Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NC, MBE (Joint) |
2019-03-05 09:55 |
Tokyo |
University of Electro Communications |
Neuron-Pruning Algorithm For Neural Network Considering Activation Values Masahiro Yamada, Masafumi Hagiwara (Keio Univ.) NC2018-64 |
In this paper, we propose a neuron-pruning algorithm using activation value. As the index for pruning neurons,
two type... [more] |
NC2018-64 pp.111-116 |
IA, IN (Joint) |
2018-12-13 14:45 |
Hiroshima |
Hiroshima Univ. |
Towards application of network topology information to network log causal anlaysis Satoru Kobayashi (NII), Kazuki Otomo (Univ. Tokyo), Kensuke Fukuda (NII) IA2018-40 |
To detect root causes of failures in large-scale networks, we need to extract contextual information from operational da... [more] |
IA2018-40 pp.1-8 |
VLD, DC, CPSY, RECONF, CPM, ICD, IE, IPSJ-SLDM, IPSJ-EMB, IPSJ-ARC (Joint) [detail] |
2018-12-05 10:20 |
Hiroshima |
Satellite Campus Hiroshima |
An FPGA implementation of Tri-state YOLOv2 using Intel OpenCL Youki Sada, Masayuki Shimoda, Shimpei Sato, Hiroki Nakahara (titech) RECONF2018-35 |
Since the convolutional neural network has a high-performance recognition accuracy,
it is expected to implement variou... [more] |
RECONF2018-35 pp.7-12 |
ISEC |
2018-09-07 12:00 |
Tokyo |
Kikai-Shinko-Kaikan Bldg. |
[Invited Talk]
Lower Bounds on Lattice Enumeration with Extreme Pruning (from Crypto 2018) Yoshinori Aono (NICT), Phong Q. Nguyen (Inria/CNRS/JFLI/Tokyo Univ.), Takenobu Seito (BoJ), Junji Shikata (YNU) ISEC2018-56 |
We give an introduction to the paper “Lower Bounds on Lattice Enumeration with Extreme Pruning” in Crypto 2018. We prove... [more] |
ISEC2018-56 p.29 |
IBISML |
2018-03-06 10:00 |
Fukuoka |
Nishijin Plaza, Kyushu University |
Learning rule-base model by Safe Pattern Pruning Hiroki Kato, Hiroyuki Hanada (Nagoya Inst. of Tech.), Ichiro Takeuchi (Nagoya Inst. of Tech./RIKEN/NIMS) IBISML2017-98 |
We consider learning the prediction model called ''rule-base model''. Rule-base model is the model which uses ''rules'' ... [more] |
IBISML2017-98 pp.55-62 |
RCS, SR, SRW (Joint) |
2018-02-28 15:40 |
Kanagawa |
YRP |
A community-based anomaly detection system by the synergetic use of mobile sensing and delay tolerant networks with cooperative data processing technique Yoshito Watanabe, Yozo Shoji (NICT) SR2017-115 |
This paper proposes a novel cooperative anomaly detection system that uses mobile sensing and delay tolerant network (DT... [more] |
SR2017-115 pp.25-30 |
RECONF |
2017-09-25 14:20 |
Tokyo |
DWANGO Co., Ltd. |
A Memory Reduction with Neuron Pruning for a Binarized Deep Convolutional Neural Network: Its FPGA Realization Tomoya Fujii, Shimpei Sato, Hiroki Nakahara (Tokyo Inst. of Tech.) RECONF2017-26 |
For a pre-trained deep convolutional neural network (CNN)
for an embedded system, a high-speed and a low power consumpt... [more] |
RECONF2017-26 pp.25-30 |
CPSY, RECONF, VLD, IPSJ-SLDM, IPSJ-ARC [detail] |
2017-01-24 15:50 |
Kanagawa |
Hiyoshi Campus, Keio Univ. |
