ATC: Approximate Temporal Coding for Efficient Implementations of Spiking Neural Networks

被引：0

作者：

Han, Ming ^{[1
]}

Wang, Ye ^{[1
]}

Dong, Jian ^{[1
]}

Liu, Heng ^{[1
]}

Wu, Jin ^{[1
]}

Qu, Gang ^{[2
]}

机构：

[1] Harbin Inst Technol, Harbin, Peoples R China

[2] Univ Maryland, College Pk, MD USA

来源：

PROCEEDINGS OF THE GREAT LAKES SYMPOSIUM ON VLSI 2023, GLSVLSI 2023 | 2023年

关键词：

approximate computing; spiking neural network; temporal coding; pruning; BACKPROPAGATION;

D O I：

10.1145/3583781.3590201

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Spiking Neural Networks (SNN) update their neurons' states, the most energy consuming action, only after receiving or firing spikes for energy efficiency. So reducing the number of spikes would lead to more efficient SNN implementations. We propose an approximate temporal coding (ATC) for this purpose. Because the reduction of spikes leads to more synapses being used rarely, we develop a pruning method for further energy improvement. Experimental results validate the efficiency of ATC and the pruning method. On the MNIST dataset, for example, 61% of the spikes are reduced, leading to 60% energy saving without any accuracy loss.

引用

页码：527 / 532

页数：6

共 50 条

[1] Efficient Spiking Neural Networks With Logarithmic Temporal Coding
Zhang, Ming
Gu, Zonghua
Zheng, Nenggan
Ma, De
Pan, Gang
[J]. IEEE ACCESS, 2020, 8 : 98156 - 98167
[2] Temporal Pattern Coding in Deep Spiking Neural Networks
Rueckauer, Bodo
Liu, Shih-Chii
[J]. 2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
[3] Supervised Learning Based on Temporal Coding in Spiking Neural Networks
Mostafa, Hesham
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (07) : 3227 - 3235
[4] Delay learning based on temporal coding in Spiking Neural Networks
Sun, Pengfei
Wu, Jibin
Zhang, Malu
Devos, Paul
Botteldooren, Dick
[J]. NEURAL NETWORKS, 2024, 180
[5] TEMPORAL CODING IN SPIKING NEURAL NETWORKS WITH ALPHA SYNAPTIC FUNCTION
Comsa, Julia M.
Potempa, Krzysztof
Versari, Luca
Fischbacher, Thomas
Gesmundo, Andrea
Alakuijala, Jyrki
[J]. 2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 8529 - 8533
[6] Simulation of spiking neural networks -: architectures and implementations
Schæfer, M
Schoenauer, T
Wolff, C
Hartmann, G
Klar, H
Rückert, U
[J]. NEUROCOMPUTING, 2002, 48 : 647 - 679
[7] An Efficient Discrete Model for Implementing Temporal Coding Spiking Neural Network
Charles, E. Y. Andrew
[J]. 14TH INTERNATIONAL CONFERENCE ON ADVANCES IN ICT FOR EMERGING REGIONS (ICTER) 2014, 2014, : 74 - 77
[8] Conversion of analog to spiking neural networks using sparse temporal coding
Rueckauer, Bodo
Liu, Shih-Chii
[J]. 2018 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2018,
[9] Composer Classification based on Temporal Coding in Adaptive Spiking Neural Networks
Prasad, Chaitanya N.
Saboo, Krishnakant
Rajendran, Bipin
[J]. 2015 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2015,
[10] Enhanced representation learning with temporal coding in sparsely spiking neural networks
Fois, Adrien
Girau, Bernard
[J]. FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2023, 17

← 1 2 3 4 5 →