Spiking Neural Network with Linear Computational Complexity for Waveform Analysis in Amperometry
<p>Tonic spiking neuron response for the input current in the range of 0 ÷ 50 pA.</p> "> Figure 2
<p>Inhibition-induced spiking neuron response for an input current of −30 ÷ 70 pA.</p> "> Figure 3
<p>SNN architecture with linear computational complexity.</p> "> Figure 4
<p>The applied SNN response coding.</p> "> Figure 5
<p>Application of the described SNN in the task of analyzing data from CNT sensors.</p> "> Figure 6
<p>Amperometric waveform showing full vesicle fusion.</p> "> Figure 7
<p>Positive <span style="color:#0000FF">—</span> and negative <span style="color:#FF0000">—</span> patterns used in SNN training with the sampling parameter <math display="inline"><semantics> <mrow> <mi>N</mi> <mo>=</mo> <mn>20</mn> </mrow> </semantics></math>.</p> "> Figure 8
<p>Accuracy vs. weight mismatch.</p> ">
Abstract
:1. Introduction
2. Network Architecture
2.1. Thalamo-Based Neurons
2.2. Network Routing
3. Network Learning
Algorithm 1 Network mapping and routing. |
Reading the set:
Calculation of input weights:
Assigning output weight:
Assigning synapse capacitance:
Response coding:
|
4. Pattern Classification
4.1. Current-Mode Signals
4.2. Classifier Efficiency
4.3. Mismatch Analysis
5. Discussion
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
SNN | Spiking Neural Network |
CNT | Carbon NanoTube |
CMOS | Complementary Metal Oxide Semiconductor |
ADC | Analog-to-Digital Converter |
FPGA | Field-Programmable Gate Array |
GPU | Graphics Processing Unit |
STDP | Spike Timing-Dependent-Plasticity |
TS | Tonic Spiking |
IIS | Inhibition-Induced Spiking |
AFE | Analog Front-End |
SE | Square Error |
TP | True Positive |
TN | True Negative |
FP | False Positive |
FN | False Negative |
TUs | Time Units |
References
- Song, Z.; Cheng, J.; Chauhan, A.; Tilevich, E. Pushing Participatory Sensing Further to the Edge. In Proceedings of the 2019 IEEE International Conference on Edge Computing (EDGE), Milan, Italy, 8–13 July 2019. [Google Scholar]
- Banks, C.; Mortimer, R.; McIntosh, S. Electrochemistry; The Royal Society of Chemistry: London, UK, 2015. [Google Scholar]
- Wu, Q.; Zhang, Q.; Liu, B.; Li, Y.; Wu, X.; Kuo, S.; Zheng, L.; Wang, C.; Zhu, F.; Zhou, Z. Dynamin 1 Restrains Vesicular Release to a Subquantal Mode In Mammalian Adrenal Chromaffin Cells. J. Neurosci. 2019, 39, 199–211. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Szczęsny, S.; Kropidłowski, M.; Naumowicz, M. 0.50-V Ultra-Low-Power ΣΔ Modulator for Sub-nA Signal Sensing in Amperometry. IEEE Sens. J. 2020, 20, 5733–5740. [Google Scholar] [CrossRef]
- Harrison, R. MOSFET Operation in Weak and Moderate Inversion; EE5720; University of Utah: Salt Lake City, UT, USA, 2014; Available online: https://studylib.net/doc/18221859/mosfet-operation-in-weak-and-moderate-inversion (accessed on 11 April 2021).
- 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. Circ. Syst. II Express Briefs 2015, 62, 1088–1092. [Google Scholar] [CrossRef] [Green Version]
- Sourikopoulos, I.; Hedayat, S.; Loyez, C.; Danneville, F.; Hoel, V.; Mercier, E.; Cappy, A. A 4-fJ/Spike Artificial Neuron in 65 nm CMOS Technology. Front. Neurosci. 2017, 11, 123. [Google Scholar] [CrossRef] [Green Version]
- Nguyen, L.; Lin, D.; Lin, Z.; Cao, J. Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation. In Proceedings of the 2018 IEEE International Symposium on Circuits and Systems (ISCAS), Florence, Italy, 27–30 May 2018. [Google Scholar]
- Thompson, N.C.; Greenewald, K.; Lee, K.; Manso, G.F. The Computational Limits of Deep Learning. MIT. 2020. Available online: https://arxiv.org/abs/2007.05558 (accessed on 11 April 2021).
