Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
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 |
RECONF, VLD, CPSY, IPSJ-ARC, IPSJ-SLDM [detail] |
2022-01-24 17:10 |
Online |
Online |
Ternarizing Deep Spiking Neural Network Man Wu, Yirong Kan, Van_Tinh Nguyen, Renyuan Zhang, Yasuhiko Nakashima (NAIST) VLD2021-61 CPSY2021-30 RECONF2021-69 |
The feasibility of ternarizing spiking neural networks (SNNs) is studied in this work toward trading a slight accuracy f... [more] |
VLD2021-61 CPSY2021-30 RECONF2021-69 pp.67-72 |
NLP, MICT, MBE, NC (Joint) [detail] |
2022-01-21 11:45 |
Online |
Online |
Physical deep learning based on optimal control of dynamical systems Satoshi Sunada, Genki Furuhata, Tomoaki Niiyama (Kanazawa Univ.) NLP2021-79 MICT2021-54 MBE2021-40 |
An underlying key factor of deep neural networks is the information propagation through the layers. This suggests a conn... [more] |
NLP2021-79 MICT2021-54 MBE2021-40 p.36 |
NLP, MICT, MBE, NC (Joint) [detail] |
2022-01-21 10:55 |
Online |
Online |
A System for Estimating Individual Differences of Perceptual Information in the Brain via Brain-activity Prediction by Convolutional Neural Networks Kiichi Kawahata (Osaka Univ.), Antoine Blanc (NICT), Naoya Maeda (NTT Data), Shinji Nishimoto (Osaka Univ.), Satoshi Nishida (NICT) NC2021-31 |
Our brains shape individual differences of perception by responding to sensory inputs differently across individuals. Th... [more] |
NC2021-31 pp.1-6 |
EA, US (Joint) |
2021-12-22 13:30 |
Kumamoto |
Sojo University |
[Poster Presentation]
Improved voice quality due to multi-speaker learning with WaveNet vocoder Satoshi Yoshida, Shingo Uenohara, Ken'ichi Furuya (Oita Univ.) EA2021-57 |
In recent years, speech synthesis and voice quality conversion techniques using neural networks have attracted much atte... [more] |
EA2021-57 pp.1-6 |
NLP |
2021-12-18 15:40 |
Oita |
J:COM Horuto Hall OITA |
Performance evaluation on timeseries prediction of multi-layer simple cycle reservoir computing Kentaro Imai, Masaharu Adachi (Tokyo Denki Univ.) NLP2021-67 |
The purpose of this study is to combine Deep Echo State Network with other models. In this study, we propose and impleme... [more] |
NLP2021-67 pp.110-113 |
PRMU |
2021-12-16 14:55 |
Online |
Online |
Fully automatic scoring of handwritten descriptive answers in Japanese language tests Hung Tuan Nguyen, Cuong Tuan Nguyen (TUAT), Haruki Oka (UTokyo), Tsunenori Ishioka (The National Center for University Entrance Examinations), Masaki Nakagawa (TUAT) PRMU2021-32 |
This paper presents an experiment of automatically scoring handwritten descriptive answers in the trial tests for the ne... [more] |
PRMU2021-32 pp.45-50 |
PRMU |
2021-12-17 14:45 |
Online |
Online |
Data Selection for Efficient Deep Learning Ryota Higashi, Toshikazu Wada (Wakayama Univ.) PRMU2021-51 |
We are investigating the method to sample the important data from the whole dataset for efficient training of Deep Neura... [more] |
PRMU2021-51 pp.148-153 |
HCGSYMPO (2nd) |
2021-12-15 - 2021-12-17 |
Online |
Online |
Modality-Independent Emotion Recognition Based on Hyper-Hemispherical Embedding and Latent Representation Unification Using Multimodal Deep Neural Networks Seiichi Harata, Takuto Sakuma, Shohei Kato (NIT) |
This study aims to obtain a mathematical representation of emotions (an emotion space) common to modalities.
