synapse
3.3.1. Long-Term Potentiation on Memristive Synapse
3.3.2. Spike-Timing-Dependent Plasticity (STDP) Process on a Memristive Synapse
4. Conclusions
Future Work
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
Opamp | Operational amplifier |
LIF | Leaky integrate-and-fire |
STDP | Spike timing-dependent plasticity |
LTP | Long-term potentiation |
LTD | Long-term depression |
Appendix A
References
- Brown, T.B.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; et al. Language Models are Few-Shot Learners. arXiv 2020, arXiv:2005.14165. [Google Scholar]
- Ramesh, A.; Dhariwal, P.; Nichol, A.; Chu, C.; Chen, M. Hierarchical Text-Conditional Image Generation with CLIP Latents. arXiv 2022, arXiv:2204.06125. [Google Scholar]
- Luccioni, A.S.; Viguier, S.; Ligozat, A.L. Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model. arXiv 2022, arXiv:2211.02001. [Google Scholar]
- Mead, C.; Ismail, M. (Eds.) Analog VLSI Implementation of Neural Systems; Springer: New York, NY, USA, 1989. [Google Scholar] [CrossRef]
- Canales-Verdial, J.I.; Wagner, J.R.; Schmucker, L.A.; Wetzel, M.; Proctor, P.; Carson, M.; Meng, J.; Withers, N.J.; Harris, C.T.; Nogan, J.J.; et al. Energy-Efficient Neuromorphic Architectures for Nuclear Radiation Detection Applications. Sensors 2024, 24, 2144. [Google Scholar] [CrossRef] [PubMed]
- Udaya Mohanan, K. Resistive Switching Devices for Neuromorphic Computing: From Foundations to Chip Level Innovations. Nanomaterials 2024, 14, 527. [Google Scholar] [CrossRef]
- Vohra, S.K.; Thomas, S.A.; Sakare, M.; Das, D.M. Circuit implementation of on-chip trainable spiking neural network using CMOS based memristive STDP synapses and LIF neurons. Integration 2024, 95, 102122. [Google Scholar] [CrossRef]
- Maass, W. Networks of spiking neurons: The third generation of neural network models. Neural Netw. 1997, 10, 1659–1671. [Google Scholar] [CrossRef]
- Rana, A.; Kim, K.K. Electrocardiography Classification with Leaky Integrate-and-Fire Neurons in an Artificial Neural Network-Inspired Spiking Neural Network Framework. Sensors 2024, 24, 3426. [Google Scholar] [CrossRef] [PubMed]
- Padovano, D.; Carpegna, A.; Savino, A.; Di Carlo, S. SpikeExplorer: Hardware-Oriented Design Space Exploration for Spiking Neural Networks on FPGA. Electronics 2024, 13, 1744. [Google Scholar] [CrossRef]
- Passias, A.; Tsakalos, K.A.; Kansizoglou, I.; Kanavaki, A.M.; Gkrekidis, A.; Menychtas, D.; Aggelousis, N.; Michalopoulou, M.; Gasteratos, A.; Sirakoulis, G.C. A Biologically Inspired Movement Recognition System with Spiking Neural Networks for Ambient Assisted Living Applications. Biomimetics 2024, 9, 296. [Google Scholar] [CrossRef]
- Costandi, M. Neuroplasticity; The MIT Press Essential Knowledge Series; MIT Press: London, UK, 2016. [Google Scholar]
- Chakraborty, I.; Jaiswal, A.; Saha, A.K.; Gupta, S.K.; Roy, K. Pathways to efficient neuromorphic computing with non-volatile memory technologies. Appl. Phys. Rev. 2020, 7, 021308. [Google Scholar] [CrossRef]
- Kornijcuk, V.; Lim, H.; Seok, J.Y.; Kim, G.; Kim, S.K.; Kim, I.; Choi, B.J.; Jeong, D.S. Leaky Integrate-and-Fire Neuron Circuit Based on Floating-Gate Integrator. Front. Neurosci. 2016, 10, 212. [Google Scholar] [CrossRef] [PubMed]