- Rowcliffe, P.; Feng, J. Buxton, Spiking Perceptrons. IEEE Trans. Neural Netw. 2006, 17, 803–807. [Google Scholar] [CrossRef] [PubMed]
- Davies, M.; Srinivasa, N.; Lin, T.; Chinya, G.; Joshi, P.; Lines, A.; Wild, A.; Wang, H. Loihi: A Neuromorphic Manycore Processor with On-Chip Learning. IEEE Micro 2018. [Google Scholar] [CrossRef]
- Cheng, H.P.; Wen, W.; Wu, C.; Li, S.; Li, H.H.; Chen, Y. Understanding the design of IBM neurosynaptic system and its tradeoffs: A user perspective. In Proceedings of the Design, Automation & Test in Europe Conference & Exhibition, Lausanne, Switzerland, 27–31 March 2017. [Google Scholar]
- Lymer, J.; Prescott, I.A.; Levy, R. Microstimulation-induced inhibition of thalamic reticular nucleus in non-human primates. Exp. Brain Res. 2019, 237, 1511–1520. [Google Scholar] [CrossRef] [PubMed]
- Abusnaina, A.A.; Abdullah, R. Spiking Neuron Models: A Review. Int. J. Digit. Content Technol. Its Appl. 2014, 8, 14–21. [Google Scholar]
- Izhikevich, E.M. Which Model to Use for Cortical Spiking Neurons? IEEE Trans. Neural Netw. 2004, 15, 1063–1070. [Google Scholar] [CrossRef]
- Corradi, F.; Adriaans, G.; Stuijk, S. Gyro: A Digital Spiking Neural Network Architecture for Multi-Sensory Data Analytics. In Proceedings of the DroneSE and RAPIDO ’21: 2021 Drone Systems Engineering and Rapid Simulation and Performance Evaluation: Methods and Tools Proceedings, Budapest, Hungary, 20 January 2021. [Google Scholar]
- Hoyoung, T.; Heetak, K.; Hyeonseong, K.; Park, J. Spike Counts Based Low Complexity SNN Architecture with Binary Synapse. IEEE Trans. Biomed. Circ. Syst. 2019, 13, 1664–1677. [Google Scholar]
- Sulaiman, M.B.G.; Juang, K.C.; Lu, C.C. Weight Quantization in Spiking Neural Network for Hardware Implementation. In Proceedings of the 2020 IEEE International Conference on Consumer Electronics, Taoyuan, Taiwan, 28–30 September 2020. [Google Scholar]
- Diehl, P.U.; Cook, M. Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Front. Comput. Neurosci. 2015, 9, 99. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Nowak, L.G.; Sanchez-Vives, M.V.; McCormick, D.A. Influence of low and high frequency inputs on spike timing in visual cortical neurons. Cereb. Cortex 1997, 7, 487–501. [Google Scholar] [CrossRef] [Green Version]
- Tazerart, S.; Mitchell, D.E.; Miranda-Rottmann, S.; Araya, R. A spike-timing-dependent plasticity rule for dendritic spines. Nat. Commun. 2020, 11, 1–16. [Google Scholar] [CrossRef]
- Schrauwen, B.; Campenhout, J.V. Improving spikeprop: Enhancements to an error-backpropagation rule for spiking neural networks. In Proceedings of the 15th ProRISC Workshop, Veldhoven, The Netherlands, 25–26 November 2004; Volume 11, pp. 301–305. [Google Scholar]
- Ponulak, F.; Kasiński, A. I Introduction to spiking neural networks: Information processing, learning and applications. Acta Neurobiol. Exp. 2011, 17, 409–433. [Google Scholar]
- Fathail, H.; Cans, A.-S. Amperometry methods for monitoring vesicular quantal size and regulation of exocytosis release. Pflugers Arch. 2018, 470, 125–134. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Goudah, G.; Suliman, S.M.A.; Elfaki, E.A. Carbon nanotubes: Challenges and opportunities. In Proceedings of the International Conference on Computing, Electrical And Electronic Engineering (ICCEEE), Khartoum, Sudan, 26–28 August 2013. [Google Scholar]
