More Web Proxy on the site http://driver.im/

research-article

Training Probabilistic Spiking Neural Networks with First- To-Spike Decoding

Authors:

Alireza Bagheri,

Osvaldo Simeone,

Bipin RajendranAuthors Info & Claims

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Pages 2986 - 2990

https://doi.org/10.1109/ICASSP.2018.8462410

Published: 15 April 2018 Publication History

Abstract

Third-generation neural networks, or Spiking Neural Networks (SNNs), aim at harnessing the energy efficiency of spike-domain processing by building on computing elements that operate on, and exchange, spikes. In this paper, the problem of training a two-layer SNN is studied for the purpose of classification, under a Generalized Linear Model (GLM) probabilistic neural model that was previously considered within the computational neuroscience literature. Conventional classification rules for SNNs operate offline based on the number of output spikes at each output neuron. In contrast, a novel training method is proposed here for a first-to-spike decoding rule, whereby the SNN can perform an early classification decision once spike firing is detected at an output neuron. Numerical results bring insights into the optimal parameter selection for the GLM neuron and on the accuracy-complexity trade-off performance of conventional and first-to-spike decoding.

References

[1]

H. Paugam-Moisy and S. Bohte, “Computing with spiking neuron networks,” in Handbook of natural computing, 2012, pp. 335–376.

[2]

J. Vincent, “Intel investigates chips designed like your brain to turn the AI tide,” https://www.theverge.com/2017/9/26/16365390/intel-investigates-chips-designed-like-your-brain-to-turn-the-ai-tide, accessed: 26 Sept 2017.

[3]

A. Diamond, T. Nowotny, and M. Schmuker, “Com-paring neuromorphic solutions in action: implementing a bio-inspired solution to a benchmark classification task on three parallel-computing platforms,” Front. Neu-rosci., vol. 9, p. 491, 2016.

[4]

F. Ponulak and A. Kasiński, “Supervised learning in spiking neural networks with ReSuMe: sequence learning, classification, and spike shifting,” Neural Comput., vol. 22, no. 2, pp. 467–510, 2010.

Digital Library

[5]

R. V. Florian, “Reinforcement learning through modulation of spike-timing-dependent synaptic plasticity,” Neural Comput., vol. 19, no. 6, pp. 1468–1502, 2007.

Digital Library

[6]

P. O'Connor and M. Welling, “Deep spiking networks,” arXiv preprint. arXiv:, 2016.

[7]

E. Hunsberger and C. Eliasmith, “Spiking deep networks with LIF neurons,” arXiv preprint. arXiv:, 2015.

[8]

N. Anwani and B. Rajendran, “NormAD-normalized approximate descent based supervised learning rule for spiking neurons,” in Proc. IEEE Int. Joint Conf. on Neural Netw. (IJCNN), 2015.

[9]

J. H. Lee, T. Delbruck, and M. Pfeiffer, “Training deep spiking neural networks using backpropagation,” Front. Neurosci., vol. 10, p. 508, 2016.

[10]

J. W. Pillow, L. Paninski, V. J. Uzzell, E. P. Simoncelli, and E. J. Chichilnisky, “Prediction and decoding of retinal ganglion cell responses with a probabilistic spiking model,” J. Neurosci., vol. 25, no. 47, pp. 11003–11013, 2005.

[11]

D. Koller and N. Friedman, Probabilistic graphical models: principles and techniques. MIT press, 2009.

Digital Library

[12]

O. Simeone, “A brief introduction to machine learning for engineers,” arXiv preprint arXiv:, 2017.

[13]

R. Jolivet, A. Rauch, H. Lüscher, and W. Gerstner, “Predicting spike timing of neocortical pyramidal neurons by simple threshold models,” J. Comput. Neurosci., vol. 21, no. 1, pp. 35–49, 2006.

[14]

B. Gardner and A. Grüning, “Supervised learning in spiking neural networks for precise temporal encoding,” PloS ONE, vol. 11, no. 8, p. e0161335, 2016.

[15]

T. Masquelier and S. J. Thorpe, “Unsupervised learning of visual features through spike timing dependent plasticity,” PLoS Comput. Biol., vol. 3, no. 2, p. e31, 2007.

[16]

M. Mozafari, S. Kheradpisheh, T. Masquelier, A. Nowzari-Dalini, and M. Ganjtabesh, “First-spike based visual categorization using reward-modulated STDP,” arXiv preprint arXiv:, 2017.

[17]

J. Wang, A. Belatreche, L. P. Maguire, and T. M. McGinnity, “SpikeTemp: An enhanced rank-order-based learning approach for spiking neural networks with adaptive structure,” IEEE Trans. Neural Netw. Learn. Syst., vol. 28, no. 1, pp. 30–43, 2017.

[18]

Z. Lin, D. Ma, J. Meng, and L. Chen, “Relative ordering learning in spiking neural network for pattern recognition,” Neurocomputing, vol. 275, pp. 94–106, 2018.

