Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NLP, MSS |
2024-03-14 11:15 |
Misc. |
Kikai-Shinko-Kaikan Bldg. |
Parallelization of a Search Algorithm for Regular Graphs with Minimum Average Shortest Path Length Taku Hirayama, Tsuyoshi Migita, Norikazu Takahashi (Okayama Univ.) MSS2023-89 NLP2023-141 |
Computer networks in data centers are modeled as regular graphs, and the average shortest path length (ASPL) of such a g... [more] |
MSS2023-89 NLP2023-141 pp.87-92 |
NLP, CAS |
2023-10-07 13:00 |
Gifu |
Work plaza Gifu |
An algorithm for finding regular graphs that maximize algebraic connectivity under a specified number of vertices and degree Masashi Kurahashi, Tsuyoshi Migita, Norikazu Takahashi (Okayama Univ.) CAS2023-54 NLP2023-53 |
Algebraic connectivity is a measure of network robustness, and defined by the second smallest eigenvalue of the Laplacia... [more] |
CAS2023-54 NLP2023-53 pp.106-110 |
AI |
2023-09-13 09:00 |
Hokkaido |
|
Implementation of Dynamic Simulation Pruning Strategy in the Assimilation of Large-scale Pedestrian Simulation Shunki Takami (Univ. of Tsukuba), Ryo Ishiyama (Kyushu Univ.), Shusuke Shigenaka (Univ. of Tsukuba), Masaki Onishi (AIST), Itsuki Noda (Hokkaido Univ.) AI2023-11 |
An implementation method for a dynamic simulation pruning strategy in assimilating large-scale pedestrian simulation is ... [more] |
AI2023-11 pp.56-59 |
IA, SITE, IPSJ-IOT [detail] |
2023-03-16 15:35 |
Gunma |
Maebashi Institute of Technology (Primary: On-site, Secondary: Online) |
Model compression by pruning of CNN based on perceptual hashes Shota Mishina, Tetsuya Morizumi, Hirotsugu Kinoshita (Kanagawa Univ.) SITE2022-59 IA2022-82 |
Message digests that identify images are indispensable for secure and convenient copyright management of digital content... [more] |
SITE2022-59 IA2022-82 pp.28-34 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2023-03-02 09:40 |
Hokkaido |
Future University Hakodate (Primary: On-site, Secondary: Online) |
Pruning for Producing Efficient DNNs: Neuron Selection and Reconstruction based on Final Layer Error Koji Kamma, Toshikazu Wada (Wakayama Univ.) PRMU2022-66 IBISML2022-73 |
Deep Neural Networks (DNNs) are dominant in the field of machine learning. However, because DNN models have large comput... [more] |
PRMU2022-66 IBISML2022-73 pp.42-47 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2023-03-03 16:20 |
Hokkaido |
Future University Hakodate (Primary: On-site, Secondary: Online) |
Collaborative Intelligence for Transformer-Based AI Systems Monikka Roslianna Busto, Shohei Enomoto, Takeharu Eda (NTT SIC) PRMU2022-111 IBISML2022-118 |
[more] |
PRMU2022-111 IBISML2022-118 pp.275-280 |
PRMU |
2022-12-15 14:25 |
Toyama |
Toyama International Conference Center (Primary: On-site, Secondary: Online) |
A DNN compression method based on output error of activation functions Koji Kamma, Toshikazu Wada (Wakayama Univ.) PRMU2022-38 |
Deep Neural Networks (DNNs) are dominant in the field of machine learning. However, because DNN models have large comput... [more] |
PRMU2022-38 pp.34-39 |
PRMU |
2022-12-16 14:10 |
Toyama |
Toyama International Conference Center (Primary: On-site, Secondary: Online) |
Sampling Strategies in Data Pruning Ryota Higashi, Toshikazu Wada (Wakayama Univ.) PRMU2022-48 |
Data Pruning is a method of selecting the training data out of an entire training dataset so as to keep the accuracy aft... [more] |
PRMU2022-48 pp.85-90 |
IBISML |
2022-09-15 15:05 |
Kanagawa |
Keio Univ. (Yagami Campus) (Primary: On-site, Secondary: Online) |
Improving Efficiency of Regularization Path Computation in Safe Pattern Pruning via Multiple Referential Solutions Takumi Yoshida (Nitech), Hiroyuki Hanada (RIKEN), Kazuya Nakagawa, Shinya Suzumura, Onur Boyar, Kazuki Iwata (Nitech), Shun Shimura, Yuji Tanaka (NaogyaU), Masayuki Karasuyama (Nitech), Kouichi Taji (NaogyaU), Koji Tsuda (UTokyo/RIKEN), Ichiro Takeuchi (NaogyaU/RIKEN) IBISML2022-38 |
Safe Screening and Safe Pattern Pruning are methods for efficiently modeling high-dimensional features by $L_1$-regulari... [more] |
IBISML2022-38 pp.39-46 |
PRMU |
2022-09-14 16:00 |
Kanagawa |
(Primary: On-site, Secondary: Online) |
Convolutional Skip Connection for Compressing DNNs with Branched Architectures Koji Kamma, Toshikazu Wada (Wakayama Univ.) PRMU2022-16 |