- Li, Y.; Tsurumaki-Fukuchi, A.; Arita, M.; Morie, T.; Takahashi, Y. Switching Current of Ta2O5-Based Resistive Analog Memories. In Proceedings of the 2019 Silicon Nanoelectronics Workshop (SNW), Kyoto, Japan, 9–10 June 2019. [Google Scholar]
- Lucien, F.; Leong, H.S. The role of extracellular vesicles in cancer microenvironment and metastasis: Myths and challenges. Biochem. Soc. Trans. 2019, 47, 273–280. [Google Scholar] [CrossRef] [PubMed]
- Zoltowska, K.M.; Maesako, M.; Lushnikova, I.; Takeda, S.; Keller, L.J.; Skibo, G.; Hyman, B.T.; Berezovska, O. Dynamic presenilin 1 and synaptotagmin 1 interaction modulates exocytosis and amyloid β production. Mol. Neurodegener. 2017, 12, 15. [Google Scholar] [CrossRef] [Green Version]
- Trampert, D.C.; Nathanson, M.H. Regulation of bile secretion by calcium signaling in health and diseas. Biochim. Biophys. Acta BBA Mol. Cell Res. 2018, 1865 Pt B, 1761–1770. [Google Scholar] [CrossRef]
- To, W.K.L.; Kumar, P.; Marshall, J.M. Hypoxia is an effective stimulus for vesicular release of ATP from human umbilical vein endothelial cells. Placenta 2015, 36, 759–766. [Google Scholar]
- Michels, A.; Albánez, S.; Mewburn, J.; Nesbitt, K.; Gould, T.J.; Liaw, P.C.; James, P.D.; Swystun, L.L.; Lillicrap, D. Histones link inflammation and thrombosis through the induction of Weibel-Palade body exocytosis. J. Thromb. Haemost. 2016, 14, 2274–2286. [Google Scholar] [CrossRef]
- Hoogstraaten, R.I.; van Keimpema, L.; Toonen, R.F.; Verhage, M. Tetanus insensitive VAMP2 differentially restores synaptic and dense core vesicle Fusion in tetanus neurotoxin treated neurons. Sci. Rep. 2020, 10, 10913. [Google Scholar] [CrossRef]
- Li, J.; Meyyappan, M.; Cassell, A.M. National Aeronautics and Space Administration NASA, Biochemical Sensors Using Carbon Nanotube Arrays. U.S. Patent 7939734B1, 10 May 2011. [Google Scholar]
- Morie, T. CMOS circuits and nanodevices for spike based neural computing. In Proceedings of the 2015 IEEE International Meeting for Future of Electron Devices, Kansai (IMFEDK), Kyoto, Japan, 4–5 June 2015. [Google Scholar]
- Basu, A.; Hasler, P.E. Nullcline-based design of a silicon neuron. IEEE Trans. Circ. Syst. I Regul. Pap. 2010, 57, 2938–2947. [Google Scholar] [CrossRef]
- Joubert, A.; Belhadj, B.; Temam, O.; Heliot, R. Hardware spiking neurons design: Analog or digital? In Proceedings of the 2012 International Joint Conference on Neural Networks, Brisbane, QLD, Australia, 10–15 June 2012. [Google Scholar]
- Szczęsny, S. Current-Mode FPAA with CMRR Elimination and Low Sensitivity to Mismatch. Circ. Syst. Signal Process. 2017, 36, 2672–2696. [Google Scholar] [CrossRef] [Green Version]
- Yuan, X.; Shimizu, T.; Mahalingam, U.; Brown, J.S.; Habib, K.Z.; Tekleab, D.G.; Su, T.; Satadru, S.; Olsen, C.M.; Rim, K.; et al. Transistor Mismatch Properties in Deep-Submicrometer CMOS Technologies. IEEE Trans. Electron Devices 2011, 58, 335–342. [Google Scholar] [CrossRef]
