Training Spiking Neural Networks with an Adaptive Leaky Integrate-and-Fire Neuron

Mingyu Sung; Yongtae Kim

doi:10.1109/ICCE-Asia49877.2020.9277455

Training Spiking Neural Networks with an Adaptive Leaky Integrate-and-Fire Neuron

Mingyu Sung
, Yongtae Kim

Kyungpook National University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

11 Scopus citations

Abstract

Spiking neural network (SNN) is more biologically plausible than traditional artificial neural networks. Since the spiking network uses binary values of spike to process, it can offer an excellent power and energy efficiency when implementing it in hardware. Therefore, it is widely utilized in various machine learning applications, such as pattern recognition. In this paper, we introduce an adaptive leaky integrate-and-fire (LIF) neuron model that improves the accuracy of the spiking network. The proposed method is employed in a spiking network that includes more than 1,500 neurons to classify the MNIST handwritten digits. The unsupervised spike timing-dependent plasticity (STDP) learning rule is used to train the network. The experimental results are shown that the accuracy performance of the network with the proposed method outperforms the baseline spiking network.

Original language	English
Title of host publication	2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728161648
DOIs	https://doi.org/10.1109/ICCE-Asia49877.2020.9277455
State	Published - 1 Nov 2020
Event	2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020 - Seoul, Korea, Republic of Duration: 1 Nov 2020 → 3 Nov 2020

Publication series

Name	2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020

Conference

Conference	2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020
Country/Territory	Korea, Republic of
City	Seoul
Period	1/11/20 → 3/11/20

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

adaptive leakage
adaptive leaky integrate-and-fire (LIF) neuron
spiking neural network (SNN)

Access to Document

10.1109/ICCE-Asia49877.2020.9277455

Cite this

Sung, M., & Kim, Y. (2020). Training Spiking Neural Networks with an Adaptive Leaky Integrate-and-Fire Neuron. In 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020 Article 9277455 (2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE-Asia49877.2020.9277455

@inproceedings{dfc3cd2028b14122a4c9d67cd6b5b476,

title = "Training Spiking Neural Networks with an Adaptive Leaky Integrate-and-Fire Neuron",

abstract = "Spiking neural network (SNN) is more biologically plausible than traditional artificial neural networks. Since the spiking network uses binary values of spike to process, it can offer an excellent power and energy efficiency when implementing it in hardware. Therefore, it is widely utilized in various machine learning applications, such as pattern recognition. In this paper, we introduce an adaptive leaky integrate-and-fire (LIF) neuron model that improves the accuracy of the spiking network. The proposed method is employed in a spiking network that includes more than 1,500 neurons to classify the MNIST handwritten digits. The unsupervised spike timing-dependent plasticity (STDP) learning rule is used to train the network. The experimental results are shown that the accuracy performance of the network with the proposed method outperforms the baseline spiking network.",

keywords = "adaptive leakage, adaptive leaky integrate-and-fire (LIF) neuron, spiking neural network (SNN)",

author = "Mingyu Sung and Yongtae Kim",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020 ; Conference date: 01-11-2020 Through 03-11-2020",

year = "2020",

month = nov,

day = "1",

doi = "10.1109/ICCE-Asia49877.2020.9277455",

language = "English",

series = "2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020",

address = "United States",

}

Sung, M & Kim, Y 2020, Training Spiking Neural Networks with an Adaptive Leaky Integrate-and-Fire Neuron. in 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020., 9277455, 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020, Institute of Electrical and Electronics Engineers Inc., 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020, Seoul, Korea, Republic of, 1/11/20. https://doi.org/10.1109/ICCE-Asia49877.2020.9277455

Training Spiking Neural Networks with an Adaptive Leaky Integrate-and-Fire Neuron. / Sung, Mingyu; Kim, Yongtae.
2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 9277455 (2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Training Spiking Neural Networks with an Adaptive Leaky Integrate-and-Fire Neuron

AU - Sung, Mingyu

AU - Kim, Yongtae

PY - 2020/11/1

Y1 - 2020/11/1

N2 - Spiking neural network (SNN) is more biologically plausible than traditional artificial neural networks. Since the spiking network uses binary values of spike to process, it can offer an excellent power and energy efficiency when implementing it in hardware. Therefore, it is widely utilized in various machine learning applications, such as pattern recognition. In this paper, we introduce an adaptive leaky integrate-and-fire (LIF) neuron model that improves the accuracy of the spiking network. The proposed method is employed in a spiking network that includes more than 1,500 neurons to classify the MNIST handwritten digits. The unsupervised spike timing-dependent plasticity (STDP) learning rule is used to train the network. The experimental results are shown that the accuracy performance of the network with the proposed method outperforms the baseline spiking network.

AB - Spiking neural network (SNN) is more biologically plausible than traditional artificial neural networks. Since the spiking network uses binary values of spike to process, it can offer an excellent power and energy efficiency when implementing it in hardware. Therefore, it is widely utilized in various machine learning applications, such as pattern recognition. In this paper, we introduce an adaptive leaky integrate-and-fire (LIF) neuron model that improves the accuracy of the spiking network. The proposed method is employed in a spiking network that includes more than 1,500 neurons to classify the MNIST handwritten digits. The unsupervised spike timing-dependent plasticity (STDP) learning rule is used to train the network. The experimental results are shown that the accuracy performance of the network with the proposed method outperforms the baseline spiking network.

KW - adaptive leakage

KW - adaptive leaky integrate-and-fire (LIF) neuron

KW - spiking neural network (SNN)

UR - https://www.scopus.com/pages/publications/85098860402

U2 - 10.1109/ICCE-Asia49877.2020.9277455

DO - 10.1109/ICCE-Asia49877.2020.9277455

M3 - Conference contribution

AN - SCOPUS:85098860402

T3 - 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020

BT - 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020

Y2 - 1 November 2020 through 3 November 2020

ER -

Sung M, Kim Y. Training Spiking Neural Networks with an Adaptive Leaky Integrate-and-Fire Neuron. In 2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020. Institute of Electrical and Electronics Engineers Inc. 2020. 9277455. (2020 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2020). doi: 10.1109/ICCE-Asia49877.2020.9277455

Training Spiking Neural Networks with an Adaptive Leaky Integrate-and-Fire Neuron

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this