Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU |
2020-12-18 11:15 |
Online |
Online |
Supervised disentangled representation learning
-- Disentangling features using classifier -- Shujiro Kuroda, Toshikazu Wada (Wakayama Univ.) PRMU2020-58 |
VAE is a DNN model for unsupervised representation learning. VAE learns to extract features from the input data as laten... [more] |
PRMU2020-58 pp.116-121 |
IBISML |
2020-10-21 09:45 |
Online |
Online |
IBISML2020-18 |
A symbol emergence system is a multi-agent system where each autonomous agent forms internal representations through int... [more] |
IBISML2020-18 pp.34-35 |
PRMU |
2020-09-02 16:30 |
Online |
Online |
Representation Learning using Video Frame Prediction and Contrastive Learning Hidemoto Nakada, Hideki Asoh (AIST) PRMU2020-17 |
The recent development in the unsupervised learning area enabled accuracy in the downstream tasks that equal the one wit... [more] |
PRMU2020-17 pp.59-64 |
IBISML |
2020-03-11 09:20 |
Kyoto |
Kyoto University (Cancelled but technical report was issued) |
Subspace Representation for Graphs Junki Ishikawa, Hiroaki Shiokawa, Kazuhiro Fukui (Tsukuba Univ.) IBISML2019-40 |
In this research, we discuss a representation learning for graph analysis, where a graph is represented by a low dimensi... [more] |
IBISML2019-40 pp.51-57 |
AI |
2020-02-14 16:50 |
Shimane |
Izumo Campus, Shimane University |
A Data Fusion Method Assuming Latent Proxy Variables for Target Variables Yoshihide Nishio, Yasuo Tanida (Synergy Marketing) AI2019-52 |
We propose an analysis method that enables cross-domain prediction and interpretation of consumer behavior, and maintain... [more] |
AI2019-52 pp.55-60 |
NC, MBE |
2019-12-06 15:40 |
Aichi |
Toyohashi Tech |
Prevention of redundant representations and of the black box in stacked autoencoders Masumi Ishikawa (Kyutech) MBE2019-56 NC2019-47 |
Recent progress in deep learning (DL) is remarkable and its recognition capability is said to surpass that of humans. Th... [more] |
MBE2019-56 NC2019-47 pp.67-72 |
NLC, IPSJ-NL, SP, IPSJ-SLP (Joint) [detail] |
2019-12-06 16:25 |
Tokyo |
NHK Science & Technology Research Labs. |
An evaluation of representation learning using phoneme posteriorgrams and data augmentation in speech emotion recognition Shintaro Okada (Nagoya Univ.), Atsushi Ando (Nagoya Univ./NTT), Tomoki Toda (Nagoya Univ.) SP2019-43 |
This paper presents a new speech emotion recognition method based on representation learning and data augmentation.
To ... [more] |
SP2019-43 pp.91-96 |
NLC, IPSJ-DC |
2019-09-28 16:50 |
Tokyo |
Future Corporation |
Semi-supervised learning for sentiment analysis by using Triple-GAN Jincheng Yang, Rui Cao, Jing Bai, Wen Ma, Hiroyuki Shinnou (Ibaraki Univ.) NLC2019-26 |
GAN has become an effective method in the field of image,but in
the field of NLP,It's difficult to design a generation ... [more] |
NLC2019-26 pp.99-102 |
NLC, IPSJ-DC |
2019-09-28 17:30 |
Tokyo |
Future Corporation |
Estimating Distributed Expressions of Unknown Compound Word Using Distributed Expressions of Known Words Ryota Takagi, Kazuhiro Kazama (Wakayama Univ), Takeshi Sakaki (Hotto Link) NLC2019-27 |
In recent years, the distributed expression, which treats the meaning of a word as a low-dimensional vector expression, ... [more] |
NLC2019-27 pp.103-108 |
TL |
2018-12-09 15:00 |
Ehime |
Ehime University |
Duality of Recognition of Time in Japanese and Chinese Viewed from the Chinese Auxiliary Verbs HUI and YAO Tomohiro Ishida, Ting Zhang (TUFS) TL2018-48 |
One of the particular difficulties for Japanese native speakers learning Chinese is use of the auxiliary verbs huì and y... [more] |
TL2018-48 pp.23-28 |
IBISML |
2018-11-05 15:10 |
Hokkaido |
Hokkaido Citizens Activites Center (Kaderu 2.7) |
[Poster Presentation]
Detecting Unlabeled Class by Intentional Clustering using Disentangled Representation Tomoki Fukuma, Fuijo Toriumi (Tokyo Univ.) IBISML2018-85 |
Clustering is ill-defined problem.What you pay attention differs the result coming from clustering and sometimes there a... [more] |
IBISML2018-85 pp.307-312 |
IBISML |
2018-11-05 15:10 |
Hokkaido |
Hokkaido Citizens Activites Center (Kaderu 2.7) |
[Poster Presentation]
A Self-Organization Model Developing Higher Order Units by Self-Test Learning Akira Date, Shunsuke Hanai (Univ. of Miyazaki) IBISML2018-100 |
We have carried out computer simulation studies of a self-organizing network Geman-Davis model in which the number of un... [more] |
IBISML2018-100 pp.419-424 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2018-09-20 09:50 |
Fukuoka |
|
Image-Caption Retrieval by Embedding to Gaussian Distribution Kenta Hama, Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) PRMU2018-38 IBISML2018-15 |
To get distributed representations of words, one has typically embedded words to points.
