Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SP, IPSJ-MUS, IPSJ-SLP [detail] |
2022-06-17 15:00 |
Online |
Online |
Blind Source Separation based on Independent Low-Rank Matrix Analysis using Restricted Boltzmann Machines Shotaro Furuta, Takuya Kishida, Toru Nakashika (UEC) SP2022-8 |
In this paper, we propose a new blind source separation method that combines independent low-rank source separation (ILR... [more] |
SP2022-8 pp.26-29 |
SIS, IPSJ-AVM, ITE-3DMT [detail] |
2019-06-13 11:20 |
Nagasaki |
Fukue Culture Center |
A random number generation method for hardware implemented neural networks Sansei Hori, Hakaru Tamukoh (Kyushu Inst. of Tech.) SIS2019-1 |
This study proposes a hardware oriented random number generation method to implement a stochastically neural networks su... [more] |
SIS2019-1 pp.1-4 |
MBE, NC (Joint) |
2016-03-22 11:25 |
Tokyo |
Tamagawa University |
Construction of Semantic Network Using Restricted Boltzmann Machine Yuichiro Tsutsui, Masafumi Hagiwara (Keio Univ.) NC2015-71 |
In this paper, we propose a new kind of neural network type semantic network utilizing distributed representation. The p... [more] |
NC2015-71 pp.13-18 |
NLC, IPSJ-NL, SP, IPSJ-SLP (Joint) [detail] |
2015-12-02 10:25 |
Aichi |
Nagoya Inst of Tech. |
Simultaneous Modelling of Acoustic, Phonetic, Speaker Features Using Improved Three-Way Restricted Boltzmann Machine Toru Nakashika (UEC), Tetsuya Takiguchi (Kobe Univ.) SP2015-71 |
In this paper, we argue the way of modelling speech signals using improved three-way restricted Boltzmann machine (3WRBM... [more] |
SP2015-71 pp.7-12 |
NC, MBE |
2015-03-16 15:10 |
Tokyo |
Tamagawa University |
A Proposal of Novel Data Detection Method and Its Application to Incremental Learning for RBMs Masahiko Osawa, Masafumi Hagiwara (Keio Univ.) MBE2014-167 NC2014-118 |
Incremental learnings without destruction of the existing memory are often difficult for deep learning, since most of th... [more] |
MBE2014-167 NC2014-118 pp.283-288 |
IBISML |
2015-03-05 16:15 |
Kyoto |
Kyoto University |
Adaptation of Machine Learning Method for Music Structure Analysis Yoshiyuki Kushibe, Toshiaki Takita (Univ. of Tsukuba), Masatoshi Hamanaka (Kyoto Univ.), Sakurako Yazawa, Junichi Hoshino (Univ. of Tsukuba) IBISML2014-89 |
This paper describes the music structure analysis method using machine learning. Music structure analysis is to automati... [more] |
IBISML2014-89 pp.31-38 |
IBISML |
2014-11-17 17:00 |
Aichi |
Nagoya Univ. |
[Poster Presentation]
Feature Extraction for Image Classification using Restricted Boltzmann Machines Reiki Suda, Koujin Takeda (Ibaraki Univ.) IBISML2014-36 |
Learning restricted Boltzmann machines (RBMs) for high-dimensional data using maximum likelihood estimation had been fac... [more] |
IBISML2014-36 pp.9-15 |
IBISML |
2014-11-17 17:00 |
Aichi |
Nagoya Univ. |
[Poster Presentation]
Training Algorithm for Restricted Boltzmann Machines Using Auxiliary Function Approach Norihiro Takamune (Univ. of Tokyo), Hirokazu Kameoka (Univ. of Tokyo/NTT) IBISML2014-56 |
Layerwise pre-training is one of important elements for deep learning, and Restricted Boltzmann Machines (RBMs) is popul... [more] |
IBISML2014-56 pp.161-168 |
IBISML |
2014-11-18 15:00 |
Aichi |
Nagoya Univ. |
[Poster Presentation]
Denoising High-dimensional Sequences with the Bidirectional Recurrent Restricted Boltzmann Machine Shoken Kaneko (Yamaha Co.) IBISML2014-62 |
We propose a probabilistic neural network for modeling high-dimensional sequences with complex non-linearities.
