FPGA implementation of sequence-to-sequence predicting spiking neural networks

被引：0

作者：

Ye, ChangMin ^{[1
]}

Kornijcuk, Vladimir ^{[1
]}

Kim, Jeeson ^{[1
]}

Jeong, Doo Seok ^{[1
]}

机构：

[1] Hanyang Univ, Div Mat Sci & Engn, Seoul, South Korea

来源：

2020 17TH INTERNATIONAL SOC DESIGN CONFERENCE (ISOCC 2020) | 2020年

关键词：

sequence-predicting spiking neural network; LbAP algorithm; rule-based event routing;

D O I：

10.1109/ISOCC50952.2020.9332910

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

We propose a hardware-efficient method to implement sequence-predicting spiking neural networks (SPSNN) on a field-programmable gate array board. The SPSNN is capable of sequence-to-sequence prediction (associative recall) when fully trained using the learning by backpropagating action potential (LbAP) algorithm. The key to the hardware-efficiency lies in the rule-based event (routing) method in place of conventional lookup-table-based methods which are memory-hungry methods, particularly, when both forward and inverse lookups should be considered.

引用

页码：322 / 323

页数：2

共 50 条

[41] Matching Recall and Storage in Sequence Learning with Spiking Neural Networks
Brea, Johanni
Senn, Walter
Pfister, Jean-Pascal
JOURNAL OF NEUROSCIENCE, 2013, 33 (23): : 9565 - 9575
[42] Spike Trains Encoding Optimization for Spiking Neural Networks Implementation in FPGA
Fang, Biao
Zhang, Yuhao
Yan, Rui
Tang, Huajin
2020 12TH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTATIONAL INTELLIGENCE (ICACI), 2020, : 412 - 418
[43] DeepObfusCode: Source Code Obfuscation through Sequence-to-Sequence Networks
Datta, Siddhartha
INTELLIGENT COMPUTING, VOL 2, 2021, 284 : 637 - 647
[44] Sequential classification of customer behavior based on sequence-to-sequence learning with gated-attention neural networks
Licheng Zhao
Yi Zuo
Katsutoshi Yada
Advances in Data Analysis and Classification, 2023, 17 : 549 - 581
[45] Sequential classification of customer behavior based on sequence-to-sequence learning with gated-attention neural networks
Zhao, Licheng
Zuo, Yi
Yada, Katsutoshi
ADVANCES IN DATA ANALYSIS AND CLASSIFICATION, 2023, 17 (03) : 549 - 581
[46] Human Activity Prediction Based on Forecasted IMU Activity Signals by Sequence-to-Sequence Deep Neural Networks
Jaramillo, Ismael Espinoza
Chola, Channabasava
Jeong, Jin-Gyun
Oh, Ji-Heon
Jung, Hwanseok
Lee, Jin-Hyuk
Lee, Won Hee
Kim, Tae-Seong
SENSORS, 2023, 23 (14)
[47] Sequence-to-sequence neural networks for short-term electrical load forecasting in commercial office buildings
Skomski, Elliott
Lee, Joon-Yong
Kim, Woohyun
Chandan, Vikas
Katipamula, Srinivas
Hutchinson, Brian
ENERGY AND BUILDINGS, 2020, 226
[48] Synthesizing waveform sequence-to-sequence to augment training data for sequence-to-sequence speech recognition
Ueno, Sei
Mimura, Masato
Sakai, Shinsuke
Kawahara, Tatsuya
ACOUSTICAL SCIENCE AND TECHNOLOGY, 2021, 42 (06) : 333 - 343
[49] Sequence-to-sequence Prediction of Personal Computer Software by Recurrent Neural Network
Yang, Qichuan
He, Zhiqiang
Ge, Fujiang
Zhang, Yang
2017 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2017, : 934 - 940
[50] Sequence-to-Sequence Load Disaggregation Using Multiscale Residual Neural Network
Zhou, Gan
Li, Zhi
Fu, Meng
Feng, Yanjun
Wang, Xingyao
Huang, Chengwei
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70

← 1 2 3 4 5 →