- Haberler, M.; Siegl, I.; Steffan, C.; Auer, M. Mismatch Reduction Techniques for Current-Mirror Based Potentiostats. In Proceedings of the 2020 43rd International Convention on Information, Communication and Electronic Technology (MIPRO), Opatija, Croatia, 28 September–2 October 2020. [Google Scholar]
- Acero, C.; Feltham, D.; Liu, Y.; Moghaddam, E.; Mukherjee, N.; Patyra, M.; Rajski, J.; Reddy, S.M.; Tyszer, J.; Zawada, J. Embedded Deterministic Test Points. IEEE Trans. Very Large Scale Integr. VLSI Syst. 2017, 25, 2949–2961. [Google Scholar] [CrossRef]
- Szczęsny, S.; Huderek, D. 60 pW 20 m size CMOS implementation of an actual soma membrane. J. Comput. Electron. 2020, 19, 242–252. [Google Scholar] [CrossRef]
- Szczęsny, S. High Speed and Low Sensitive Current-Mode CMOS Perceptron. Microelectron. Eng. 2016, 165, 41–51. [Google Scholar] [CrossRef]
- Handkiewicz, A. Mixed-Signal Systems: A Guide to CMOS Circuit Design; Wiley: Hoboken, NJ, USA, 2002. [Google Scholar]
- 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, 4, 1–11. [Google Scholar] [CrossRef] [Green Version]
Patterns | (ms) | (ms) | SE | |
---|---|---|---|---|
positive * | 1 | 3.0 | 3.0 | 0 |
2 | 3.0 | 3.0 | 0 | |
3 | 3.0 | 3.0 | 0 | |
… | … | … | … | |
21 | 3.0 | 3.0 | 0 | |
22 | 4.0 | 5.0 | 5 | |
23 | 4.0 | 5.0 | 5 | |
… | … | … | … | |
38 | 4.0 | 6.0 | 10 | |
39 | 4.0 | 6.0 | 10 | |
40 | 4.0 | 6.0 | 10 | |
negative | 1 | 5.0 | 7.0 | 20.0 |
2 | 8.0 | 4.0 | 26.0 | |
3 | 8.0 | 5.0 | 29.0 | |
4 | 8.0 | 5.0 | 29.0 | |
5 | 8.0 | 5.0 | 29.0 | |
6 | 9.0 | 4.0 | 37.0 | |
… | … | … | … | |
36 | 18.0 | 15.0 | 369.0 | |
37 | 18.0 | 15.0 | 369.0 | |
38 | 19.0 | 15.0 | 400.0 | |
39 | 25.0 | 13.0 | 584.0 | |
40 | 27.0 | 8.0 | 601.0 | |
* mode = [3.0, 3.0]. |
SNN | TS | IIS | TP | TN | FP | FN | ACC | COMPLEX |
---|---|---|---|---|---|---|---|---|
40-1 | 35 | 5 | 40 | 40 | 0 | 0 | 1 | 40v + 166c |
35-1 | 31 | 4 | 40 | 40 | 0 | 0 | 1 | 35v + 146c |
30-1 | 26 | 4 | 40 | 40 | 0 | 0 | 1 | 30v + 126c |
25-1 | 22 | 3 | 40 | 40 | 0 | 0 | 1 | 25v + 106c |
20-1 | 17 | 3 | 40 | 40 | 0 | 0 | 1 | 20v + 86c |
15-1 | 13 | 2 | 40 | 38 | 2 | 0 | 0.975 | 15v + 66c |
10-1 | 9 | 1 | 40 | 37 | 3 | 0 | 0.9625 | 10v + 46c |
Period (ms) | ACC | |
---|---|---|
resonant burst coding | 10 | 0.783 |
coding by synchrony | 5 | 0.798 |
phase coding | 12 | 0.941 |
time to first spike | 4 | 0.946 |
two latencies | 10 | 1 |
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
Szczęsny, S.; Huderek, D.; Przyborowski, Ł. Spiking Neural Network with Linear Computational Complexity for Waveform Analysis in Amperometry. Sensors 2021, 21, 3276. https://doi.org/10.3390/s21093276
Szczęsny S, Huderek D, Przyborowski Ł. Spiking Neural Network with Linear Computational Complexity for Waveform Analysis in Amperometry. Sensors. 2021; 21(9):3276. https://doi.org/10.3390/s21093276
Chicago/Turabian StyleSzczęsny, Szymon, Damian Huderek, and Łukasz Przyborowski. 2021. "Spiking Neural Network with Linear Computational Complexity for Waveform Analysis in Amperometry" Sensors 21, no. 9: 3276. https://doi.org/10.3390/s21093276
APA StyleSzczęsny, S., Huderek, D., & Przyborowski, Ł. (2021). Spiking Neural Network with Linear Computational Complexity for Waveform Analysis in Amperometry. Sensors, 21(9), 3276. https://doi.org/10.3390/s21093276