Our mod... [more] |
IBISML2014-62 pp.207-212 |
MBE, NC (Joint) |
2014-10-18 14:50 |
Osaka |
Osaka Electro-Communication University |
Analysis of Learning Characteristics of RBM and Automatic Method for Deciding the Number of Hidden Neurons Masahiko Osawa, Masafumi Hagiwara (Keio Univ.) NC2014-22 |
In this paper,we analyze the learning characteristics of Restricted Boltzmann Machine (RBM) by computer simulation. Then... [more] |
NC2014-22 pp.7-12 |
NLP |
2014-07-01 10:00 |
Miyagi |
Tohoku Univ. |
Learning Restricted Boltzmann Machine with discrete learning parameter Seitaro Shinagawa (Tohoku Univ.), Yoshihiro Hayakawa (SNCT), Shigeo Sato, Takeshi Onomi, Koji Nakajima (Tohoku Univ.) NLP2014-27 |
Recently, the method of Deep Neural Network (DNN) with hierarchical learning has been remarkable for performance to solv... [more] |
NLP2014-27 pp.37-40 |
SP, IPSJ-MUS |
2014-05-25 11:30 |
Tokyo |
|
A joint restricted Boltzmann machine for dictionary learning in sparse-representation-based voice conversion Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) SP2014-34 |
In voice conversion, sparse-representation-based methods have recently been garnering attention because they are, relati... [more] |
SP2014-34 pp.343-348 |
SP, IPSJ-SLP |
2013-12-19 17:15 |
Tokyo |
|
Speaker-dependent conditional restricted Boltzmann machine for voice conversion Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) SP2013-88 |
In this paper, we present a voice conversion (VC) method that utilizes conditional restricted Boltzmann machines (CRBMs)... [more] |
SP2013-88 pp.83-88 |
SP, IPSJ-SLP |
2013-12-20 10:45 |
Tokyo |
|
[Invited Talk]
Acoustic Modeling Using Restricted Boltzmann Machines and Deep Belief Networks for Statistical Parametric Speech Synthesis and Voice Conversion Zhen-Hua Ling, Ling-Hui Chen, Li-Rong Dai (USTC) SP2013-90 |
This paper summarizes our previous work on spectral modeling using restricted Boltzmann machines (RBM) and deep belief n... [more] |
SP2013-90 pp.103-108 |
SP, IPSJ-SLP (Joint) |
2013-07-26 14:20 |
Miyagi |
Soho (togatta spa) |
[Invited Talk]
An Introduction to Deep Learning
-- Restricted Boltzmann Machine and Pre-Training -- Muneki Yasuda (Yamagata Univ.) SP2013-60 |
Deep learnings are learnings on multi-layered learning models.
Deep learnings have achieved astounding success in the f... [more] |
SP2013-60 pp.45-49 |
IBISML |
2012-11-07 15:30 |
Tokyo |
Bunkyo School Building, Tokyo Campus, Tsukuba Univ. |
Regularization of Restricted Boltzmann Machine Learning through entropy minimization Taichi Kiwaki, Takaki Makino, Kazuyuki Aihara (Univ. Tokyo) IBISML2012-48 |
We propose a learning scheme for Restricted Boltzmann Machines (RBMs) that suppresses over-fitting, where the entropy of... [more] |
IBISML2012-48 pp.103-106 |
NC, IPSJ-BIO [detail] |
2011-06-24 16:30 |
Okinawa |
50th Anniversary Memorial Hall, University of the Ryukyus |
Solving POMDPs using Restricted Boltzmann Machines with Echo State Networks Makoto Otsuka, Junichiro Yoshimoto, Stefan Elfwing, Kenji Doya (OIST) NC2011-19 |
A partially observable Markov decision process (POMDP) can be solved in a model-based way using explicit knowledge of th... [more] |
NC2011-19 pp.143-148 |
NC, MBE (Joint) |
2009-03-11 16:35 |
Tokyo |
Tamagawa Univ. |
A Learning Algorithm of Helmholtz Machine with Mean Field Approximation Yuki Aoki (Nara Inst. of Sci and Tech.), Shin-ichi Maeda, Shin Ishii (Kyoto Univ.) NC2008-113 |
It is often required to extract a compact feature of an original high-dimensional datum. Such a compactfeature is useful... [more] |
NC2008-113 pp.57-62 |