- Linares-Barranco, B.; Serrano-Gotarredona, T.; Camuñas-Mesa, L.; Perez-Carrasco, J.; Zamarreño-Ramos, C.; Masquelier, T. On Spike-Timing-Dependent-Plasticity, Memristive Devices, and Building a Self-Learning Visual Cortex. Front. Neurosci. 2011, 5, 26. [Google Scholar] [CrossRef]
- Chua, L. Memristor-The missing circuit element. IEEE Trans. Circuit Theory 1971, 18, 507–519. [Google Scholar] [CrossRef]
- AI hardware has an energy problem. Nat. Electron. 2023, 6, 463. [CrossRef]
- Feng, R.; Li, J.; Xie, S.; Mao, X. Efficient Training Method for Memristor-Based Array Using 1T1M Synapse. IEEE Trans. Circuits Syst. II Express Briefs 2023, 70, 2410–2414. [Google Scholar] [CrossRef]
- Wang, D.; Xu, J.; Li, F.; Zhang, L.; Cao, C.; Stathis, D.; Lansner, A.; Hemani, A.; Zheng, L.R.; Zou, Z. A Memristor-Based Learning Engine for Synaptic Trace-Based Online Learning. IEEE Trans. Biomed. Circuits Syst. 2023, 17, 1153–1165. [Google Scholar] [CrossRef] [PubMed]
- Barraj, I.; Mestiri, H.; Masmoudi, M. Overview of Memristor-Based Design for Analog Applications. Micromachines 2024, 15, 505. [Google Scholar] [CrossRef]
- Hodgkin, A.L.; Huxley, A.F. A quantitative description of membrane current and its application to conduction and excitation in nerve. J. Physiol. 1952, 117, 500–544. [Google Scholar] [CrossRef]
- Gerstner, W.; Kistler, W.M.; Naud, R.; Paninski, L. Neuronal Dynamics: From Single Neurons to Networks and Models of Cognition; Cambridge University Press: Cambridge, UK, 2014. [Google Scholar] [CrossRef]
- Wang, J.; Mao, S.; Zhu, S.; Hou, W.; Yang, F.; Sun, B. Biomemristors-based synaptic devices for artificial intelligence applications. Org. Electron. 2022, 106, 106540. [Google Scholar] [CrossRef]
- Strukov, D.B.; Snider, G.S.; Stewart, D.R.; Williams, R.S. The missing memristor found. Nature 2008, 453, 80–83. [Google Scholar] [CrossRef]
- Joglekar, Y.N.; Wolf, S.J. The elusive memristor: Properties of basic electrical circuits. Eur. J. Phys. 2009, 30, 661. [Google Scholar] [CrossRef]
- Vourkas, I.; Sirakoulis, G.C. Memristor-Based Nanoelectronic Computing Circuits and Architectures; Springer International Publishing: Berlin/Heidelberg, Germany, 2016. [Google Scholar] [CrossRef]
- Hebb, D.O. The Organization of Behavior; Psychology Press: Philadelphia, PA, USA, 2002. [Google Scholar]
- Dayan, P.; Abbott, L.F. Theoretical Neuroscience; Computational neuroscience; MIT Press: London, UK, 2001. [Google Scholar]
- Caporale, N.; Dan, Y. Spike Timing–Dependent Plasticity: A Hebbian Learning Rule. Annu. Rev. Neurosci. 2008, 31, 25–46. [Google Scholar] [CrossRef]
- Rastogi, M.; Lu, S.; Islam, N.; Sengupta, A. On the Self-Repair Role of Astrocytes in STDP Enabled Unsupervised SNNs. Front. Neurosci. 2021, 14, 603796. [Google Scholar] [CrossRef]
- Zhang, J. Gradient Descent based Optimization Algorithms for Deep Learning Models Training. arXiv 2019. [Google Scholar] [CrossRef]
- Tholeti, T.; Kalyani, S. Concavifiability and convergence: Necessary and sufficient conditions for gradient descent analysis. arXiv 2019. [Google Scholar] [CrossRef]
- Lobo, J.L.; Del Ser, J.; Bifet, A.; Kasabov, N. Spiking Neural Networks and online learning: An overview and perspectives. Neural Netw. 2020, 121, 88–100. [Google Scholar] [CrossRef] [PubMed]
- Rozenberg, M.J.; Schneegans, O.; Stoliar, P. An ultra-compact leaky-integrate-and-fire model for building spiking neural networks. Sci. Rep. 2019, 9, 11123. [Google Scholar] [CrossRef] [PubMed]