Recent studies successfully... [more] |
PRMU2018-38 IBISML2018-15 pp.17-20 |
NLC, IPSJ-DC |
2018-09-07 15:30 |
Tokyo |
Seikei University |
[Invited Lecture]
Toru Shimizu (Yahoo Japan) NLC2018-24 |
In this presentation, we report highlights from 56th Annual Meeting of the Association for Computational Linguistics (AC... [more] |
NLC2018-24 p.93 |
EMM |
2018-03-05 15:45 |
Kagoshima |
Naze Community Center (Amami-Shi, Kagoshima) |
[Poster Presentation]
What kind of embedding methods do neural networks learn? Ippei Hamamoto, Masaki Kawamura (Yamaguchi Univ.) EMM2017-83 |
We proposed an embedder, i.e., an embedding method using a layered neural network. The discrete cosine transform (DCT) c... [more] |
EMM2017-83 pp.31-36 |
MBE, NC (Joint) |
2017-11-24 13:25 |
Miyagi |
Tohoku University |
Phased Learning for Distributed Word Representations Considering Synonym Chiaki Yonekura, Masafumi Hagiwara (Keio Univ.) NC2017-28 |
In natural language processing, distributed word representation is one of the representation methods for treating words ... [more] |
NC2017-28 pp.7-12 |
MBE, NC (Joint) |
2017-05-26 13:50 |
Toyama |
Toyama Prefectural Univ. |
A Parallel Forward-Backward Propagation Learning Rule for Auto-Encoder Yoshihiro Ohama, Takayoshi Yoshimura (Toyota CRDL) NC2017-3 |
Auto-encoder is known as a hourglass neural network for acquiring essential representations from multi-dimensional data ... [more] |
NC2017-3 pp.13-18 |
IBISML |
2017-03-06 16:30 |
Tokyo |
Tokyo Institute of Technology |
New Lerning Algorythm of Neural Network using Integral Representation and Kernel Herding Takuo Matsubara, Sho Sonoda, Noboru Murata (Waseda Univ.) IBISML2016-103 |
A new learning algorithm for neural networks that converges at $mathcal{O}(frac{1}{n})$ with respect to model complexity... [more] |
IBISML2016-103 pp.25-31 |
NC, IPSJ-BIO, IBISML, IPSJ-MPS [detail] |
2016-07-06 15:20 |
Okinawa |
Okinawa Institute of Science and Technology |
Feedforward supervised learning for deep neural networks with local competitiveness information Takashi Shinozaki (NICT) NC2016-15 |
This study proposes a novel supervised learning method for deep neural networks that uses feedforward supervisory signal... [more] |
NC2016-15 pp.229-234 |
EA, SP, SIP |
2016-03-29 09:00 |
Oita |
Beppu International Convention Center B-ConPlaza |
[Poster Presentation]
A Study of Indoor-environmental Sound Discrimination Based on Deep Neural Network with Mel-cepstrum Sakiko Mishima, Yukoh Wakabayashi, Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura (Ritsumeikan University) EA2015-121 SIP2015-170 SP2015-149 |
Surveillance systems with a video camera have been utilized for the safety of people. Environmental sound discrimination... [more] |
EA2015-121 SIP2015-170 SP2015-149 pp.305-310 |