Presentation | 2021-10-28 Enhancement of spatio-temporal coding performance in spiking neural network and its application to hazard detection for landing of spacecrafts Hideaki Kinoshita, Shinichi Kimura, Seisuke Fukuda, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Spiking neural networks (SNNs) are a neuromimetic computational architecture that has attracted much attention in recent years for its low power consumption in edge devices, and is expected to be applied to onboard processing of spacecrafts. SNNs have a higher coding capability in the time domain than artificial neural networks (ANNs) because each neuron can retain its own dynamic properties. In this study, we propose a method to improve the spatio-temporal coding performance by adding a gate with convolutional structure to the spiking neural unit proposed by Wozniak. We also present the results of the verification of the effectiveness and power consumption of the method, using the obstacle detection in the landing of a spacecraft as an example. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Spiking Neural Network / LiDAR / semantic segmentation / spacecraft navigation |
Paper # | NC2021-21 |
Date of Issue | 2021-10-21 (NC) |
Conference Information | |
Committee | MBE / NC |
---|---|
Conference Date | 2021/10/28(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Ryuhei Okuno(Setsunan Univ.) / Rieko Osu(Waseda Univ.) |
Vice Chair | Junichi Hori(Niigata Univ.) / Hiroshi Yamakawa(Univ of Tokyo) |
Secretary | Junichi Hori(Osaka Electro-Communication Univ) / Hiroshi Yamakawa(ATR) |
Assistant | Jun Akazawa(Meiji Univ. of Integrative Medicine) / Emi Yuda(Tohoku Univ) / Nobuhiko Wagatsuma(Toho Univ.) / Tomoki Kurikawa(KMU) |
Paper Information | |
Registration To | Technical Committee on ME and Bio Cybernetics / Technical Committee on Neurocomputing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Enhancement of spatio-temporal coding performance in spiking neural network and its application to hazard detection for landing of spacecrafts |
Sub Title (in English) | |
Keyword(1) | Spiking Neural Network |
Keyword(2) | LiDAR |
Keyword(3) | semantic segmentation |
Keyword(4) | spacecraft navigation |
1st Author's Name | Hideaki Kinoshita |
1st Author's Affiliation | Tokyo University of Science(TUS) |
2nd Author's Name | Shinichi Kimura |
2nd Author's Affiliation | Tokyo University of Science(TUS) |
3rd Author's Name | Seisuke Fukuda |
3rd Author's Affiliation | Japan Aerospace Exploration Agency(JAXA) |
Date | 2021-10-28 |
Paper # | NC2021-21 |
Volume (vol) | vol.121 |
Number (no) | NC-223 |
Page | pp.pp.16-21(NC), |
#Pages | 6 |
Date of Issue | 2021-10-21 (NC) |