research-article

Efficient Optimized Spike Encoding of Multivariate Time-series

Authors:

Dighanchal Banerjee,

Arun M. George,

Arijit MukherjeeAuthors Info & Claims

NICE '22: Proceedings of the 2022 Annual Neuro-Inspired Computational Elements Conference

Pages 22 - 28

https://doi.org/10.1145/3517343.3517349

Published: 03 May 2022 Publication History

Abstract

Spiking neural network (SNN) are emerging as a bio-plausible AI paradigm best suited for energy constrained edge use case. However the performance of SNNs largely depends upon the information content of the spike trains generated from real valued data by spike encoders - which are often found to be lossy. In this work, we have proposed a mutual information based optimisation technique of spike encoding to be used on multivariate time-series data. When tested using a spiking reservoir network, the technique is found to increase the network performance by upto 6% while performing classification task on different multivariate sensor data having variety of attributes.

References

[1]

Fevzi Alimoğlu and Ethem Alpaydin. 2001. Combining multiple representations for pen-based handwritten digit recognition. Turkish Journal of Electrical Engineering & Computer Sciences 9, 1(2001), 1–12.

[2]

Anthony J. Bagnall, Hoang Anh Dau, Jason Lines, Michael Flynn, James Large, Aaron Bostrom, Paul Southam, and Eamonn J. Keogh. 2018. The UEA multivariate time series classification archive, 2018. ArXiv abs/1811.00075(2018).

[3]

Dighanchal Banerjee, Sounak Dey, Arun M George, and Arijit Mukherjee. 2020. Efficient Optimized Spike Encoding for Spiking Neural Networks. In 12th OPTML workshop at 35th Conference on Neural Information Processing Systems (NeurIPS). NeurIPS Foundation, Montreal.

[4]

Benjamin Blankertz, Gabriel Curio, and Klaus-Robert Müller. 2001. Classifying Single Trial EEG: Towards Brain Computer Interfacing. In Proceedings of the 14th International Conference on Neural Information Processing Systems: Natural and Synthetic (Vancouver, British Columbia, Canada) (NIPS’01). MIT Press, Cambridge, MA, USA, 157–164.

[5]

Alexander Borst and Frédéric E Theunissen. 1999. Information theory and neural coding. Nature neuroscience 2, 11 (1999), 947–957.

[6]

Bruno Cessac, Hélène Paugam-Moisy, and Thierry Viéville. 2010. Overview of facts and issues about neural coding by spikes. Journal of Physiology-Paris 104, 1-2 (2010), 5–18.

[7]

Bruno Cessac, Horacio Rostro, Juan-Carlos Vasquez, and Thierry Viéville. 2009. How Gibbs distributions may naturally arise from synaptic adaptation mechanisms. A model-based argumentation. Journal of Statistical Physics 136, 3 (2009), 565–602.

[8]

Long Cheng, Yang Liu, Zeng-Guang Hou, Min Tan, Dajun Du, and Minrui Fei. 2021. A rapid spiking neural network approach with an application on hand gesture recognition. IEEE Transactions on Cognitive and Developmental Systems 13, 1(2021), 151–161.

[9]

H. G. Eyherabide. 2016. Neural stochastic codes, encoding and decoding. ArXiv abs/1611.05080(2016).

[10]

Haowen Fang, Amar Shrestha, and Qinru Qiu. 2020. Multivariate time series classification using spiking neural networks. In 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, USA, 1–7.

[11]

Arun M. George, Dighanchal Banerjee, Sounak Dey, Arijit Mukherjee, and P. Balamurali. 2020. A Reservoir-based Convolutional Spiking Neural Network for Gesture Recognition from DVS Input. In 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, USA, 1–9.

[12]

Wulfram Gerstner and Werner M Kistler. 2002. Mathematical formulations of Hebbian learning. Biological cybernetics 87, 5-6 (2002), 404–415.

[13]

A. L. Goldberger, L. A. N. Amaral, L. Glass, J. M. Hausdorff, P. Ch. Ivanov, R. G. Mark, J. E. Mietus, G. B. Moody, C.-K. Peng, and H. E. Stanley. 2000 (June 13). PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation 101, 23 (2000 (June 13)), e215–e220. Circulation Electronic Pages: http://circ.ahajournals.org/content/101/23/e215.full 1085218;

[14]

Hananel Hazan, Daniel J Saunders, Hassaan Khan, Darpan T Sanghavi, Hava T Siegelmann, and Robert Kozma. 2018. BindsNET: A machine learning-oriented spiking neural networks library in Python. Frontiers in neuroinformatics 12 (2018), 89.

[15]

Michael Hough, Hugo De Garis, Michael Korkin, Felix Gers, and Norberto Eiji Nawa. 1999. SPIKER: Analog waveform to digital spiketrain conversion in ATR’s artificial brain (cam-brain) project. In International Conference on Robotics and Artificial Life, Vol. 92. ICAROB, Japan.