Digital Library

[19]

J. W. Pillow, J. Shlens, L. Paninski, A. Sher, A. M. Litke, E. J. Chichilnisky, and E. P. Simoncelli, “Spatio-temporal correlations and visual signalling in a complete neuronal population,” Nature, vol. 454, no. 7207, pp. 995–999, 2008.

[20]

J. Shlens, “Notes on generalized linear models of neurons,” arXiv preprint arXiv:, 2014.

[21]

P. Baldi and A. F. Atiya, “How delays affect neural dynamics and learning,” IEEE Transactions on Neural Networks, vol. 5, no. 4, pp. 612–621, 1994.

Digital Library

[22]

A. Taherkhani, A. Belatreche, Y. Li, and L. P. Maguire, “DL-ReSuMe: a delay learning-based remote supervised method for spiking neurons,” IEEE Trans. Neural Netw. Learn. Syst., vol. 26, no. 12, pp. 3137–3149, 2015.

[23]

A. Bagheri, O. Simeone, and B. Rajendran, “Training probabilistic spiking neural networks with first-to-spike decoding,” arXiv preprint arXiv:, 2017.

[24]

N. Frémaux and W. Gerstner, “Neuromodulated spike-timing-dependent plasticity, and theory of three-factor learning rules,” Front. Neural Circuits, vol. 9, 2015.

[25]

Y. LeCun, “The MNIST database of handwritten digits,” http://yann.lecun.com/exdb/mnist/, 1998.

Cited By

Li RXu XWan LLi QYuan YLiu N(2023)Autoencoder Induced Deep Spiking Neural NetworkProceedings of the 2023 7th International Conference on Innovation in Artificial Intelligence10.1145/3594409.3594437(147-153)Online publication date: 3-Mar-2023
https://dl.acm.org/doi/10.1145/3594409.3594437
Alam SFoshie ARose GThapliyal HDeMara RPartin-Vaisband IKatkoori S(2023)A Runtime-Reconfigurable Hardware Encoder for Spiking Neural NetworksProceedings of the Great Lakes Symposium on VLSI 202310.1145/3583781.3590284(203-206)Online publication date: 5-Jun-2023
https://dl.acm.org/doi/10.1145/3583781.3590284
Schuman CRizzo CMcDonald-Carmack JSkuda NPlank J(2022)Evaluating Encoding and Decoding Approaches for Spiking Neuromorphic SystemsProceedings of the International Conference on Neuromorphic Systems 202210.1145/3546790.3546792(1-9)Online publication date: 27-Jul-2022
https://dl.acm.org/doi/10.1145/3546790.3546792

Index Terms

Training Probabilistic Spiking Neural Networks with First- To-Spike Decoding

Index terms have been assigned to the content through auto-classification.

Recommendations

Spiking neural networks for cortical neuronal spike train decoding

Recent investigation of cortical coding and computation indicates that temporal coding is probably a more biologically plausible scheme used by neurons than the rate coding used commonly in most published work. We propose and demonstrate in this letter ...
Spiking Neural Network Inter-Spike Time Based Decoding Scheme

Information transmission among biological neurons is carried out by a complex series of spike signals. The input inter-spike arrival times at a neuron are believed to carry information which the neurons utilize to carry out a task. In this paper, a new ...
Improved Izhikevich neurons for spiking neural networks

Spiking neural networks constitute a modern neural network paradigm that overlaps machine learning and computational neurosciences. Spiking neural networks use neuron models that possess a great degree of biological realism. The most realistic model of ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Apr 2018

17916 pages

Copyright © 2018.

Publisher

IEEE Press

Publication History

Published: 15 April 2018

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
0
Total Downloads

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

Reflects downloads up to 05 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Li RXu XWan LLi QYuan YLiu N(2023)Autoencoder Induced Deep Spiking Neural NetworkProceedings of the 2023 7th International Conference on Innovation in Artificial Intelligence10.1145/3594409.3594437(147-153)Online publication date: 3-Mar-2023
https://dl.acm.org/doi/10.1145/3594409.3594437
Alam SFoshie ARose GThapliyal HDeMara RPartin-Vaisband IKatkoori S(2023)A Runtime-Reconfigurable Hardware Encoder for Spiking Neural NetworksProceedings of the Great Lakes Symposium on VLSI 202310.1145/3583781.3590284(203-206)Online publication date: 5-Jun-2023
https://dl.acm.org/doi/10.1145/3583781.3590284
Schuman CRizzo CMcDonald-Carmack JSkuda NPlank J(2022)Evaluating Encoding and Decoding Approaches for Spiking Neuromorphic SystemsProceedings of the International Conference on Neuromorphic Systems 202210.1145/3546790.3546792(1-9)Online publication date: 27-Jul-2022
https://dl.acm.org/doi/10.1145/3546790.3546792

View Options

View options

Media

Figures

Other

Tables

View Table of Contents