Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NC, MBE, NLP, MICT (Joint) [detail] |
2024-01-24 10:00 |
Tokushima |
Naruto University of Education |
Hierarchical lossless compression of high dynamic range images using predictors based on cellular neural networks Seiya Kushi, Kazuki Nakashima, Hideharu Toda (Chukyo Univ.), Tsuyoshi Otake (Tamagawa Univ.), Hisashi Aomori (Chukyo Univ.) NLP2023-85 MICT2023-40 MBE2023-31 |
We have been developing a scalable lossless coding method using cellular neural networks (CNN) as predictors. This metho... [more] |
NLP2023-85 MICT2023-40 MBE2023-31 pp.12-15 |
SIP, IT, RCS |
2024-01-18 11:45 |
Miyagi |
(Primary: On-site, Secondary: Online) |
A Study on Massive MIMO Channel Estimation Based on Sparse Bayesian Learning Using Hierarchical Model Kengo Furuta, Takumi Takahashi, Kenta Ito (Osaka Univ.), Shinsuke Ibi (Doshisha Uni.) IT2023-34 SIP2023-67 RCS2023-209 |
Massive multi-input multi-output (MIMO) channels are known to have pseudo-sparsity in the angular (beam) domain, and it ... [more] |
IT2023-34 SIP2023-67 RCS2023-209 pp.25-30 |
CAS, NLP |
2022-10-20 14:55 |
Niigata |
(Primary: On-site, Secondary: Online) |
Hierarchical Lossless Coding with Arithmetic Coders for Each CNN Predictor Kazuki Nakashima, Ryo Nakazawa, Hideharu Toda, Hisashi Aomori (Chukyo Univ.), Tsuyoshi Otake (Tamagawa Univ.), Ichiro Matsuda, Susumu Itoh (TUS) CAS2022-23 NLP2022-43 |
We have been developing a scalable lossless coding method using the cellular neural networks (CNN) as predictors.
This ... [more] |
CAS2022-23 NLP2022-43 pp.20-24 |
CCS |
2021-11-19 11:10 |
Osaka |
Osaka Univ. (Primary: On-site, Secondary: Online) |
Toward Human Cognition-inspired High-Level Decision Making For Hierarchical Reinforcement Learning Agents Rousslan Fernand Julien Dossa (Kobe Univ.), Takashi Matsubara (Osaka Univ.) CCS2021-28 |
Hierarchical reinforcement learning (HRL) methods aim to leverage the concept of temporal abstraction to efficiently sol... [more] |
CCS2021-28 pp.61-66 |
R |
2019-11-28 13:45 |
Osaka |
Central Electric Club |
A Note on Moment-Based Approximation for Uncertainty Propagation in Hierarchical Models Jiahao Zhang (Hiroshima Univ.), Junjun Zheng (Ritsumeikan Univ.), Hiroyuki Okamura, Tadashi Dohi (Hiroshima Univ.) R2019-43 |
This paper discusses an approximation method for uncertainty propagation in a hierarchical model. The uncertainty propag... [more] |
R2019-43 pp.1-6 |
R |
2019-11-28 16:25 |
Osaka |
Central Electric Club |
Reliability Methodologies for Degradation Predictions Based on Hierarchical Bayesian Modeling and Machine Learning Toru Kaise, Toyohiko Egami (Univ. of Hyogo) R2019-49 |
Degradation processes are significant for making values of reliability.
Particularly, it is known that stochastic model... [more] |
R2019-49 pp.35-38 |
EA, SIP, SP |
2019-03-15 10:25 |
Nagasaki |
i+Land nagasaki (Nagasaki-shi) |
Neural Language Models based on Conditional Hierarchical Recurrent Encoder-Decoder for Multi-Party Conversational Speech Recognition Ryo Masumura, Tomohiro Tanaka, Atsushi Ando, Takanobu Oba, Yushi Aono (NTT) EA2018-131 SIP2018-137 SP2018-93 |
This paper presents fully neural network based language models (LMs) that can leverage long-range conversational context... [more] |
EA2018-131 SIP2018-137 SP2018-93 pp.191-196 |
NC, MBE (Joint) |
2018-10-19 14:25 |
Miyagi |
Tohoku Univ. |
Functional complexity in neuronal network models with hierarchically modular organization Zhixiong Chen, Hideaki Yamamoto, Satoshi Moriya, Katsuya Ide (Tohoku Univ.), Shigeru Kubota (Yamagata Univ.), Shigeo Sato, Ayumi Hirano-Iwata (Tohoku Univ.) NC2018-14 |
Research and development of hardware and architectures that imitate the information processing mechanism of brains is be... [more] |
NC2018-14 pp.7-12 |
SP |
2016-08-24 14:00 |
Kyoto |
ACCMS, Kyoto Univ. |
[Invited Talk]
Unsupervised Music Understanding based on Hierarchical Bayesian Acoustic and Language Models Kazuyoshi Yoshii (Kyoto Univ.) SP2016-29 |
This paper presents a statistical approach to unsupervised music understanding. Our goal is to estimate musical notes fr... [more] |
SP2016-29 pp.13-18 |
NLP |
2014-06-30 16:00 |
Miyagi |