The propos... [more] |
|
ET |
2021-12-11 13:00 |
Online |
Online |
Development of trait-based neural automated essay scoring incorporating multidimensional item response theory Takumi Shibata, Masaki Uto (UEC) ET2021-33 |
In recent years, deep neural network (DNN)-based automated essay scoring (AES) models that can simultaneously predict th... [more] |
ET2021-33 pp.23-28 |
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 |
RISING (3rd) |
2021-11-16 09:30 |
Tokyo |
(Primary: On-site, Secondary: Online) |
Inter-User Distance Estimation in 5G mmWave Cellular Networks Using Deep Learning Mondher Bouazizi, Siyuan Yang, Tomoaki Ohtsuki (Keio Univ.) |
In mmWave massive MIMO system, the distance between each pair of user equipments (UE) is of great importance and conside... [more] |
|
MBE, NC (Joint) |
2021-10-29 11:40 |
Online |
Online |
A numerical study on the relationship between complexity and accuracy of neural networks based on ordinary differential equations Kaoru Esashika, Jun Ohkubo (Saitama Univ.) NC2021-26 |
In recent years, many reports have been published on deep neural networks. The residual networks have contributed to rem... [more] |
NC2021-26 pp.46-50 |
PRMU |
2021-10-09 09:30 |
Online |
Online |
Explaining Adversarial Examples by the Embedding Structure of Data Manifold Hajime Tasaki, Yuji Kaneko, Jinhui Chao (Chuo Univ.) PRMU2021-19 |
It is widely known that adversarial examples cause misclassification in classifiers using deep learning. Inspite of nume... [more] |
PRMU2021-19 pp.17-21 |
SIS, ITE-BCT |
2021-10-08 10:00 |
Online |
Online |
[Tutorial Lecture]
The Past and The Future of Explainable AI Techniques Yoshitaka Kameya (Meijo Univ.) SIS2021-17 |
Machine learning models of high predictive performance, such as deep neural networks and ensemble models, now play a cen... [more] |
SIS2021-17 pp.36-41 |
RECONF |
2021-09-10 09:30 |
Online |
Online |
A Low-Latency Inference of Randomly Wired Convolutional Neural Networks on an FPGA Ryosuke Kuramochi, Hiroki Nakahara (Tokyo Tech) RECONF2021-17 |
Convolutional neural networks (CNNs) are widely used for image processing tasks in both embedded systems and data center... [more] |
RECONF2021-17 pp.1-6 |
PN |
2021-08-30 14:00 |
Online |
Online |
[Invited Lecture]
Optical Link Diagnosis Technology that Applies Deep Learning to DSP Data and its Implementation on an Open Platform Takafumi Tanaka, Tetsuro Inui, Shingo Kawai (NTT) PN2021-16 |
In order to reduce the operational expenditure (OPEX) of optical networks, researches on autonomous optical network oper... [more] |
PN2021-16 p.28 |
AP, SANE, SAT (Joint) |
2021-07-29 12:40 |
Online |
Online |
[Invited Lecture]
Radio Propagation Prediction using Geographical Classification by Clustering and Convolutional Neural Network Tatsuya Nagao, Takahiro Hayashi (KDDI Research) AP2021-36 |
Beyond 5G is expected to play an essential role in the future social infrastructure, and there is a need for a new syste... [more] |
AP2021-36 pp.70-75 |
RCS, SR, NS, SeMI, RCC (Joint) |
2021-07-16 14:30 |
Online |
Online |
Considerations on Accuracy Improvement in Close DOA Estimation with Deep Learning Yuya Kase, Toshihiko Nishimura, Takeo Ohgane, Yasutaka Ogawa, Takanori Sato (Hokkaido Univ.), Yoshihisa Kishiyama (NTT DOCOMO) RCC2021-39 NS2021-55 RCS2021-97 SR2021-39 SeMI2021-28 |
In addition to subspace methods such as MUSIC and ESPRIT, recently,
compressed sensing and deep learning have been appl... [more] |
RCC2021-39 NS2021-55 RCS2021-97 SR2021-39 SeMI2021-28 pp.77-82(RCC), pp.118-123(NS), pp.98-103(RCS), pp.100-105(SR), pp.76-81(SeMI) |
KBSE, IPSJ-SE, SS [detail] |
2021-07-08 15:15 |
Online |
Online (Zoom) |
A Study of Voiceprint Authentication Using Deep Learning of Image Classification Yuki Hiroi, Mengchun Xie, Nobuo Iwasaki, Mitsutoshi Murata, Toru Mori (NIT,Wakayama College) SS2021-7 KBSE2021-19 |
Currently, special fraud targeting the elderly is a problem in Japan. As a countermeasure, it is possible to identify th... [more] |
SS2021-7 KBSE2021-19 pp.37-40 |