[16]

Herbert Jaeger and Harald Haas. 2004. Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication. Science 304, 5667 (2004), 78–80.

[17]

Nikola Kasabov, Nathan Matthew Scott, Enmei Tu, Stefan Marks, Neelava Sengupta, Elisa Capecci, Muhaini Othman, Maryam Gholami Doborjeh, Norhanifah Murli, Reggio Hartono, 2016. Evolving spatio-temporal data machines based on the NeuCube neuromorphic framework: design methodology and selected applications. Neural Networks 78(2016), 1–14.

Digital Library

[18]

Andrzej S Kucik and Gabriele Meoni. 2021. Investigating Spiking Neural Networks for Energy-Efficient On-Board AI Applications. A Case Study in Land Cover and Land Use Classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, USA, 2020–2030.

[19]

L Lapicque. 1907. Recherches quantitatives sur l’excitation electrique des nerfs traitée comme une polarization. J. Physiol. Pathol. Gen. 9 (1907), 620–635.

[20]

James Large, E Kate Kemsley, Nikolaus Wellner, Ian Goodall, and Anthony Bagnall. 2018. Detecting forged alcohol non-invasively through vibrational spectroscopy and machine learning. In Pacific-Asia conference on knowledge discovery and data mining. Springer International Publishing, Cham, 298–309.

[21]

Cheng-Han Li, Tobi Delbruck, and Shih-Chii Liu. 2012. Real-time speaker identification using the AEREAR2 event-based silicon cochlea. In 2012 IEEE international symposium on circuits and systems (ISCAS). IEEE, USA, 1159–1162.

[22]

Wolfgang Maass, Thomas Natschläger, and Henry Markram. 2002. Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations. Neural Computation 14, 11 (2002), 2531–2560.

Digital Library

[23]

GE Moody. 2004. Spontaneous termination of atrial fibrillation: a challenge from physionet and computers in cardiology 2004. In Computers in Cardiology, 2004. IEEE, USA, 101–104.

[24]

Priyadarshini Panda and Narayan Srinivasa. 2018. Learning to recognize actions from limited training examples using a recurrent spiking neural model. Frontiers in neuroscience 12 (2018), 126.

[25]

Leo Pape, Jornt de Gruijl, and Marco Wiering. 2008. Democratic liquid state machines for music recognition. In Speech, Audio, Image and Biomedical Signal Processing using Neural Networks. Springer, Cham, 191–215.

[26]

Donald H Perkel, George L Gerstein, and George P Moore. 1967. Neuronal spike trains and stochastic point processes: I. The single spike train. Biophysical journal 7, 4 (1967), 391–418.

[27]

Balint Petro, Nikola Kasabov, and Rita M Kiss. 2019. Selection and optimization of temporal spike encoding methods for spiking neural networks. IEEE transactions on neural networks and learning systems 31, 2(2019), 358–370.

[28]

Benjamin Schrauwen and Jan Van Campenhout. 2003. BSA, a fast and accurate spike train encoding scheme. In Proceedings of the International Joint Conference on Neural Networks, 2003., Vol. 4. IEEE, USA, 2825–2830.

[29]

Sabyasachi Shivkumar, Richard Lange, Ankani Chattoraj, and Ralf Haefner. 2018. A probabilistic population code based on neural samples. In Advances in Neural Information Processing Systems, Vol. 31. Curran Associates, Inc., Montréal, Canada, 7070–7079.

[30]

Aboozar Taherkhani, Georgina Cosma, and Thomas Martin McGinnity. 2019. Optimization of output spike train encoding for a spiking neuron based on its spatio–temporal input pattern. IEEE Transactions on Cognitive and Developmental Systems 12, 3(2019), 427–438.

[31]

Carlos D. Virgilio G., Juan H. Sossa A., Javier M. Antelis, and Luis E. Falcón. 2020. Spiking Neural Networks applied to the classification of motor tasks in EEG signals. Neural Networks 122(2020), 130 – 143. https://doi.org/10.1016/j.neunet.2019.09.037

Digital Library

[32]

Zhanglu Yan, Jun Zhou, and Weng-Fai Wong. 2021. Energy efficient ECG classification with spiking neural network. Biomedical Signal Processing and Control 63 (2021), 102170. https://doi.org/10.1016/j.bspc.2020.102170

[33]

Emre Yılmaz, Ozgür Bora Gevrek, Jibin Wu, Yuxiang Chen, Xuanbo Meng, and Haizhou Li. 2020. Deep convolutional spiking neural networks for keyword spotting. In Proceedings of Interspeech. ISCA, France, 2557–2561.

[34]

Anguo Zhang, Wei Zhu, and Ming Liu. 2017. Self-organizing reservoir computing based on spiking-timing dependent plasticity and intrinsic plasticity mechanisms. In 2017 Chinese Automation Congress (CAC). IEEE, USA, 6189–6193.