A Memory Reduction with Neuron Pruning for a Convolutional Neural Network: Its FPGA Realization Tomoya Fujii, Simpei Sato, Hiroki Nakahara (Tokyo Tech), Masato Motomura (Hokkaido univ.) VLD2016-79 CPSY2016-115 RECONF2016-60 |
For a pre-trained deep convolutional neural network (CNN) aim at an embedded system, a high-speed and a low power consum... [more] |
VLD2016-79 CPSY2016-115 RECONF2016-60 pp.55-60 |
NC, MBE |
2015-03-16 15:35 |
Tokyo |
Tamagawa University |
Further Speeding Up and Solution Quality Improvement of Singularity Stairs Following Seiya Satoh, Ryohei Nakano (Chubu Univ.) MBE2014-168 NC2014-119 |
In a search space of a multilayer perceptron (MLP), there exists singular regions where any point is I-O equivalent to t... [more] |
MBE2014-168 NC2014-119 pp.289-294 |
SIP, EA, SP |
2015-03-03 09:00 |
Okinawa |
|
[Poster Presentation]
Content-Aware Image Compression Using Iterative Edge-Directed Interpolation Eri Hosogai, Yuichi Tanaka (Tokyo Univ. of Agri. and Tech.) EA2014-93 SIP2014-134 SP2014-156 |
This paper proposes a content-aware image compression method for low bit-rate image coding using an iterative upsampling... [more] |
EA2014-93 SIP2014-134 SP2014-156 pp.109-114 |
CQ, CS (Joint) |
2011-04-22 12:05 |
Kagoshima |
Yakushima Environmental Culture Village Center |
A Study on Improvements of Rate Estimation and Reduction of Computational Complexity for Rate Compatible Punctured LDPC Codes Tetsuo Tsujioka, Satoshi Yoshimura (Osaka City Univ.) CS2011-9 |
Rate compatible punctured LDPC codes (RCP-LDPC codes) has powerful error correcting capability and flexible coding rate ... [more] |
CS2011-9 pp.51-56 |
CQ, MVE, IE (Joint) [detail] |
2011-03-08 11:15 |
Nagasaki |
Yasuragi IOUJIMA |
Mixed Resolution Distributed Video Coding Based on Selective Data Pruning Tuan Tai Phan, Yuichi Tanaka, Madoka Hasegawa, Shigeo Kato (Utsunomiya Univ.) IE2010-186 MVE2010-174 |
In current distributed video coding (DVC) issues, the huge computational complexity caused at the decoder has not been s... [more] |
IE2010-186 MVE2010-174 pp.237-242 |
NS, RCS (Joint) |
2010-12-17 10:30 |
Okayama |
Okayama Univ. |
A Total Dominant Pruning-based Scheme with Passive ACK and Active NACK for Reliable Broadcasting in MANETs Yiyuan Diao, Yumi Takaki, Chikara Ohta, Hisashi Tamaki (Kobe Univ.) NS2010-130 |
Flooding is one of the most fundamental operations in mobile ad-hoc networks; however, pure flooding suffers from the pr... [more] |
NS2010-130 pp.149-153 |
RCS, NS (Joint) |
2010-07-15 09:20 |
Hokkaido |
Abashiri Public Auditorium |
A Simple Interleaver Design for Variable-Length Turbo Codes Ken Enokizono, Hideki Ochiai (Yokohama National Univ.) RCS2010-48 |
In recent wireless standards, variable frame length turbo codes are used.Bit error rate (BER) and frame error rate (FER)... [more] |
RCS2010-48 pp.1-6 |
NLP |
2005-11-19 15:40 |
Fukuoka |
Kyushu Institute of Technology |
Application of minimum description length to Least Squares Support Vector Machines for modeling chaotic dynamical systems Tsutomu Maeda, Masaharu Adachi (Tokyo Denki Univ.) |
In this study, we attempt to prune the support vectors of Least Squares Support Vector Machines for function estimation... [more] |
NLP2005-83 pp.71-76 |