Tohoku Univ. |
Backpropagation learning using inverse function delay-less model Yuta Horiuchi (Tohoku Univ.), Yoshihiro Hayakawa (SNCT), Takeshi Onomi, Koji Nakajima (Tohoku Univ.) NLP2014-25 |
The Inverse function Delayed (ID) model has been proposed as one of novel neural models. ID model has a oscillation capa... [more] |
NLP2014-25 pp.27-30 |
NLP |
2014-01-21 15:40 |
Hokkaido |
Niseko Park Hotel |
Neural Network learning using Inverse Function Delayless Model Yuta Horiuchi (Tohoku Univ.), Yoshihiro Hayakawa (SNCT), Shigeo Sato, Koji Nakajima (Tohoku Univ.) NLP2013-142 |
The Inverse function Delayed (ID) model has been proposed as one of novel neural models. The ID model has an ability of ... [more] |
NLP2013-142 pp.73-76 |
IBISML |
2013-03-05 14:35 |
Aichi |
Nagoya Institute of Technology |
* Yusuke Kishi, Takuma Nakamura, Tatsuhiro Harada, Takashi Matsumoto (Waseda Univ.) IBISML2012-105 |
Infinite Hidden Markov Random Fields have been proposed for image segmentation as a solution to the problem of automatic... [more] |
IBISML2012-105 pp.87-94 |
PRMU, MVE, IPSJ-CVIM (Joint) [detail] |
2013-01-23 09:30 |
Kyoto |
|
Face model creation based on simultaneous execution of hierarchical training-set clustering and common local feature extraction Takayuki Fukui, Toshikazu Wada, Hiroshi Oike, Jun Sakata (Wakayama Univ.) PRMU2012-84 MVE2012-49 |
Face image retrieval based on local features has advantages of short elapsed time and robustness against the occlusions.... [more] |
PRMU2012-84 MVE2012-49 pp.23-28 |
ICD |
2012-12-18 09:30 |
Tokyo |
Tokyo Tech Front |
A Hardware-Implementation-Friendly Algorithm Based on Hierarchical Models for Real-Time Human Action Recognition Kazumi Fukuda, Tadashi Shibata (Univ. of Tokyo) ICD2012-113 |
Naturally modeling the hierarchy and shared features of human actions such as running and jumping, we present a hardware... [more] |
ICD2012-113 pp.85-90 |
IBISML |
2012-11-07 15:30 |
Tokyo |
Bunkyo School Building, Tokyo Campus, Tsukuba Univ. |
Nested-Hierarchical Dirichlet Process Mixtures for Simultaneous Document-Topic Clustering Shoji Tominaga, Masamichi Shimosaka, Rui Fukui, Tomomasa Sato (Univ. of Tokyo) IBISML2012-56 |
In this paper, we propose a nonparametric Bayesian framework for natural language processing (NLP). Our framework is bas... [more] |
IBISML2012-56 pp.157-164 |
MBE, NC (Joint) |
2012-03-14 14:10 |
Tokyo |
Tamagawa University |
Emergence of even-symmetric response property of complex cell by hierarchical Bayesian model Hiroki Yokoyama, Osamu Watanabe (Muroran Inst. Tech.) NC2011-130 |
Neurons in the primary visual cortex (V1) can be classified into two types: simple- and complex-cells. Many statistical ... [more] |
NC2011-130 pp.51-56 |
SP, NLC, IPSJ-SLP [detail] |
2011-12-20 10:30 |
Tokyo |
|
Speaker Verification Using MMAP Adaptation Sangeeta Biswas, Johan Rohdin, Koichi Shinoda, Sadaoki Furui (Tokyo Inst. of Tech.) NLC2011-48 SP2011-93 |
This paper proposes maximum a posteriori (MAP) adaptation of Gaussian mixture models (GMM) using multiple priors for tex... [more] |
NLC2011-48 SP2011-93 pp.133-137 |
IBISML |
2011-11-09 15:45 |
Nara |
Nara Womens Univ. |
An Accuracy Analysis of Latent Variable Estimation with the Maximum Likelihood Estimator Keisuke Yamazaki (Tokyo Inst. of Tech.) IBISML2011-55 |
Hierarchical learning models such as
mixture models and hidden Markov models
are widely used in machine learning and d... [more] |
IBISML2011-55 pp.87-91 |
NC, NLP |
2011-01-24 18:25 |
Hokkaido |
Hokakido Univ. |
Model Adaptation with Bayesian Hierarchical Models Hideki Asoh (AIST) NLP2010-140 NC2010-104 |
Model adaptation is a process of modifying general model which is trained with large amount of training data to adapt a ... [more] |
NLP2010-140 NC2010-104 pp.93-98 |
IBISML |
2010-11-05 15:30 |
Tokyo |
IIS, Univ. of Tokyo |
[Poster Presentation]
Infinite Latent Harmonic Allocation based on Hierarchical Dirichlet Process for Music Signal Analysis Kazuyoshi Yoshii, Masataka Goto (AIST) IBISML2010-86 |
This paper presents a method called the infinite latent harmonic allocation (iLHA) for detecting multiple fundamental fr... [more] |
IBISML2010-86 pp.195-202 |