Cited By

Banerjee DDey SPal A(2024)Atrial Fibrillation Detector from ECG on Wearable Edge Devices using Spiking Neural Networks2024 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN60899.2024.10650023(1-8)Online publication date: 30-Jun-2024
https://doi.org/10.1109/IJCNN60899.2024.10650023
Stasenko SLebedev ALevanova TKazantsev V(2024)Study of the Influence of Macroparameters of a Spiking Neural Network on the Quality of Image Recognition2024 Sixth International Conference Neurotechnologies and Neurointerfaces (CNN)10.1109/CNN63506.2024.10705826(216-220)Online publication date: 19-Sep-2024
https://doi.org/10.1109/CNN63506.2024.10705826
Kahali SDey SKadway CMukherjee APal ASuri M(2023)Low-Power Lossless Image Compression on Small Satellite Edge using Spiking Neural Network2023 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN54540.2023.10191704(1-8)Online publication date: 18-Jun-2023
https://doi.org/10.1109/IJCNN54540.2023.10191704
Show More Cited By

Recommendations

Efficient Spike Encoding Algorithms for Neuromorphic Speech Recognition
ICONS '22: Proceedings of the International Conference on Neuromorphic Systems 2022

Spiking Neural Networks are known to be very effective for neuromorphic processor implementations, achieving orders of magnitude improvements in energy efficiency and computational latency over traditional deep learning approaches. Comparable ...
Spike-Time-Dependent Encoding for Neuromorphic Processors
Special Issue on Cross-Layer System Design and Regular Papers

This article presents our research towards developing novel and fundamental methodologies for data representation using spike-timing-dependent encoding. Time encoding efficiently maps a signal's amplitude information into a spike time sequence that ...
Modulated spike-time dependent plasticity (STDP)-based learning for spiking neural network (SNN): A review
Abstract
Computational models known as Spiking Neural Networks (SNNs) are inspired by the intricate information processing observed in the brain. A key learning principle, spike-timing-dependent plasticity (STDP), governs how the temporal relationship ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

NICE '22: Proceedings of the 2022 Annual Neuro-Inspired Computational Elements Conference

March 2022

122 pages

ISBN:9781450395595

DOI:10.1145/3517343

Copyright © 2022 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 03 May 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

NICE 2022

NICE 2022: Neuro-Inspired Computational Elements Conference

March 28 - April 1, 2022

Virtual Event, USA

Acceptance Rates

Overall Acceptance Rate 25 of 40 submissions, 63%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
197
Total Downloads

Downloads (Last 12 months)27
Downloads (Last 6 weeks)0

Reflects downloads up to 07 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Banerjee DDey SPal A(2024)Atrial Fibrillation Detector from ECG on Wearable Edge Devices using Spiking Neural Networks2024 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN60899.2024.10650023(1-8)Online publication date: 30-Jun-2024
https://doi.org/10.1109/IJCNN60899.2024.10650023
Stasenko SLebedev ALevanova TKazantsev V(2024)Study of the Influence of Macroparameters of a Spiking Neural Network on the Quality of Image Recognition2024 Sixth International Conference Neurotechnologies and Neurointerfaces (CNN)10.1109/CNN63506.2024.10705826(216-220)Online publication date: 19-Sep-2024
https://doi.org/10.1109/CNN63506.2024.10705826
Kahali SDey SKadway CMukherjee APal ASuri M(2023)Low-Power Lossless Image Compression on Small Satellite Edge using Spiking Neural Network2023 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN54540.2023.10191704(1-8)Online publication date: 18-Jun-2023
https://doi.org/10.1109/IJCNN54540.2023.10191704
Kadway CDey SMukherjee APal ABézard G(2023)Low Power & Low Latency Cloud Cover Detection in Small Satellites Using On-board Neuromorphic Processors2023 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN54540.2023.10191569(1-8)Online publication date: 18-Jun-2023
https://doi.org/10.1109/IJCNN54540.2023.10191569
Abunahla HAbbas YGebregiorgis AWaheed WMohammad BHamdioui SAlazzam ARezeq M(2023)Analog monolayer SWCNTs-based memristive 2D structure for energy-efficient deep learning in spiking neural networksScientific Reports10.1038/s41598-023-48529-z13:1Online publication date: 4-Dec-2023
https://doi.org/10.1038/s41598-023-48529-z
Arrassi AGebregiorgis AHaddadi AHamdioui S(2022)Energy-Efficient SNN Implementation Using RRAM-Based Computation In-Memory (CIM)2022 IFIP/IEEE 30th International Conference on Very Large Scale Integration (VLSI-SoC)10.1109/VLSI-SoC54400.2022.9939654(1-6)Online publication date: 3-Oct-2022
https://doi.org/10.1109/VLSI-SoC54400.2022.9939654

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View Table of Conten