Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
ICD |
2024-04-11 14:55 |
Kanagawa |
(Primary: On-site, Secondary: Online) |
[Invited Talk]
A818-4094TOPS/W Capacitor-Reconfigured CIM Macro for Unified Acceleration of CNNs and Transformers Kentaro Yoshioka (Keio) ICD2024-8 |
In the field of machine learning, various neural network architectures such as CNNs, Transformers, and hybrid structures... [more] |
ICD2024-8 pp.24-26 |
ITS, IE, ITE-MMS, ITE-ME, ITE-AIT [detail] |
2024-02-19 10:30 |
Hokkaido |
Hokkaido Univ. |
A Proposal of an Automatic Power Line Removal Method on Images Using Semantic Segmentation and U-Net Trained by the Semantics Touma Saito, Kazunori Uruma (Kogakuin Univ.) ITS2023-46 IE2023-35 |
In recent years, image processing technology and hardware performance have improved, making it possible to easily proces... [more] |
ITS2023-46 IE2023-35 pp.1-6 |
VLD, DC, RECONF, ICD, IPSJ-SLDM [detail] |
2023-11-15 15:55 |
Kumamoto |
Civic Auditorium Sears Home Yume Hall (Primary: On-site, Secondary: Online) |
Preliminary Data-Pattern Analysis towards Energy-Efficient Adaptive In-Cache Computing for CNN Accelerations Zhengpan Fei, Koji Inoue (Kyushu Univ.) VLD2023-42 ICD2023-50 DC2023-49 RECONF2023-45 |
In Look-Up Table (LUT) based computing, naively covering all possible results requires an exponential amount of hardware... [more] |
VLD2023-42 ICD2023-50 DC2023-49 RECONF2023-45 pp.70-75 |
RECONF, VLD, CPSY, IPSJ-ARC, IPSJ-SLDM [detail] |
2022-01-24 16:20 |
Online |
Online |
Addition of DPU Training Function by Tail Layer Training Yuki Takashima, Akira Jinguji, Hiroki Nakahara (Tokyo Tech) VLD2021-59 CPSY2021-28 RECONF2021-67 |
The demand for deep learning has been increasing, and many hardware implementations have been proposed. The Deep learnin... [more] |
VLD2021-59 CPSY2021-28 RECONF2021-67 pp.55-60 |
SDM, ICD, ITE-IST [detail] |
2021-08-18 13:00 |
Online |
Online |
[Invited Talk]
A 12nm autonomous driving processor running 60.4 TOPS and 13.8 TOPS/W CNNs with task-separated ASIL D control Katsushige Matsubara, Lieske Hanno (Renesas Electronics), Motoki Kimura (Renesas Electronics Europe), Atsushi Nakamura, Manabu Koike, Kazuaki Terashima, Shun Morikawa, Yoshihiko Hotta, Takahiro Irita, Seiji Mochizuki, Hiroyuki Hamasaki, Tatsuya Kamei (Renesas Electronics) SDM2021-39 ICD2021-10 |
Next-generation driver assistance systems and automated driving systems require both high performances to realize enormo... [more] |
SDM2021-39 ICD2021-10 pp.48-53 |
SIS |
2021-03-04 14:10 |
Online |
Online |
Hardware Implementation of Object Recognition Neural Network using Depth Images Yuma Yoshimoto (Kyutech/JSPS Research Fellow), Hakaru Tamukoh (Kyutech/Research Center for Neuromorphic AI Hardware) SIS2020-47 |
In this study, we propose an object recognition neural network using depth images, implemented on an FPGA for service ro... [more] |
SIS2020-47 pp.67-70 |
HWS, VLD [detail] |
2021-03-03 10:25 |
Online |
Online |
Evaluation on Approximate Multiplier for CNN Calculation Yuechuan Zhang, Masahiro Fujita, Takashi Matsumoto (UTokyo) VLD2020-68 HWS2020-43 |
Improving the accuracy of a convolutional neural network (CNN) typically requires larger hardware with more energy consu... [more] |
VLD2020-68 HWS2020-43 pp.7-12 |
SDM |
2020-01-28 14:45 |
Tokyo |
Kikai-Shinko-Kaikan Bldg. |
[Invited Talk]
Can in-memory/Analog Accelerators be a Silver Bullet for Energy-efficient Inference? Jun Deguchi, Daisuke Miyashita, Asuka Maki, Shinichi Sasaki, Kengo Nakata, Fumihiko Tachibana, Ryuichi Fujimoto (KIOXIA) SDM2019-85 |
This presentation introduces and discuss recent trends on in-memory/analog computing for deep learning inference, which ... [more] |
SDM2019-85 p.11 |
VLD, DC, CPSY, RECONF, ICD, IE, IPSJ-SLDM, IPSJ-EMB, IPSJ-ARC (Joint) [detail] |
2019-11-15 10:45 |
Ehime |
Ehime Prefecture Gender Equality Center |
[Keynote Address]
Co-optimization of hardware architecture and algorithm for energy-efficient CNN inference Daisuke Miyashita (Kioxia) VLD2019-47 ICD2019-36 IE2019-42 CPSY2019-46 DC2019-71 RECONF2019-42 |
(To be available after the conference date) [more] |
VLD2019-47 ICD2019-36 IE2019-42 CPSY2019-46 DC2019-71 RECONF2019-42 p.173(VLD), p.41(ICD), p.41(IE), p.53(CPSY), p.173(DC), p.31(RECONF) |
SIS |
2018-12-07 10:30 |
Yamaguchi |
Hagi Civic Center |
Hardware Oriented Object Recognition Neural Network using Depth Image Yuma Yoshimoto, Hakaru Tamukoh (KIT) SIS2018-32 |
In recent years, deep learning using Convolutional Neural Network (CNN) has attracted attention as a powerful method for... [more] |
SIS2018-32 pp.55-60 |
VLD, DC, CPSY, RECONF, CPM, ICD, IE, IPSJ-SLDM, IPSJ-EMB, IPSJ-ARC (Joint) [detail] |
2017-11-07 14:55 |
Kumamoto |
Kumamoto-Kenminkouryukan Parea |
DCNN Training with Short Bit Length Format Considering Loss of Trailing Digits Shin-ichi O'uchi, Hiroshi Fuketa, Ryousei Takano (AIST) CPSY2017-41 |
Loss of trailing digits in training deep convolutional neural network (DCNN) is considered to implement training with a ... [more] |
CPSY2017-41 pp.7-12 |