Although Deep Neural Network (DNN) is a core technology in Computer Vision, it is difficult to implement DNN models beca... [more] |
PRMU2022-16 pp.37-42 |
PRMU |
2022-09-15 10:00 |
Kanagawa |
(Primary: On-site, Secondary: Online) |
One-cut Network Pruning at Initialization with Explainable Image Concepts Yinan Yang (Rits Univ.), Ying Ji (Nagoya Univ.), Yu Wang (Hitotsubashi Univ.), Jien Kato (Rits Univ.) PRMU2022-18 |
Recent research investigates the feasibility of one-cut network pruning at initialization (OPAI). SNIP and GraSP are tw... [more] |
PRMU2022-18 pp.49-54 |
RECONF |
2022-06-08 15:25 |
Ibaraki |
CCS, Univ. of Tsukuba (Primary: On-site, Secondary: Online) |
A Compact High-Speed CNN Implementation based on Redundant Computational Analysis and FPGA Acceleration Li Qi, Li Hengyi, Meng Lin (Ritsumeikan Univ.) RECONF2022-21 |
Convolutional Neural Networks (CNNs) have achieved high performance and are widely used in various applications. However... [more] |
RECONF2022-21 pp.89-94 |
RECONF, VLD, CPSY, IPSJ-ARC, IPSJ-SLDM [detail] |
2022-01-24 15:55 |
Online |
Online |
Accelerating Deep Neural Networks on Edge Devices by Knowledge Distillation and Layer Pruning Yuki Ichikawa, Akira Jinguji, Ryosuke Kuramochi, Hiroki Nakahara (Titech) VLD2021-58 CPSY2021-27 RECONF2021-66 |
A deep neural network (DNN) is computationally expensive, making it challenging to run DNN on edge devices. Therefore, m... [more] |
VLD2021-58 CPSY2021-27 RECONF2021-66 pp.49-54 |
VLD, DC, RECONF, ICD, IPSJ-SLDM (Joint) [detail] |
2021-12-01 09:45 |
Online |
Online |
Sparsity-Gradient-Based Pruning and the Vitis-AI Implementation for Compacting Deep Learning Models Hengyi Li, Xuebin Yue, Lin Meng (Ritsumeikan Univ.) VLD2021-22 ICD2021-32 DC2021-28 RECONF2021-30 |
The paper proposes a Sparsity-Gradient-Based layer-wise Pruning technique for compacting deep neural networks and accele... [more] |
VLD2021-22 ICD2021-32 DC2021-28 RECONF2021-30 pp.31-36 |
MBE, NC (Joint) |
2021-10-28 15:30 |
Online |
Online |
A Deep Neural Network Model Compression with Spherical Clustering of Neurons Shin Sakamoto, Masao Okita, Fumihiko Ino (Osaka Univ) NC2021-22 |
In this paper, we propose weight matrix compression with spherical clustering of neurons , aiming at reducing memory usa... [more] |
NC2021-22 pp.22-27 |
WBS, IT, ISEC |
2021-03-04 09:25 |
Online |
Online |
List-Pruning SCL Decoder for Polar Codes Using Parity-Check Bits Yusuke Oki, Ryo Shibata, Hiroyuki Yashima (TUS) IT2020-112 ISEC2020-42 WBS2020-31 |
In this paper, we propose encoding and decoding algorithms of polar codes which add pruning bits into the transmitted in... [more] |
IT2020-112 ISEC2020-42 WBS2020-31 pp.1-6 |
IPSJ-SLDM, RECONF, VLD, CPSY, IPSJ-ARC [detail] |
2020-01-22 17:45 |
Kanagawa |
Raiosha, Hiyoshi Campus, Keio University |
An FPGA Implementation of Monocular Depth Estimation Youki Sada, Masayuki Shimoda, Shimpei Sato, Hiroki Nakahara (titech) VLD2019-66 CPSY2019-64 RECONF2019-56 |
Among a lot of image recognition applications, Convolutional Neural Network (CNN) has gained high accuracy and increasin... [more] |
VLD2019-66 CPSY2019-64 RECONF2019-56 pp.73-78 |
PRMU |
2019-10-18 10:45 |
Tokyo |
|
[Short Paper]
An attribution-based pruning method for single object detection network Rui Shi, Tianxing Li, Yasushi Yamaguchi (UTokyo) PRMU2019-34 |
Deep neural networks (DNNs) have achieved advanced results on different vision tasks. However, the cost of high computat... [more] |
PRMU2019-34 pp.17-20 |
EMM, IT |
2019-05-24 14:20 |
Hokkaido |
Asahikawa International Conference Hall |
Reduced-Complexity Successive Cancellation List Decoding of Polar Codes Using Parity Check and List-Pruning Yusuke Oki, Ryo Shibata, Gou Hosoya, Hiroyuki Yashima (TUS) IT2019-14 EMM2019-14 |
In this paper, we propose encoding and decoding algorithms which add pruning bits into the transmitted information in or... [more] |
IT2019-14 EMM2019-14 pp.73-78 |
RECONF |
2019-05-10 10:00 |
Tokyo |
Tokyo Tech Front |
An FPGA Implementation of the Semantic Segmentation Model with Multi-path Structure Youki Sada, Masayuki Shimoda, Shimpei Sato, Hiroki Nakahara (titech) RECONF2019-10 |
Since the convolutional neural network has a high-performance recognition accuracy,
it is expected to implement variou... [more] |
RECONF2019-10 pp.49-54 |