- Wu, X.; Saxena, V.; Zhu, K.; Balagopal, S. A CMOS Spiking Neuron for Brain-Inspired Neural Networks With Resistive Synapses and In Situ Learning. IEEE Trans. Circuits Syst. II Express Briefs 2015, 62, 1088–1092. [Google Scholar] [CrossRef]
- Analog Devices. 500 MHz Ultra-Low Bias Current FET Input Op Amp; Analog Devices Inc.: Norwood, MA, USA, 2017. [Google Scholar]
- Analog Devices. High Speed, Low Cost, Op Amp; Analog Devices Inc.: Norwood, MA, USA, 2006. [Google Scholar]
- Banerjee, W.; Nikam, R.D.; Hwang, H. Prospect and challenges of analog switching for neuromorphic hardware. Appl. Phys. Lett. 2022, 120, 060501. [Google Scholar] [CrossRef]
- Analog Devices. CMOS, ±5 V/+5 V, 4 Ω, Single SPDT Switches; Analog Devices Inc.: Norwood, MA, USA, 2011. [Google Scholar]
- Analog Devices. CMOS, 2.5 Ω Low Voltage, Triple/Quad SPDT Switches; Analog Devices Inc.: Norwood, MA, USA, 2001. [Google Scholar]
- Analog Devices. 2.5 Ω, 1.8 V to 5.5 V, ±2.5 V Triple/Quad SPDT Switches in Chip Scale Packages; Analog Devices Inc.: Norwood, MA, USA, 2015. [Google Scholar]
- Knowm. Memristors to Machine Intelligence. Available online: https://knowm.org/ (accessed on 10 February 2024).
- Maida, A. Chapter 2—Cognitive Computing and Neural Networks: Reverse Engineering the Brain. In Cognitive Computing: Theory and Applications; Gudivada, V.N., Raghavan, V.V., Govindaraju, V., Rao, C., Eds.; Handbook of Statistics; Elsevier: Amsterdam, The Netherlands, 2016; Volume 35, pp. 39–78. [Google Scholar] [CrossRef]
- Butts, D.A.; Goldman, M.S. Tuning Curves, Neuronal Variability, and Sensory Coding. PLoS Biol. 2006, 4, e92. [Google Scholar] [CrossRef] [PubMed]
- Keysight. InfiniiVision X-Series Oscilloscope LabVIEW Instrument Drivers. Available online: https://www.keysight.com (accessed on 10 February 2024).
- Stoliar, P.; Yamada, H.; Toyosaki, Y.; Sawa, A. Spike-shape dependence of the spike-timing dependent synaptic plasticity in ferroelectric-tunnel-junction synapses. Sci. Rep. 2019, 9, 17740. [Google Scholar] [CrossRef] [PubMed]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 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
Ramirez-Morales, R.R.; Ponce-Ponce, V.H.; Molina-Lozano, H.; Sossa-Azuela, H.; Islas-García, O.; Rubio-Espino, E. Analog Implementation of a Spiking Neuron with Memristive Synapses for Deep Learning Processing. Mathematics 2024, 12, 2025. https://doi.org/10.3390/math12132025
Ramirez-Morales RR, Ponce-Ponce VH, Molina-Lozano H, Sossa-Azuela H, Islas-García O, Rubio-Espino E. Analog Implementation of a Spiking Neuron with Memristive Synapses for Deep Learning Processing. Mathematics. 2024; 12(13):2025. https://doi.org/10.3390/math12132025
Chicago/Turabian StyleRamirez-Morales, Royce R., Victor H. Ponce-Ponce, Herón Molina-Lozano, Humberto Sossa-Azuela, Oscar Islas-García, and Elsa Rubio-Espino. 2024. "Analog Implementation of a Spiking Neuron with Memristive Synapses for Deep Learning Processing" Mathematics 12, no. 13: 2025. https://doi.org/10.3390/math12132025
APA StyleRamirez-Morales, R. R., Ponce-Ponce, V. H., Molina-Lozano, H., Sossa-Azuela, H., Islas-García, O., & Rubio-Espino, E. (2024). Analog Implementation of a Spiking Neuron with Memristive Synapses for Deep Learning Processing. Mathematics, 12(13), 2025. https://doi.org/10.3390/math12132025